From 1c556d5689b4c259ee57e46f429d3fc988a8acd7 Mon Sep 17 00:00:00 2001 From: Sim Pi Agent Date: Thu, 24 Sep 2026 19:10:59 +0000 Subject: [PATCH 1/3] docs(library): update best-ai-agent-builders-with-mcp-support --- .../index.mdx | 119 ++++++++++++------ 1 file changed, 80 insertions(+), 39 deletions(-) diff --git a/apps/sim/content/library/best-ai-agent-builders-with-mcp-support/index.mdx b/apps/sim/content/library/best-ai-agent-builders-with-mcp-support/index.mdx index 8c511cddaac..b9c451771b7 100644 --- a/apps/sim/content/library/best-ai-agent-builders-with-mcp-support/index.mdx +++ b/apps/sim/content/library/best-ai-agent-builders-with-mcp-support/index.mdx @@ -3,10 +3,10 @@ slug: best-ai-agent-builders-with-mcp-support title: 'Best AI Agent Builders with MCP Support' description: 'Compare the best AI agent builders with MCP support, including Sim, n8n, Zapier, Make, and Gumloop, across client and server roles, authentication, deployment, and enterprise controls.' date: 2026-09-19 -updated: 2026-09-19 +updated: 2026-09-24 authors: - andrew -readingTime: 14 +readingTime: 16 tags: [AI Agents, MCP, Automation, Open Source, Sim] ogImage: /library/best-ai-agent-builders-with-mcp-support/cover.jpg canonical: https://www.sim.ai/library/best-ai-agent-builders-with-mcp-support @@ -23,54 +23,68 @@ faq: - q: "What does a custom remote MCP server require?" a: "A remote MCP server needs a reachable endpoint that publishes valid tool definitions and handles tool requests. You also need hosting, authentication, and operational monitoring. Sim can publish deployed workflows as remote MCP tools and provides connection configurations for supported clients." - q: "Which platform fits enterprise MCP use?" - a: "Sim and n8n fit enterprises that require source access, self-hosting, or custom workflow control. Zapier, Make, and Gumloop fit enterprises that prefer vendor-managed visual automation, but their governance features and deployment options differ by plan. Before purchasing any platform, verify its current identity controls and audit logging, along with its data residency and governance options." + a: "Sim and n8n are relevant options for enterprises comparing source access, self-hosting, or custom workflow control. Zapier, Make, and Gumloop are relevant options for enterprises comparing vendor-managed visual automation. Dify, Langflow, Flowise, and Microsoft Copilot Studio should remain on the shortlist only after their required MCP roles and production controls are confirmed in current first-party documentation. Governance features, deployment options, and MCP availability may vary by product and plan. Before purchasing any platform, verify its current identity controls and audit logging, along with its data residency and governance options." --- ## TL;DR -- **Sim** consumes MCP tools and exposes deployed workflows as MCP tools. Its open-source codebase and multi-model agent workspace suit buyers building custom agents. +- **Sim** [consumes MCP tools](https://docs.sim.ai/agents/mcp) and exposes deployed workflows as MCP tools. Its open-source codebase and multi-model agent workspace suit buyers building custom agents that need flexible model and deployment options. - **n8n** [supports both MCP patterns](https://docs.n8n.io/integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.toolmcp). It fits technical users who want [low-code workflow control and self-hosting](https://n8n.io/). - **Zapier** [connects AI clients to app actions through managed MCP servers](https://docs.zapier.com/mcp/home). It fits no-code users already working within Zapier's integration catalog. - **Make** [supports consuming MCP tools](https://apps.make.com/c5ZhYquO55e90hoCJ0rzt) and [exposing scenarios to AI clients](https://help.make.com/make-mcp-server). It fits visual builders who want granular automation control. -- **Gumloop** [supports both MCP patterns](https://docs.gumloop.com/nodes/mcp/custom_mcp_servers) for AI-focused workflows. It fits operations users who want [agent automation with limited coding](https://docs.gumloop.com/). +- **Gumloop** supports [consuming tools from custom MCP servers](https://docs.gumloop.com/nodes/mcp/custom_mcp_servers) and [making workflows and agents available through its MCP server](https://docs.gumloop.com/mcp-server/overview). It fits operations users who want [agent automation with limited coding](https://docs.gumloop.com/). ## What Model Context Protocol support actually means for agent builders [Model Context Protocol](https://modelcontextprotocol.io/) lets an AI application discover and call tools through a shared interface. An MCP tool might search a database, update a CRM record, or run an automation. The protocol standardizes how the AI application finds that tool, describes its inputs, and receives its output. -An MCP client consumes tools published by external MCP servers. For example, an agent builder may connect to a remote server and let its agents call the server's tools. [Sim](https://docs.sim.ai/agents/mcp), [n8n](https://docs.n8n.io/integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.toolmcp), [Make](https://apps.make.com/c5ZhYquO55e90hoCJ0rzt), and [Gumloop](https://docs.gumloop.com/nodes/mcp/custom_mcp_servers) provide ways to connect workflows or agents to external MCP tools. Supported transports and authentication methods vary by platform. +An MCP client consumes tools published by external MCP servers. For example, an agent builder may connect to a remote server and let its agents call the server's tools. [Sim](https://docs.sim.ai/agents/mcp), [n8n](https://docs.n8n.io/integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.toolmcp), [Make](https://apps.make.com/c5ZhYquO55e90hoCJ0rzt), and [Gumloop](https://docs.gumloop.com/nodes/mcp/custom_mcp_servers) provide ways to connect workflows or agents to external MCP tools. Supported transports and authentication methods vary by platform. Buyers should verify whether each product supports the transport required by the intended MCP server or client, rather than treating all MCP integrations as interchangeable. An MCP server publishes tools that other applications can call. Sim can expose deployed workflows as MCP tools and connect them to supported clients such as Claude Desktop, Cursor, and VS Code. The [Sim MCP deployment documentation](https://docs.sim.ai/workflows/deployment/mcp) covers its supported connection configurations. [n8n can expose selected workflows through its MCP Server Trigger](https://docs.n8n.io/integrations/builtin/core-nodes/n8n-nodes-langchain.mcptrigger). [Make](https://help.make.com/get-started-with-make-mcp-server) and [Gumloop](https://docs.gumloop.com/mcp-server/overview) can make workflows available to compatible clients. [Zapier's MCP offering gives AI clients access to configured app actions](https://help.zapier.com/hc/en-us/articles/36265551472781-Manage-tools-for-your-Zapier-MCP-server). That approach differs from publishing any existing Zap as a custom MCP tool. Verify whether each platform consumes external MCP tools, publishes its own tools, or supports both roles before comparing products. A builder that consumes MCP tools can add external capabilities to its own agents, but other AI clients cannot necessarily call the builder's workflows. A