Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension


Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion .agents/plugins/marketplace.json
Original file line number Diff line number Diff line change
Expand Up @@ -5,7 +5,7 @@
},
"metadata": {
"description": "Identity, scoped access, and proof for AI agents through Proofable MCP.",
"version": "0.1.6"
"version": "0.1.7"
},
"plugins": [
{
Expand Down
2 changes: 1 addition & 1 deletion .claude-plugin/marketplace.json
Original file line number Diff line number Diff line change
Expand Up @@ -5,7 +5,7 @@
},
"metadata": {
"description": "Identity, scoped access, and proof for AI agents through Proofable MCP.",
"version": "0.1.6"
"version": "0.1.7"
},
"plugins": [
{
Expand Down
2 changes: 1 addition & 1 deletion .cursor-plugin/marketplace.json
Original file line number Diff line number Diff line change
Expand Up @@ -5,7 +5,7 @@
},
"metadata": {
"description": "Identity, scoped access, and proof for AI agents through Proofable MCP.",
"version": "0.1.6"
"version": "0.1.7"
},
"plugins": [
{
Expand Down
13 changes: 12 additions & 1 deletion .github/workflows/ci.yml
Original file line number Diff line number Diff line change
Expand Up @@ -14,10 +14,21 @@ jobs:
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v7
- name: Select matching SDK review branch
id: sdk-ref
env:
CANDIDATE_REF: ${{ github.head_ref }}
run: |
ref=main
if [[ -n "$CANDIDATE_REF" ]] && git ls-remote --exit-code https://github.com/proofable/sdk.git "refs/heads/$CANDIDATE_REF" >/dev/null; then
ref="$CANDIDATE_REF"
fi
echo "ref=$ref" >> "$GITHUB_OUTPUT"
- name: Check out proofable/sdk for skill parity
uses: actions/checkout@v7
with:
repository: proofable/sdk
ref: ${{ steps.sdk-ref.outputs.ref }}
path: sdk
- uses: actions/setup-node@v7
with:
Expand All @@ -27,4 +38,4 @@ jobs:
run: npm test
env:
PROOFABLE_SDK_SKILLS_ROOT: ${{ github.workspace }}/sdk/skills
- run: npm pack --dry-run
- run: npm pack --dry-run
1 change: 1 addition & 0 deletions README.md
Original file line number Diff line number Diff line change
Expand Up @@ -66,6 +66,7 @@ Install one Proofable connection per client. A marketplace plugin and a manual e
| Check whether a qualifying proof already exists | `proofable_proofs_check` |
| Reuse a current proof or get the next verification step | `proofable_verify_or_guide` |
| Create or refresh a proof | `proofable_verify` |
| Prepare and submit a check needing another signer | `proofable_verify_prepare`, `proofable_verify_submit` |

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

P2 Badge Add the new verification tools to the changelog

When 0.1.7 is tagged, the release workflow publishes this package and registry manifest, but CHANGELOG.md still has an empty Unreleased section and ends at 0.1.6. As a result, the newly public prepare/submit workflow and changed Vault replacement behavior are absent from the repository's promised record of notable package, plugin, and skill changes; document them under Unreleased or a 0.1.7 section before release.

Useful? React with 👍 / 👎.

| Find and read proofs | `proofable_proofs_get` |
| Update proof metadata or add feedback | `proofable_proofs_update` |
| Check, create, and load agent permissions | `proofable_agent_link`, `proofable_agent_create`, `proofable_agent_mount` |
Expand Down
4 changes: 2 additions & 2 deletions package-lock.json

Some generated files are not rendered by default. Learn more about how customized files appear on GitHub.

