claude-yolo · Oct 31, 2026 · Oct 31, 2026
diff --git a/content/.metadata.json b/content/.metadata.json
diff --git a/content/claude/third-party/claude-desktop/import.md b/content/claude/third-party/claude-desktop/import.md
@@ -33,11 +33,17 @@ Use the [import wizard](#open-the-import-wizard) for your claude.ai conversation
 * Your administrator has turned import on by setting [`claudeAiImport`](https://claude.com/docs/third-party/claude-desktop/configuration#claudeaiimport) with `enabled` set to `true` in the managed configuration. The import wizard is off by default; until then, **Settings → Import & export** has no **Import…** button and reports that import isn't enabled for this deployment. The [automatic import of earlier third-party sessions](#automatic-import-of-earlier-third-party-sessions) doesn't depend on this setting.
 * If your administrator lists the claude.ai organizations you may import from, with `allowedOrganizationUuids` under [`claudeAiImport`](https://claude.com/docs/third-party/claude-desktop/configuration#claudeaiimport), you can import only by signing in to claude.ai, and only from a listed organization. A sign-in to any other organization or to a personal account is refused, and the wizard's options to import from a file or from earlier sessions on this computer are turned off. The [automatic import of earlier third-party sessions](#automatic-import-of-earlier-third-party-sessions) isn't affected by this list.
 * Claude Desktop is installed and running in third-party mode. See [Installation and setup](https://claude.com/docs/third-party/claude-desktop/installation.md).
-* To bring history over from a claude.ai Team or Enterprise workspace, an owner of that workspace has enabled member data export (next section). Personal claude.ai accounts can always export.
+* To bring history over from a claude.ai Team or Enterprise workspace, an owner of that workspace has [enabled member data export](#enable-member-data-export-admins), which isn't possible in a HIPAA-ready organization. Personal claude.ai accounts can always export.
 
 ## Enable member data export (admins)
 
-On Team and Enterprise workspaces, member data export is off by default. A workspace owner enables it on claude.ai under **Settings → Organization → Data and privacy → Allow members to export their own data**.
+On Team and Enterprise workspaces, member data export is off by default.
+
+> [!NOTE]
+>
+> In a [HIPAA-ready organization](https://support.claude.com/en/articles/13296973-hipaa-ready-enterprise-plans), member data export can't be turned on. Both ways to import claude.ai chats and projects in [step 1 of the import wizard](#step-1-claude-ai-chats-and-projects) need member data export, so neither works for members of that organization. If [`allowedOrganizationUuids`](https://claude.com/docs/third-party/claude-desktop/configuration#claudeaiimport) isn't set, they can still import Cowork and Claude Code sessions already on their computer in [step 2](#step-2-local-cowork-and-code-sessions).
+
+To enable member data export, a workspace owner goes to [**Organization settings > Data and privacy**](https://claude.ai/admin-settings/data-privacy-controls) on claude.ai and turns on the **Allow members to export their own data** toggle.
 
 ![claude.ai organization settings, Data and privacy page, with the Allow members to export their own data toggle turned on and a confirmation toast reading Member data export enabled.](https://mintcdn.com/claude-ai/HpR2FaaZXZXkiUcV/images/third-party/import/import-admin-toggle.png?fit=max\&auto=format\&n=HpR2FaaZXZXkiUcV\&q=85\&s=f1f4696a2124cd36ee9a7366cb1c4772)
 

diff --git a/content/mcp/community/interest-groups/security.md b/content/mcp/community/interest-groups/security.md
@@ -12,13 +12,16 @@
 
 ## Mission Statement
 
-The Security Interest Group catalogs MCP-specific threats, reviews security-relevant proposals, and
-scopes validated problems into focused Working Groups or [SEPs](https://modelcontextprotocol.io/community/sep-guidelines.md).
+The Security Interest Group is the first stop for MCP-specific security topics. It vets incoming
+threats, security-relevant proposals, and disclosure questions, then routes validated work to the
+Working Group or [SEP](https://modelcontextprotocol.io/community/sep-guidelines.md) that owns it.
 
 ## Scope
 
 ### In Scope
 
+* **Triage and routing**: receiving security topics raised on Discord or GitHub and handing them
+  to the owning group (Auth IG, Transports WG, Registry WG, Tool Annotations IG, SDK maintainers)
 * **Threat modeling**: developing and maintaining a shared, layered view of MCP attack surfaces
   spanning admission and identity, caller governance, runtime behavior, interception and enforcement,
   and auditability, to give individual proposals a common frame of reference
@@ -92,17 +95,20 @@ scopes validated problems into focused Working Groups or [SEPs](https://modelcon
 | Stefano Ortolani | Broadcom | [@ostefano](https://github.com/ostefano) | `ostefano.` | Participant |
 
 Open to anyone. Join the `#security-ig` channel on the
-[MCP Contributors Discord](https://modelcontextprotocol.io/community/communication.md#discord). Calls are open and active
-participation is highly encouraged. The group is looking for contributors who will engage with
-proposals and help drive work forward rather than observe.
+[MCP Contributors Discord](https://modelcontextprotocol.io/community/communication.md#discord). Discussion runs asynchronously in
+the channel between calls, and the agenda for each monthly call is assembled there. The group is
+looking for contributors who will engage with proposals and help drive work forward rather than
+observe.
 
 ## Operations
 
 | Meeting | Frequency | Duration | Purpose |
 | - | - | - | - |
-| Office Hours | Every 2 weeks | 45 min | Threat review, proposal triage, deployment reports, WG-proposal scoping |
+| Forum call | Monthly | 45 min | Triage and routing of topics on the published agenda, WG proposal scoping |
+| Digest | Monthly | n/a | Summary of routed items, open topics, and advisories |
 
-An agenda is shared in `#security-ig` ahead of each call.
+The facilitators post a call for agenda in `#security-ig` ahead of each monthly call, and anyone
+can add topics to it.
 
 Discord: [#security-ig](https://discord.com/channels/1358869848138059966/1379811011669921883)
 
@@ -128,4 +134,5 @@ evolve as the group identifies new areas of interest.
 
 | Date | Change |
 | - | - |
+| 2026-08-26 | Restructured as a routing group, replaced biweekly office hours with a monthly agenda-driven call and digest (core maintainer meeting, [discussion #3316](https://github.com/modelcontextprotocol/modelcontextprotocol/discussions/3316)) |
 | 2026-06-13 | Initial charter |
diff --git a/content/mcp/community/security.md b/content/mcp/community/security.md
@@ -65,6 +65,6 @@ boundary. The SDK's stdio transport is not a sandbox.
 
 ## Security Interest Group
 
-The [Security Interest Group](https://modelcontextprotocol.io/community/interest-groups/security.md) is the venue for
-discussing MCP-specific threats, reviewing security-relevant proposals, and routing
-disclosure questions that don't fit a single repository.
+The [Security Interest Group](https://modelcontextprotocol.io/community/interest-groups/security.md) is where you raise MCP-specific
+security topics, including disclosure questions that don't fit a single repository, and where
+facilitators route them to the group that owns the work.