builder that publishes workflows may serve Claude or Cursor without supporting external MCP tools inside its own agents. -Buyers should also compare authentication, model choice, deployment, enterprise controls, and coding requirements. Authentication may rely on static credentials, OAuth, or platform-managed access. Deployment determines whether you can use a hosted endpoint or run the platform on your own infrastructure. When MCP tools can change business data, access policies and execution logs help administrators control and review those actions. Visual platforms reduce routine configuration work, but advanced tools and authentication may still require code. The broader [AI workflow automation buyer's checklist](https://www.sim.ai/library/ai-workflow-automation-platform-buyers-checklist) explains how to evaluate those operational requirements. +Buyers should also compare transport, authentication, model choice, deployment, human approval, observability, enterprise controls, and coding requirements. Transport determines how the client reaches the MCP server, while authentication determines who may connect. Authentication may rely on static credentials, OAuth, or platform-managed access. Deployment determines whether you can use a hosted endpoint or run the platform on your own infrastructure. When MCP tools can change business data, access policies determine who can run them, human approval can pause sensitive actions, and execution logs let administrators review what happened. Visual platforms reduce routine configuration work, but advanced tools and authentication may still require code. The broader [AI workflow automation buyer's checklist](https://www.sim.ai/library/ai-workflow-automation-platform-buyers-checklist) explains how to evaluate those operational requirements. + +## How these MCP agent builders were evaluated + +The comparison uses first-party product documentation to verify whether each platform can consume external MCP tools, publish capabilities to MCP clients, or do both. It also considers authentication, supported deployment models, model choice, enterprise administration, coding requirements, human approval options, and execution visibility. A product's inclusion does not imply that every feature is available on every plan. + +Product interfaces, plan limits, and MCP implementations can change. Verify material purchasing requirements in the linked documentation and test them in the intended deployment environment. ## Comparison table: AI agent builders with MCP support +### Evaluation methodology + +This comparison uses linked first-party product documentation for product-specific capabilities. It treats consuming external MCP tools and publishing workflows or actions as MCP tools as separate capabilities. The review also checks transport, authentication, deployment, model choice, enterprise controls, human approval, observability, and coding requirements. A field is marked "Unclear" when the reviewed first-party documentation does not establish the capability; it is not inferred from general AI, API, or automation features. Preview, beta, and plan-dependent features should be validated with the vendor before purchase. + The table separates platforms that consume external MCP tools from those that make workflows callable by MCP clients. -| Platform | MCP client support | Exposes workflows as MCP tools | Authentication | Model support | Deployment options | Enterprise controls | Coding required | Best-fit buyer | -| --- | --- | --- | --- | --- | --- | --- | --- | --- | -| **Sim** | [Yes](https://docs.sim.ai/agents/mcp) | [Yes, deployed workflows](https://docs.sim.ai/workflows/deployment/mcp) | API keys and provider credentials | Multi-model and BYOK | [Cloud or self-hosted](https://docs.sim.ai/platform/self-hosting) | [Enterprise access controls](https://docs.sim.ai/platform/enterprise) and self-hosting | Low-code, code optional | Teams building custom, portable agents | -| **n8n** | [Yes](https://docs.n8n.io/integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.toolmcp) | [Yes](https://docs.n8n.io/integrations/builtin/core-nodes/n8n-nodes-langchain.mcptrigger) | [Bearer, header, or OAuth authentication](https://docs.n8n.io/integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.toolmcp) | [Multiple model providers](https://n8n.io/) | [Cloud or self-hosted](https://n8n.io/) | [SSO, role controls, and audit features vary by plan](https://n8n.io/pricing/) | [Low-code](https://n8n.io/) | Technical teams needing workflow control | -| **Zapier** | [Yes, through its MCP Client integration](https://help.zapier.com/hc/en-us/articles/38777069364109-Connect-remote-MCP-servers-to-Zapier-using-MCP-Client) | [Exposes selected app actions rather than existing Zaps](https://help.zapier.com/hc/en-us/articles/36265551472781-Manage-tools-for-your-Zapier-MCP-server) | [OAuth and managed connections](https://docs.zapier.com/mcp/home) | Managed within Zapier products | [Managed cloud](https://docs.zapier.com/mcp/home) | [Admin and governance features vary by plan](https://zapier.com/pricing) | [No-code](https://zapier.com/mcp) | Buyers using Zapier's app ecosystem | -| **Make** | [Yes](https://apps.make.com/c5ZhYquO55e90hoCJ0rzt) | [Yes, scenarios](https://help.make.com/get-started-with-make-mcp-server) | [Tokens, OAuth, and managed connections](https://help.make.com/mcp-toolboxes) | [Multiple providers through integrations](https://www.make.com/) | [Managed cloud](https://www.make.com/) | [Administration features vary by plan](https://www.make.com/en/pricing) | [No-code to low-code](https://www.make.com/en/pricing) | Visual automation users needing granular scenarios | -| **Gumloop** | [Yes](https://docs.gumloop.com/nodes/mcp/custom_mcp_servers) | [Yes](https://docs.gumloop.com/mcp-server/overview) | [API keys, OAuth, and managed connections](https://docs.gumloop.com/mcp-server/overview) | [Multi-model](https://docs.gumloop.com/core-concepts/ai_models) | [Managed cloud](https://docs.gumloop.com/) | [Enterprise identity controls](https://docs.gumloop.com/enterprise-features/sso_saml_scim) | [No-code](https://docs.gumloop.com/) | Operations teams building AI-focused automations | +| Platform | MCP client support | Publishes workflows or actions as MCP tools | Transport | Authentication | Deployment | Model choice | Enterprise controls | Human approval | Observability | Coding requirements | +| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | +| **Sim** | [Yes](https://docs.sim.ai/agents/mcp) | [Yes, deployed workflows](https://docs.sim.ai/workflows/deployment/mcp) | See the [current deployment configurations](https://docs.sim.ai/workflows/deployment/mcp) | See the [current deployment guide](https://docs.sim.ai/workflows/deployment/mcp) | [Hosted or self-hosted](https://docs.sim.ai/platform/self-hosting) | Hosted multi-model access and BYOK; local-model workflows require [Enterprise access](https://docs.sim.ai/platform/enterprise) | [Enterprise controls](https://docs.sim.ai/platform/enterprise) and self-hosting | Available, but the reviewed MCP documentation does not establish MCP-specific approval behavior | Run logs are available, but the reviewed MCP documentation does not establish MCP-specific logging coverage | Low-code; technical