2 changes: 1 addition & 1 deletion package.json
Original file line number Diff line number Diff line change
@@ -1,6 +1,6 @@
{
"name": "@proofable/mcp",
"version": "0.1.6",
"version": "0.1.7",
"description": "Identity, scoped access, and proof for AI agents through Proofable MCP.",
"type": "module",
"main": "./index.mjs",
Expand Down
2 changes: 1 addition & 1 deletion plugins/proofable-mcp/.claude-plugin/plugin.json
Original file line number Diff line number Diff line change
Expand Up @@ -2,7 +2,7 @@
"name": "proofable-mcp",
"displayName": "Proofable",
"description": "Identity, scoped access, and proof for AI agents through Proofable MCP.",
"version": "0.1.6",
"version": "0.1.7",
"author": {
"name": "Proofable",
"url": "https://proofable.me"
Expand Down
2 changes: 1 addition & 1 deletion plugins/proofable-mcp/.codex-plugin/plugin.json
Original file line number Diff line number Diff line change
@@ -1,6 +1,6 @@
{
"name": "proofable-mcp",
"version": "0.1.6",
"version": "0.1.7",
"description": "Identity, scoped access, and proof for AI agents through Proofable MCP.",
"author": {
"name": "Proofable",
Expand Down
2 changes: 1 addition & 1 deletion plugins/proofable-mcp/.cursor-plugin/plugin.json
Original file line number Diff line number Diff line change
Expand Up @@ -2,7 +2,7 @@
"name": "proofable-mcp",
"displayName": "Proofable",
"description": "Identity, scoped access, and proof for AI agents through Proofable MCP.",
"version": "0.1.6",
"version": "0.1.7",
"author": {
"name": "Proofable"
},
Expand Down
2 changes: 1 addition & 1 deletion plugins/proofable-mcp/skills/proofable-integrate/SKILL.md
Original file line number Diff line number Diff line change
Expand Up @@ -5,7 +5,7 @@ license: Apache-2.0
compatibility: Requires @proofable/sdk (npm).
metadata:
author: Proofable
version: "0.1.6"
version: "0.1.7"
homepage: https://docs.proofable.me/use-cases/gate-access
---

Expand Down
2 changes: 1 addition & 1 deletion plugins/proofable-mcp/skills/proofable-setup/SKILL.md
Original file line number Diff line number Diff line change
Expand Up @@ -5,7 +5,7 @@ license: Apache-2.0
compatibility: Requires an MCP-capable client that can register a remote HTTP server.
metadata:
author: Proofable
version: "0.1.6"
version: "0.1.7"
homepage: https://docs.proofable.me/mcp/setup
---

Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -5,7 +5,7 @@ license: Apache-2.0
compatibility: Requires a client that supports remote HTTP MCP servers and hosted OAuth.
metadata:
author: Proofable
version: "0.1.6"
version: "0.1.7"
homepage: https://docs.proofable.me/mcp/setup
---

Expand All @@ -25,7 +25,7 @@ Use this before an assistant runs sensitive tools or takes another verification-

1. **`proofable_context`** once per session. Prefer signed-in profile context; omit wallet fields on check/verify tools.
2. **Profile agent:** **`proofable_agent_mount`** (or `proofable mount <agentId> --apply <host>`) for identity, permissions, skills, and context.
3. **Trust before action:** use **`proofable_verify_or_guide`** directly. It reuses qualifying proofs or returns the next secure step. Use **`proofable_proofs_check`** only for an explicit yes/no eligibility, gate, or access question; never use it for memory, context, or content retrieval. When signed in, ownership checks continue with **`proofable_verify`**. Share a browser link only when a tool returns one.
3. **Trust before action:** use **`proofable_verify_or_guide`** directly. It reuses qualifying proofs or returns the next secure step. Use **`proofable_proofs_check`** only for an explicit yes/no eligibility, gate, or access question; never use it for memory, context, or content retrieval. When signed in, ownership checks continue with **`proofable_verify`**. For another signer, prepare with **`proofable_verify_prepare`** and submit with **`proofable_verify_submit`**. Share a browser link only when a tool returns one.
4. **Agent:** **`proofable_agent_link`**. If missing, **`proofable_agent_create`** (a dedicated account needs a key you create and hold; pass only its public address). Then **`proofable_agent_mount`**.
5. **Proofs and context:** use the `proofable_context` context index first, then **`proofable_proofs_get`** with a known proof ID and `include=content` for an exact body.
6. **Vault:** **`proofable_secret_list`** / **`proofable_secret_create`** / **`proofable_secret_revoke`**.
Expand Down
16 changes: 12 additions & 4 deletions server.json
Original file line number Diff line number Diff line change
Expand Up @@ -3,7 +3,7 @@
"name": "io.github.proofable/mcp",
"title": "Proofable MCP",
"description": "Identity, scoped access, and proof for AI agents through Proofable MCP.",
"version": "0.1.6",
"version": "0.1.7",
"repository": {
"url": "https://github.com/proofable/mcp",
"source": "github"
Expand Down Expand Up @@ -44,15 +44,23 @@
},
{
"name": "proofable_verifiers_catalog",
"description": "List the verification checks Proofable supports, including required inputs and supported networks for each check. Verifier IDs select Proofable checks; they are not separate MCP tools."
"description": "Return supported check definitions with the inputs and networks each requires."
},
{
"name": "proofable_proofs_check",
"description": "Does this wallet already have the required proofs? Returns pass or fail, not records. To read proofs, use proofable_proofs_get. Omit the wallet when signed in."
},
{
"name": "proofable_verify",
"description": "Create or refresh portable proofs for the requested Proofable checks. For signed-in ownership checks, omit the wallet; the session supplies it. Share a browser link only when this tool returns one."
"description": "Create a proof directly for the signed-in account. Omit the wallet for your own account. If another signer is required, use proofable_verify_prepare and proofable_verify_submit."
},
{
"name": "proofable_verify_prepare",
"description": "Prepare a signature request for the selected Proofable checks. Returns the exact signing string, timestamp, chain, and hosted fallback. This call does not submit the check or create a proof."
},
{
"name": "proofable_verify_submit",
"description": "Submit a signed Proofable check using the same wallet, checks, data, and chain used to prepare it, plus the returned signing timestamp and signature. Creates a proof only when verification succeeds."
},
{
"name": "proofable_verify_or_guide",
Expand Down Expand Up @@ -80,7 +88,7 @@
},
{
"name": "proofable_secret_create",
"description": "Encrypt and save one secret in the Vault for the signed-in profile. Returns metadata only; the stored value is never returned."
"description": "Encrypt and save one secret in the Vault for the signed-in profile. Saving the same alias again replaces and revokes its prior value. Returns metadata only; the stored value is never returned."
},
{
"name": "proofable_secret_list",
Expand Down
2 changes: 1 addition & 1 deletion skills/proofable-integrate/SKILL.md
Original file line number Diff line number Diff line change
Expand Up @@ -5,7 +5,7 @@ license: Apache-2.0
compatibility: Requires @proofable/sdk (npm).
metadata:
author: Proofable
version: "0.1.6"
version: "0.1.7"
homepage: https://docs.proofable.me/use-cases/gate-access
---