work may be needed for custom integrations or self-hosting | +| **n8n** | [Yes](https://docs.n8n.io/integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.toolmcp) | [Yes](https://docs.n8n.io/integrations/builtin/core-nodes/n8n-nodes-langchain.mcptrigger) | Confirm against the [client](https://docs.n8n.io/integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.toolmcp) and [server](https://docs.n8n.io/integrations/builtin/core-nodes/n8n-nodes-langchain.mcptrigger) node documentation | [Bearer, header, or OAuth, depending on the node](https://docs.n8n.io/integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.toolmcp) | [Cloud or self-hosted](https://n8n.io/) | [Multiple model providers](https://n8n.io/) | [Features vary by plan](https://n8n.io/pricing/) | Unclear from the reviewed first-party MCP documentation | Execution visibility should be tested for the selected MCP node | [Low-code, with code nodes available](https://docs.n8n.io/build/code-in-n8n/using-the-code-node) | +| **Zapier** | [Yes](https://help.zapier.com/hc/en-us/articles/38777069364109-Connect-remote-MCP-servers-to-Zapier-using-MCP-Client) | [Selected app actions, not arbitrary existing Zaps](https://help.zapier.com/hc/en-us/articles/36265551472781-Manage-tools-for-your-Zapier-MCP-server) | Unclear from the reviewed first-party documentation | [Managed connections and authorization](https://docs.zapier.com/mcp/home) | [Managed cloud](https://docs.zapier.com/mcp/home) | Product-dependent | [Features vary by plan](https://zapier.com/pricing) | Unclear from the reviewed first-party MCP documentation | Unclear from the reviewed first-party MCP documentation | [No-code configuration](https://zapier.com/mcp) | +| **Make** | [Yes](https://apps.make.com/c5ZhYquO55e90hoCJ0rzt) | [Yes, eligible scenarios](https://help.make.com/get-started-with-make-mcp-server) | Unclear from the reviewed first-party documentation | [Configured connections and toolbox access](https://help.make.com/mcp-toolboxes) | [Managed cloud](https://www.make.com/) | [Multiple providers through integrations](https://www.make.com/) | [Features vary by plan](https://www.make.com/en/pricing) | Unclear from the reviewed first-party MCP documentation | Unclear from the reviewed first-party MCP documentation | [No-code to low-code](https://www.make.com/en/pricing) | +| **Gumloop** | [Yes](https://docs.gumloop.com/nodes/mcp/custom_mcp_servers) | [Yes](https://docs.gumloop.com/mcp-server/overview) | Unclear from the reviewed first-party documentation | See the [MCP server documentation](https://docs.gumloop.com/mcp-server/overview) | [Managed cloud](https://docs.gumloop.com/) | [Multiple models](https://docs.gumloop.com/core-concepts/ai_models) | [Enterprise identity controls](https://docs.gumloop.com/enterprise-features/sso_saml_scim) | Unclear from the reviewed first-party MCP documentation | Unclear from the reviewed first-party MCP documentation | [No-code builder](https://docs.gumloop.com/core-concepts/workbooks) | +| **Dify** | Not verified from reviewed first-party documentation | Not verified from reviewed first-party documentation | Unclear | Unclear | Unclear | Unclear | Unclear | Unclear | Unclear | Unclear | +| **Langflow** | Not verified from reviewed first-party documentation | Not verified from reviewed first-party documentation | Unclear | Unclear | Unclear | Unclear | Unclear | Unclear | Unclear | Unclear | +| **Flowise** | Not verified from reviewed first-party documentation | Not verified from reviewed first-party documentation | Unclear | Unclear | Unclear | Unclear | Unclear | Unclear | Unclear | Unclear | +| **Microsoft Copilot Studio** | Not verified from reviewed first-party documentation | Not verified from reviewed first-party documentation | Unclear | Unclear | Unclear | Unclear | Unclear | Unclear | Unclear | Unclear | -Authentication methods and enterprise controls can vary by plan and MCP connection type. Buyers should confirm current limits before choosing a production deployment. +Authentication methods, enterprise controls, human approval features, and observability can vary by plan and MCP connection type. During evaluation, record the supported transport, credential method, approval behavior, and execution data available for each product. Buyers should confirm current limits before choosing a production deployment. ### Sim -Sim is an open-source, multi-model workspace for building custom agents with specific tools, models, and data sources. You construct and deploy your own workflows rather than start with a single ready-made assistant. The open-source code lets technical buyers inspect and modify the software and operate a [self-hosted deployment](https://docs.sim.ai/platform/self-hosting). Teams comparing source access and deployment rights can also read this guide to [open-source AI agent frameworks](https://www.sim.ai/library/best-open-source-ai-agent-frameworks). +Sim is an open, extensible, multi-model agent workspace for building custom agents with specific tools, models, and data sources. You construct and deploy your own workflows rather than start with a single ready-made assistant. The open-source code lets technical buyers inspect and modify the software and operate a [self-hosted deployment](https://docs.sim.ai/platform/self-hosting). Teams comparing source access and deployment rights can also read this guide to [open-source AI agent frameworks](https://www.sim.ai/library/best-open-source-ai-agent-frameworks). -Sim can turn a deployed workflow into a tool that other applications call through an MCP server. After you create a server and add the workflow as a tool, Sim provides [connection configurations for supported MCP clients](https://docs.sim.ai/workflows/deployment/mcp). Supported clients include Cursor, Codex, Claude Code, Claude Desktop, VS Code, and Sim itself. Each client can then invoke the workflow through the tool interface instead of reproducing its logic locally. +Sim can [consume tools from external MCP servers](https://docs.sim.ai/agents/mcp) and turn a deployed workflow into a tool that other applications call through an MCP server. After you create a server and add the workflow as a tool, Sim provides [connection configurations for supported MCP clients](https://docs.sim.ai/workflows/deployment/mcp). Supported clients include Cursor, Codex, Claude Code, Claude Desktop, VS Code, and Sim itself. Each client can then invoke the workflow through the tool interface instead of reproducing its logic locally. -Sim supports hosted models and bring-your-own-key access for connecting a provider account. Model and deployment availability can vary by plan and environment, so buyers should verify current terms for their intended setup. The [BYOK and multi-model agent builder guide](https://www.sim.ai/library/byok-multi-model-ai-agent-builder) covers the tradeoffs behind provider choice. +Sim supports hosted model access and bring-your-own-key connections for provider accounts. Local-model workflows are not available on regular plans; they require [Enterprise access](https://docs.sim.ai/platform/enterprise). Model and deployment availability can vary by plan and environment, so buyers should verify current terms for their intended setup. The [BYOK and multi-model agent builder guide](https://www.sim.ai/library/byok-multi-model-ai-agent-builder) covers the tradeoffs behind provider choice. -**Best for.** Sim fits technical buyers who want to build custom, multi-model agents and expose their workflows to several MCP clients. It also suits buyers who value access to source code and deployment flexibility. +**Best for:** Sim fits technical buyers who want to build custom, multi-model agents and expose their workflows to several MCP clients. It also suits buyers who need source access or the option to self-host. -**Pros.** Sim combines agent construction, workflow deployment, and MCP tool exposure in one workspace. Multi-model access reduces dependence on one model provider, and client-specific configurations simplify connections to common coding and assistant applications. +**Pros.** Sim lets buyers construct agents, deploy workflows, consume external MCP tools, and expose deployed workflows as MCP tools in one workspace. Multi-model access reduces dependence on one model provider, and client-specific configurations simplify connections to common coding and assistant applications. **Cons.** Buyers seeking a ready-made assistant may find Sim broader than necessary. Complex custom integrations and self-hosted deployments still require technical ownership. @@ -95,12 +109,12 @@ Authentication depends on the MCP node and server configuration. The MCP Client **Cons** -- Complex agents can become difficult to test and maintain as node counts grow. +- Large n8n workflows can require more testing and maintenance because each added node introduces another configuration, data mapping, or execution path to review. - Self-hosting requires operational knowledge. - Custom nodes, unsupported APIs, and advanced transformations may require code. - [Enterprise governance features depend on the selected plan](https://n8n.io/pricing/). -**Pricing:** [n8n offers self-hosted and paid cloud options, with cloud pricing based on workflow executions](https://n8n.io/pricing/). Buyers should compare execution limits because agent loops and tool calls can increase usage quickly. +**Pricing:** [n8n offers self-hosted and paid cloud options, with cloud pricing based on workflow executions](https://n8n.io/pricing/). Buyers should compare execution limits against a representative agent workflow because loops and repeated tool calls can increase the number of executions. ### Zapier @@ -112,13 +126,13 @@ Zapier also supports consuming remote MCP tools through its [MCP Client integrat **Pros:** [Zapier handles MCP hosting, credentials, and connection setup](https://docs.zapier.com/mcp/home). Its integration catalog lets agents use configured actions in supported business applications. [Action-level configuration](https://help.zapier.com/hc/en-us/articles/36265551472781-Manage-tools-for-your-Zapier-MCP-server) also limits which capabilities an MCP client can invoke. -**Cons:** Zapier offers less control over server behavior, deployment, and custom tool logic than open-source or developer-focused platforms. Zapier MCP is vendor-hosted, and advanced workflows remain subject to Zapier's product limits. +**Cons:** Zapier manages MCP hosting and does not provide the source access or self-hosted deployment options offered by open-source platforms in this comparison. Buyers who need custom tool logic should confirm whether Zapier's supported actions and configuration options cover the intended workflow. Zapier MCP is vendor-hosted, and advanced workflows remain subject to Zapier's product limits. **Pricing:** [Zapier uses plan-based pricing](https://zapier.com/pricing), and MCP-triggered actions may count toward applicable usage limits. Buyers should confirm current MCP access and task allowances for their chosen plan. ### Make -Make suits users who want visual control over how an AI agent moves data and calls tools. Its [visual scenario editor](https://www.make.com/) displays each step and its associated filters or data mappings. Buyers can use that detail to configure branching and transformations within a scenario. +Make suits buyers who want visual control over how an AI agent moves data and calls tools. Its [visual scenario editor](https://www.make.com/) displays each step and its associated filters or data mappings. Buyers can use that detail to configure branching and transformations within a scenario. Make supports both MCP directions. Its [MCP Client app](https://apps.make.com/c5ZhYquO55e90hoCJ0rzt) can connect scenarios to external MCP servers and call their available tools. Make can also [expose eligible scenarios through its MCP server](https://help.make.com/get-started-with-make-mcp-server) so supported AI clients can run them as tools. Authentication relies on configured connections and access controls, while each scenario defines the actions an AI client can reach. @@ -126,13 +140,13 @@ Make supports both MCP directions. Its [MCP Client app](https://apps.make.com/c5 **Pros:** The visual canvas makes branching logic and data transformations easier to inspect. Make also provides an integration catalog and supports both [consuming MCP tools](https://apps.make.com/c5ZhYquO55e90hoCJ0rzt) and [making scenarios callable through MCP](https://help.make.com/mcp-toolboxes). -**Cons:** Complex scenarios can become difficult to maintain as routes and mappings multiply. Standard integrations require little coding, but custom APIs, JSON payloads, and unsupported authentication methods may require technical knowledge. Make is a managed cloud platform rather than a self-hosted open-source platform such as Sim or n8n. +**Cons:** Scenarios require more maintenance as routes and mappings multiply because each branch adds configuration that buyers must test and update. Standard integrations require little coding, but custom APIs, JSON payloads, and unsupported authentication methods may require technical knowledge. Make is a managed cloud platform rather than a self-hosted open-source platform such as Sim or n8n. **Pricing:** [Make offers a free plan and paid tiers based on usage credits](https://www.make.com/en/pricing). Scenario module actions count toward credits, so buyers should estimate costs using expected agent call volume. ### Gumloop -Gumloop gives operations and AI teams a [no-code environment for building agent-driven automations](https://docs.gumloop.com/). Its visual workflows center on AI tasks and actions across connected business applications. +Gumloop gives operations and AI users a [no-code environment for building agent-driven automations](https://docs.gumloop.com/). Its visual workflows center on AI tasks and actions across connected business applications. Gumloop supports both sides of MCP. Workflows can [call tools from external MCP servers](https://docs.gumloop.com/nodes/mcp/custom_mcp_servers), and the [Gumloop MCP server](https://docs.gumloop.com/mcp-server/overview) lets compatible clients manage and trigger workflows and agents. The [visual builder](https://docs.gumloop.com/core-concepts/workbooks) removes most coding requirements, although custom APIs and unusual authentication flows may still need technical work. @@ -140,20 +154,20 @@ Gumloop supports both sides of MCP. Workflows can [call tools from external MCP **Pros:** Gumloop combines [no-code workflow