Expand Down
2 changes: 1 addition & 1 deletion skills/proofable-setup/SKILL.md
Original file line number Diff line number Diff line change
Expand Up @@ -5,7 +5,7 @@ license: Apache-2.0
compatibility: Requires an MCP-capable client that can register a remote HTTP server.
metadata:
author: Proofable
version: "0.1.6"
version: "0.1.7"
homepage: https://docs.proofable.me/mcp/setup
---

Expand Down
4 changes: 2 additions & 2 deletions skills/proofable-trust-workflow/SKILL.md
Original file line number Diff line number Diff line change
Expand Up @@ -5,7 +5,7 @@ license: Apache-2.0
compatibility: Requires a client that supports remote HTTP MCP servers and hosted OAuth.
metadata:
author: Proofable
version: "0.1.6"
version: "0.1.7"
homepage: https://docs.proofable.me/mcp/setup
---

Expand All @@ -25,7 +25,7 @@ Use this before an assistant runs sensitive tools or takes another verification-

1. **`proofable_context`** once per session. Prefer signed-in profile context; omit wallet fields on check/verify tools.
2. **Profile agent:** **`proofable_agent_mount`** (or `proofable mount <agentId> --apply <host>`) for identity, permissions, skills, and context.
3. **Trust before action:** use **`proofable_verify_or_guide`** directly. It reuses qualifying proofs or returns the next secure step. Use **`proofable_proofs_check`** only for an explicit yes/no eligibility, gate, or access question; never use it for memory, context, or content retrieval. When signed in, ownership checks continue with **`proofable_verify`**. Share a browser link only when a tool returns one.
3. **Trust before action:** use **`proofable_verify_or_guide`** directly. It reuses qualifying proofs or returns the next secure step. Use **`proofable_proofs_check`** only for an explicit yes/no eligibility, gate, or access question; never use it for memory, context, or content retrieval. When signed in, ownership checks continue with **`proofable_verify`**. For another signer, prepare with **`proofable_verify_prepare`** and submit with **`proofable_verify_submit`**. Share a browser link only when a tool returns one.
4. **Agent:** **`proofable_agent_link`**. If missing, **`proofable_agent_create`** (a dedicated account needs a key you create and hold; pass only its public address). Then **`proofable_agent_mount`**.
5. **Proofs and context:** use the `proofable_context` context index first, then **`proofable_proofs_get`** with a known proof ID and `include=content` for an exact body.
6. **Vault:** **`proofable_secret_list`** / **`proofable_secret_create`** / **`proofable_secret_revoke`**.
Expand Down
Loading