design](https://docs.gumloop.com/core-concepts/workbooks) with AI-focused nodes and [reusable subflows](https://docs.gumloop.com/core-concepts/subflows). Its MCP client and server capabilities support agents that consume external tools or provide automations to other MCP clients. -**Cons:** Gumloop focuses more narrowly on AI workflows than broad automation platforms such as n8n, Zapier, and Make. Buyers with large libraries of conventional business automations should compare connector coverage before migrating. Deployment and infrastructure requirements may also matter more to developer-led or regulated organizations. +**Cons:** Gumloop centers its product on AI workflows, while n8n, Zapier, and Make also serve broader business automation use cases. Buyers with large libraries of conventional business automations should compare connector coverage before migrating. Buyers that require self-hosting, private-network access, or specific data-residency controls should verify whether Gumloop's available deployment options meet those requirements. **Pricing:** [Gumloop bills agent chats and workflow runs with credits](https://docs.gumloop.com/core-concepts/credits). Buyers should check its [current pricing page](https://www.gumloop.com/pricing) for workflow, collaboration, and enterprise terms before estimating production costs. ## How to expose a Sim workflow as an MCP tool -Sim exposes a workflow through MCP in four steps. +You can expose a deployed Sim workflow as an MCP tool in four steps. 1. Create an MCP server in Sim. The server groups the workflow tools that external clients can call. 2. Deploy the workflow you want to expose. Deployment creates a callable version of the workflow rather than exposing an unpublished draft. 3. Add the deployed workflow to the MCP server as a tool. Give the tool a clear name and description so the connected model can determine when to call it. 4. Copy the connection configuration that Sim provides for Cursor, Codex, Claude Code, Claude Desktop, VS Code, or Sim. The client can then discover the tool and invoke the workflow with the required inputs. -Authentication settings control who can connect to the MCP server. Use the configuration and credentials Sim provides, and avoid placing sensitive credentials directly inside workflow prompts. A remote client must also have network access to the deployed MCP endpoint. A self-hosted environment may require network routing and firewall configuration so the client can reach the MCP endpoint. +Authentication settings determine which clients can connect to the MCP server. Use the configuration and credentials Sim provides, and avoid placing sensitive credentials directly inside workflow prompts. A remote client must also have network access to the deployed MCP endpoint. A self-hosted environment may require network routing and firewall configuration so the client can reach the MCP endpoint. Sim's [MCP deployment guide](https://docs.sim.ai/workflows/deployment/mcp) provides the current client-specific configuration fields, authentication instructions, and deployment details. @@ -163,22 +177,49 @@ Choose MCP client support when your agent needs to call tools hosted elsewhere. Choose MCP server support when external assistants need to call your workflow. For example, you might package an approval process or data lookup as a reusable tool for Cursor, Claude Desktop, or another MCP client. Buyers should verify that the platform can deploy remote endpoints, define tool inputs, and authenticate incoming requests. -Choose a platform that supports both patterns when agents must consume external tools and provide capabilities to other clients. For example, an internal research agent could query third-party data through MCP and expose its completed report workflow as another MCP tool. A platform that handles both roles can keep tool consumption and workflow publishing in the same workspace. - -Enterprise requirements can narrow the choice. Regulated buyers should verify identity controls such as SSO and role-based access. They should also examine audit logs and policies for secrets and data retention. Self-hosting matters when company policy prevents workflows or credentials from running in a vendor-managed cloud. - -Coding requirements determine who can maintain the deployment. Ops users benefit from visual tool configuration and managed authentication. Developers may prefer low-code or open-source platforms when they need custom server logic, private network access, or control over deployment. Before committing, test authentication and logging with a representative workflow. A feature checklist cannot show how much configuration a specific connection requires. The guide to the [best no-code and low-code AI agent builders](https://www.sim.ai/library/best-no-code-ai-agent-builders-2026) provides another view of this maintenance tradeoff. - -## Why Sim fits teams building custom agents beyond a single assistant +Choose a platform that supports both patterns when your agents must consume external tools and provide capabilities to other clients. For example, an internal research agent could query third-party data through MCP and expose its completed report workflow as another MCP tool. A platform that handles both roles can keep tool consumption and workflow publishing in the same workspace. + +Enterprise requirements can eliminate products that lack the required identity, audit, deployment, or data controls. Buyers with regulatory requirements should verify identity controls such as SSO and role-based access. They should also test whether audit logs record MCP connections, tool calls, approvals, errors, and the identity responsible for each action. Policies for secrets and data retention should cover the information passed through MCP tools. Self-hosting matters when company policy prevents workflows or credentials from running in a vendor-managed cloud. + +Coding requirements determine who can maintain the deployment. Ops users benefit from visual tool configuration and managed authentication. Developers may prefer low-code or open-source platforms when they need custom server logic, private network access, or control over deployment. Before committing, test authentication and logging with a representative workflow. A documented feature may still require unsupported authentication work, custom input mapping, or network configuration in a real deployment. For a broader comparison of maintenance requirements, the guide to the [best no-code and low-code AI agent builders](https://www.sim.ai/library/best-no-code-ai-agent-builders-2026) provides another view of this maintenance tradeoff. + +## Practical MCP testing checklist + +Before selecting a platform, test a representative workflow rather than relying only on feature labels: + +- Confirm whether the platform is acting as an MCP client, an MCP server, or both. +- Connect through every transport required by the intended client and deployment environment. +- Test successful authentication, expired credentials, revoked credentials, and insufficient permissions. +- Verify that credentials and tokens are issued for the intended MCP server rather than passed through from another service; the [MCP security guidance forbids token passthrough](https://modelcontextprotocol.io/docs/tutorials/security/security_best_practices). +- Check that OAuth discovery and redirects cannot reach private, loopback, or cloud metadata addresses, following the [MCP guidance on server-side request forgery](https://modelcontextprotocol.io/docs/tutorials/security/security_best_practices). +- Review the discovered tool names, descriptions, and input schemas for ambiguity or excessive permissions. +- Run valid, malformed, oversized, and unauthorized tool calls and inspect the returned errors. +- Require human approval for at least one sensitive write action and confirm that rejecting or abandoning the request leaves no partial changes. +- Confirm that logs identify the user or agent, selected tool, inputs permitted for logging, result, failure, and approval outcome. +- Test network interruption, timeout, duplicate submission, and retry behavior with a non-destructive workflow. +- Verify that a remote client can reach the production endpoint through the intended proxy, firewall, and load balancer. +- Confirm plan limits, preview or beta status, data retention, identity controls, and production support with the vendor. +- Authenticate with the production credential method and verify how credentials are stored and rotated. +- Inspect the tool name, description, and input schema that the model receives. +- Test the required model provider and verify any plan restrictions, including Enterprise access for Sim workflows that use local models. +- Confirm whether the platform can run in the required cloud, self-hosted, or private-network environment. +- Estimate usage with a realistic number of agent loops and tool calls rather than a single successful run. +- Ask the intended maintainer to modify the workflow and recover from a failed execution. +- Verify identity, role, audit, retention, and data-residency controls against current plan documentation. +- Verify that unauthorized users and clients cannot discover or invoke restricted tools. +- Check whether secrets are stored outside prompts and whether logs redact sensitive values. +- Repeat the test after publishing a workflow update to confirm that existing MCP clients continue to work. + +## Why Sim fits buyers building custom agents beyond a single assistant Sim fits buyers who need custom agents with tailored access to company tools and data. Its open-source codebase supports [self-hosting and modification](https://docs.sim.ai/platform/self-hosting). Multi-model support lets buyers configure workflows with more than one model provider. -Sim provides blocks and logs for reviewing outputs, approving runs, and inspecting execution. Human-in-the-loop blocks can pause a run for approval, and guardrails can restrict inputs or outputs. Evaluator blocks assess results against defined criteria. Wait blocks suspend execution, while run logs support debugging and review. +Sim provides workflow controls for review, approval, evaluation, waiting, and post-run inspection. Buyers should test these controls with the intended MCP workflow and confirm that the resulting logs capture the tool call, approval outcome, and execution details required by their policies. -Sim makes the most sense when developers or technical operators will extend, deploy, and govern the agent workspace. Buyers seeking pure no-code automation with minimal engineering involvement may find Zapier or Gumloop easier to adopt. Teams centered on general workflow automation and self-hosting should also compare n8n before deciding. +Sim best fits buyers with developers or technical operators who can extend, deploy, and govern the agent workspace. Buyers seeking pure no-code automation with minimal engineering involvement may find Zapier or Gumloop easier to adopt. Buyers focused on general workflow automation and self-hosting should also compare n8n before deciding. ## Conclusion Choose an MCP agent builder by confirming whether it consumes external tools, exposes workflows to MCP clients, or supports both roles. Then compare authentication, deployment, governance, and coding requirements. -Sim fits buyers who want an open-source, multi-model workspace for building custom agents and exposing deployed workflows as MCP tools. Buyers focused on familiar no-code automation may prefer another platform. Use the comparison table to identify suitable platforms. If Sim matches your requirements, follow [Sim's MCP deployment guide](https://docs.sim.ai/workflows/deployment/mcp) for setup instructions. +Sim fits buyers who want an open, extensible, multi-model agent workspace that can [consume external MCP tools](https://docs.sim.ai/agents/mcp) and [expose deployed workflows as reusable MCP tools](https://docs.sim.ai/workflows/deployment/mcp). Buyers focused on familiar no-code automation may prefer another platform. Use the comparison table to create a shortlist, then test each candidate with the same workflow, authentication method, approval requirement, and logging checks. If Sim matches your requirements, follow [Sim's MCP deployment guide](https://docs.sim.ai/workflows/deployment/mcp) for setup instructions. From 3bbf5274a3199adb64cb124e6b4792f275aac41b Mon Sep 17 00:00:00 2001 From: Sim Pi Agent Date: Thu, 24 Sep 2026 19:17:28 +0000 Subject: [PATCH 2/3] Pi Babysit: address PR #8251 feedback --- .../best-ai-agent-builders-with-mcp-support/index.mdx | 11 +++-------- 1 file changed, 3 insertions(+), 8 deletions(-) diff --git a/apps/sim/content/library/best-ai-agent-builders-with-mcp-support/index.mdx b/apps/sim/content/library/best-ai-agent-builders-with-mcp-support/index.mdx index b9c451771b7..6a2f452afd6 100644 --- a/apps/sim/content/library/best-ai-agent-builders-with-mcp-support/index.mdx +++ b/apps/sim/content/library/best-ai-agent-builders-with-mcp-support/index.mdx @@ -62,15 +62,11 @@ The table separates platforms that consume external MCP tools from those that ma | Platform | MCP client support | Publishes workflows or actions as MCP tools | Transport | Authentication | Deployment | Model choice | Enterprise controls | Human approval | Observability | Coding requirements | | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | -| **Sim** | [Yes](https://docs.sim.ai/agents/mcp) | [Yes, deployed workflows](https://docs.sim.ai/workflows/deployment/mcp) | See the [current deployment configurations](https://docs.sim.ai/workflows/deployment/mcp) | See the [current deployment guide](https://docs.sim.ai/workflows/deployment/mcp) | [Hosted or self-hosted](https://docs.sim.ai/platform/self-hosting) | Hosted multi-model access and BYOK; local-model workflows require [Enterprise access](https://docs.sim.ai/platform/enterprise) | [Enterprise controls](https://docs.sim.ai/platform/enterprise) and self-hosting | Available, but the reviewed MCP documentation does not establish MCP-specific approval behavior | Run logs are available, but the reviewed MCP documentation does not establish MCP-specific logging coverage | Low-code; technical work may be needed for custom integrations or self-hosting | +| **Sim** | [Yes](https://docs.sim.ai/agents/mcp) | [Yes, deployed workflows](https://docs.sim.ai/workflows/deployment/mcp) | See the [current deployment configurations](https://docs.sim.ai/workflows/deployment/mcp) | See the [current deployment guide](https://docs.sim.ai/workflows/deployment/mcp) | [Hosted or self-hosted](https://docs.sim.ai/platform/self-hosting) | Hosted multi-model access and BYOK; self-hosted deployments can use [locally configured Ollama models](https://docs.sim.ai/platform/self-hosting/environment-variables) | [Enterprise controls](https://docs.sim.ai/platform/enterprise) and self-hosting | Available, but the reviewed MCP documentation does not establish MCP-specific approval behavior | Run logs are available, but the reviewed MCP documentation does not establish MCP-specific logging coverage | Low-code; technical work may be needed for custom integrations or self-hosting | | **n8n** | [Yes](https://docs.n8n.io/integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.toolmcp) | [Yes](https://docs.n8n.io/integrations/builtin/core-nodes/n8n-nodes-langchain.mcptrigger) | Confirm against the [client](https://docs.n8n.io/integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.toolmcp) and [server](https://docs.n8n.io/integrations/builtin/core-nodes/n8n-nodes-langchain.mcptrigger) node documentation | [Bearer, header, or OAuth, depending on the node](https://docs.n8n.io/integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.toolmcp) | [Cloud or self-hosted](https://n8n.io/) | [Multiple model providers](https://n8n.io/) | [Features vary by plan](https://n8n.io/pricing/) | Unclear from the reviewed first-party MCP documentation | Execution visibility should be tested for the selected MCP node | [Low-code, with code nodes available](https://docs.n8n.io/build/code-in-n8n/using-the-code-node) | | **Zapier** | [Yes](https://help.zapier.com/hc/en-us/articles/38777069364109-Connect-remote-MCP-servers-to-Zapier-using-MCP-Client) | [Selected app actions, not arbitrary existing Zaps](https://help.zapier.com/hc/en-us/articles/36265551472781-Manage-tools-for-your-Zapier-MCP-server) | Unclear from the reviewed first-party documentation | [Managed connections and authorization](https://docs.zapier.com/mcp/home) | [Managed cloud](https://docs.zapier.com/mcp/home) | Product-dependent | [Features vary by plan](https://zapier.com/pricing) | Unclear from the reviewed first-party MCP documentation | Unclear from the reviewed first-party MCP documentation | [No-code configuration](https://zapier.com/mcp) | | **Make** | [Yes](https://apps.make.com/c5ZhYquO55e90hoCJ0rzt) | [Yes, eligible scenarios](https://help.make.com/get-started-with-make-mcp-server) | Unclear from the reviewed first-party documentation | [Configured connections and toolbox access](https://help.make.com/mcp-toolboxes) | [Managed cloud](https://www.make.com/) | [Multiple providers through integrations](https://www.make.com/) | [Features vary by plan](https://www.make.com/en/pricing) | Unclear from the reviewed first-party MCP documentation | Unclear from the reviewed first-party MCP documentation | [No-code to low-code](https://www.make.com/en/pricing) | | **Gumloop** | [Yes](https://docs.gumloop.com/nodes/mcp/custom_mcp_servers) | [Yes](https://docs.gumloop.com/mcp-server/overview) | Unclear from the reviewed first-party documentation | See the [MCP server documentation](https://docs.gumloop.com/mcp-server/overview) | [Managed cloud](https://docs.gumloop.com/) | [Multiple models](https://docs.gumloop.com/core-concepts/ai_models) | [Enterprise identity controls](https://docs.gumloop.com/enterprise-features/sso_saml_scim) | Unclear from the reviewed first-party MCP documentation | Unclear from the reviewed first-party MCP documentation | [No-code builder](https://docs.gumloop.com/core-concepts/workbooks) | -| **Dify** | Not verified from reviewed first-party documentation | Not verified from reviewed first-party documentation | Unclear | Unclear | Unclear | Unclear | Unclear | Unclear | Unclear | Unclear | -| **Langflow** | Not verified from reviewed first-party documentation | Not verified from reviewed first-party documentation | Unclear | Unclear | Unclear | Unclear | Unclear | Unclear | Unclear | Unclear | -| **Flowise** | Not verified from reviewed first-party documentation | Not verified from reviewed first-party documentation | Unclear | Unclear | Unclear | Unclear | Unclear | Unclear | Unclear | Unclear | -| **Microsoft Copilot Studio** | Not verified from reviewed first-party documentation | Not verified from reviewed first-party documentation | Unclear | Unclear | Unclear | Unclear | Unclear | Unclear | Unclear | Unclear | Authentication methods, enterprise controls, human approval features, and observability can vary by plan and MCP connection type. During evaluation, record the supported transport, credential method, approval behavior, and execution data available for each product. Buyers should confirm current limits before choosing a production deployment. @@ -80,7 +76,7 @@ Sim is an open, extensible, multi-model agent workspace for building custom agen Sim can [consume tools from external MCP servers](https://docs.sim.ai/agents/mcp) and turn a deployed workflow into a tool that other applications call through an MCP server. After you create a server and add the workflow as a tool, Sim provides [connection configurations for supported MCP clients](https://docs.sim.ai/workflows/deployment/mcp). Supported clients include Cursor, Codex, Claude Code, Claude Desktop, VS Code, and Sim itself. Each client can then invoke the workflow through the tool interface instead of reproducing its logic locally. -Sim supports hosted model access and bring-your-own-key connections for provider accounts. Local-model workflows are not available on regular plans; they require [Enterprise access](https://docs.sim.ai/platform/enterprise). Model and deployment availability can vary by plan and environment, so buyers should verify current terms for their intended setup. The [BYOK and multi-model agent builder guide](https://www.sim.ai/library/byok-multi-model-ai-agent-builder) covers the tradeoffs behind provider choice. +Sim supports hosted model access and bring-your-own-key connections for provider accounts. Self-hosted deployments can use [locally configured Ollama models](https://docs.sim.ai/platform/self-hosting/environment-variables). Model and deployment availability can vary by plan and environment, so buyers should verify current terms for their intended setup. The [BYOK and multi-model agent builder guide](https://www.sim.ai/library/byok-multi-model-ai-agent-builder) covers the tradeoffs behind provider choice. **Best for:** Sim fits technical buyers who want to build custom, multi-model agents and expose their workflows to several MCP clients. It also suits buyers who need source access or the option to self-host. @@ -200,8 +196,7 @@ Before selecting a platform, test a representative workflow rather than relying - Verify that a remote client can reach the production endpoint through the intended proxy, firewall, and load balancer. - Confirm plan limits, preview or beta status, data retention, identity controls, and production support with the vendor. - Authenticate with the production credential method and verify how credentials are stored and rotated. -- Inspect the tool name, description, and input schema that the model receives. -- Test the required model provider and verify any plan restrictions, including Enterprise access for Sim workflows that use local models. +- Test the required model provider and verify any plan or deployment restrictions. - Confirm whether the platform can run in the required cloud, self-hosted, or private-network environment. - Estimate usage with a realistic number of agent loops and tool calls rather than a single successful run. - Ask the intended maintainer to modify the workflow and recover from a failed execution. From b858a0c07c6dd19beb7674701cfe646710349359 Mon Sep 17 00:00:00 2001 From: Sim Pi Agent Date: Thu, 24 Sep 2026 19:23:29 +0000 Subject: [PATCH 3/3] Pi Babysit: address PR #8251 feedback --- .../library/best-ai-agent-builders-with-mcp-support/index.mdx | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/apps/sim/content/library/best-ai-agent-builders-with-mcp-support/index.mdx b/apps/sim/content/library/best-ai-agent-builders-with-mcp-support/index.mdx index 6a2f452afd6..2c06153ffa3 100644 --- a/apps/sim/content/library/best-ai-agent-builders-with-mcp-support/index.mdx +++ b/apps/sim/content/library/best-ai-agent-builders-with-mcp-support/index.mdx @@ -62,7 +62,7 @@ The table separates platforms that consume external MCP tools from those that ma | Platform | MCP client support | Publishes workflows or actions as MCP tools | Transport | Authentication | Deployment | Model choice | Enterprise controls | Human approval | Observability | Coding requirements | | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | -| **Sim** | [Yes](https://docs.sim.ai/agents/mcp) | [Yes, deployed workflows](https://docs.sim.ai/workflows/deployment/mcp) | See the [current deployment configurations](https://docs.sim.ai/workflows/deployment/mcp) | See the [current deployment guide](https://docs.sim.ai/workflows/deployment/mcp) | [Hosted or self-hosted](https://docs.sim.ai/platform/self-hosting) | Hosted multi-model access and BYOK; self-hosted deployments can use [locally configured Ollama models](https://docs.sim.ai/platform/self-hosting/environment-variables) | [Enterprise controls](https://docs.sim.ai/platform/enterprise) and self-hosting | Available, but the reviewed MCP documentation does not establish MCP-specific approval behavior | Run logs are available, but the reviewed MCP documentation does not establish MCP-specific logging coverage | Low-code; technical work may be needed for custom integrations or self-hosting | +| **Sim** | [Yes](https://docs.sim.ai/agents/mcp) | [Yes, deployed workflows](https://docs.sim.ai/workflows/deployment/mcp) | See the [current deployment configurations](https://docs.sim.ai/workflows/deployment/mcp) | See the [current deployment guide](https://docs.sim.ai/workflows/deployment/mcp) | [Hosted or self-hosted](https://docs.sim.ai/platform/self-hosting) | Hosted multi-model access and BYOK; self-hosted deployments can use locally configured model providers | [Enterprise controls](https://docs.sim.ai/platform/enterprise) and self-hosting | Available, but the reviewed MCP documentation does not establish MCP-specific approval behavior | Run logs are available, but the reviewed MCP documentation does not establish MCP-specific logging coverage | Low-code; technical work may be needed for custom integrations or self-hosting | | **n8n** | [Yes](https://docs.n8n.io/integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.toolmcp) | [Yes](https://docs.n8n.io/integrations/builtin/core-nodes/n8n-nodes-langchain.mcptrigger) | Confirm against the [client](https://docs.n8n.io/integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.toolmcp) and [server](https://docs.n8n.io/integrations/builtin/core-nodes/n8n-nodes-langchain.mcptrigger) node documentation | [Bearer, header, or OAuth, depending on the node](https://docs.n8n.io/integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.toolmcp) | [Cloud or self-hosted](https://n8n.io/) | [Multiple model providers](https://n8n.io/) | [Features vary by plan](https://n8n.io/pricing/) | Unclear from the reviewed first-party MCP documentation | Execution visibility should be tested for the selected MCP node | [Low-code, with code nodes available](https://docs.n8n.io/build/code-in-n8n/using-the-code-node) | | **Zapier** | [Yes](https://help.zapier.com/hc/en-us/articles/38777069364109-Connect-remote-MCP-servers-to-Zapier-using-MCP-Client) | [Selected app actions, not arbitrary existing Zaps](https://help.zapier.com/hc/en-us/articles/36265551472781-Manage-tools-for-your-Zapier-MCP-server) | Unclear from the reviewed first-party documentation | [Managed connections and authorization](https://docs.zapier.com/mcp/home) | [Managed cloud](https://docs.zapier.com/mcp/home) | Product-dependent | [Features vary by plan](https://zapier.com/pricing) | Unclear from the reviewed first-party MCP documentation | Unclear from the reviewed first-party MCP documentation | [No-code configuration](https://zapier.com/mcp) | | **Make** | [Yes](https://apps.make.com/c5ZhYquO55e90hoCJ0rzt) | [Yes, eligible scenarios](https://help.make.com/get-started-with-make-mcp-server) | Unclear from the reviewed first-party documentation | [Configured connections and toolbox access](https://help.make.com/mcp-toolboxes) | [Managed cloud](https://www.make.com/) | [Multiple providers through integrations](https://www.make.com/) | [Features vary by plan](https://www.make.com/en/pricing) | Unclear from the reviewed first-party MCP documentation | Unclear from the reviewed first-party MCP documentation | [No-code to low-code](https://www.make.com/en/pricing) | @@ -76,7 +76,7 @@ Sim is an open, extensible, multi-model agent workspace for building custom agen Sim can [consume tools from external MCP servers](https://docs.sim.ai/agents/mcp) and turn a deployed workflow into a tool that other applications call through an MCP server. After you create a server and add the workflow as a tool, Sim provides [connection configurations for supported MCP clients](https://docs.sim.ai/workflows/deployment/mcp). Supported clients include Cursor, Codex, Claude Code, Claude Desktop, VS Code, and Sim itself. Each client can then invoke the workflow through the tool interface instead of reproducing its logic locally. -Sim supports hosted model access and bring-your-own-key connections for provider accounts. Self-hosted deployments can use [locally configured Ollama models](https://docs.sim.ai/platform/self-hosting/environment-variables). Model and deployment availability can vary by plan and environment, so buyers should verify current terms for their intended setup. The [BYOK and multi-model agent builder guide](https://www.sim.ai/library/byok-multi-model-ai-agent-builder) covers the tradeoffs behind provider choice. +Sim supports hosted model access and bring-your-own-key connections for provider accounts. Self-hosted deployments can use locally configured model providers. Model and deployment availability can vary by plan and environment, so buyers should verify current terms for their intended setup. The [BYOK and multi-model agent builder guide](https://www.sim.ai/library/byok-multi-model-ai-agent-builder) covers the tradeoffs behind provider choice. **Best for:** Sim fits technical buyers who want to build custom, multi-model agents and expose their workflows to several MCP clients. It also suits buyers who need source access or the option to self-host.