Build on the memory.

Your agent reads — and acts on — the memory.

Endpoint https://mcp.meetcrew.ai/v1 over Streamable HTTP. Authenticate with a Microsoft Entra bearer token for a service principal you grant in the admin console. The tenant is derived from the token — a client can’t reach another tenant’s memory even by guessing IDs. Reads and actions are scoped to a deployment (one named teammate); cross-deployment access requires an admin opt-in grant.

Resources

Tools

Every record carries attribution — a Microsoft Entra platform identity, or anonymous — plus created_at and deployment_id. No voiceprints are ever used for attribution.

Actions v1

Actions are confined to workflow state on action items, decisions, and open questions. There is no delete, and no action can alter a transcript, a statement, provenance, or the audit log. Every action is authenticated, tenant- and deployment-scoped, and logged.

Example — search memory

// MCP tools/call
{
  "name": "searchMemory",
  "arguments": {
    "deployment_id": "dep_jim",
    "query": "pricing decision",
    "types": ["decision", "open_question"],
    "since": "2026-06-01",
    "limit": 2
  }
}

{
  "results": [
    {
      "id": "dec_5521", "type": "decision", "score": 0.94,
      "text": "Hold list pricing flat through Q3; revisit at QBR.",
      "decided_at": "2026-06-30T16:20:00Z", "meeting_id": "mtg_4790",
      "attribution": { "kind": "platform_identity", "display_name": "Priya Shah" },
      "deployment_id": "dep_jim"
    },
    {
      "id": "oq_0912", "type": "open_question", "score": 0.71, "status": "open",
      "text": "Do enterprise renewals get the same flat-pricing treatment?",
      "raised_at": "2026-06-30T16:24:00Z", "meeting_id": "mtg_4790",
      "attribution": { "kind": "anonymous" }, "deployment_id": "dep_jim"
    }
  ],
  "next_cursor": null
}

Example — close an action item

// MCP tools/call
{
  "name": "updateActionItem",
  "arguments": {
    "action_item_id": "ai_3315",
    "status": "done"
  }
}

{
  "id": "ai_3315", "type": "action_item", "status": "done",
  "text": "Add pricing revisit to QBR agenda",
  "assignee": { "kind": "platform_identity", "display_name": "Dana Ruiz" },
  "updated_at": "2026-07-07T15:40:00Z",
  "updated_by": { "kind": "service_principal", "display_name": "Renewals Agent" },
  "deployment_id": "dep_jim"
}

First 15 minutes.

Zero to a teammate answering in a test meeting, and your agent reading that meeting’s memory over MCP.

1. Sign in to the admin console with an Entra admin account. Confirm your tenant region is US (excluding Illinois) or Canada.
2. Create a deployment — name the teammate (say, “Jim”), pick platform, voice, and avatar. This provisions memory scoped to dep_jim.
3. Register your agent backend endpoint. Choose Entra or a shared secret; for a secret, paste a Key Vault secret reference, not the secret.
4. Stub the backend: return { "speech": "Hi, I'm Jim." } and confirm it answers within the 3s budget.
5. Admit the teammate into a test meeting. Confirm the disclosure banner shows Jim as AI.
6. Say “Jim, are you there?” and hear the stubbed reply. The backend contract now works end to end.
7. Point the endpoint at your real Copilot Studio, Microsoft Foundry, or custom agent. Use utterance + retrieved_memory to compose the reply.
8. Grant your agent MCP access — create a service-principal grant in the console.
9. Connect your MCP client to https://mcp.meetcrew.ai/v1 with an Entra bearer token. List meetcrew://deployments and confirm dep_jim appears.
10. Call getMeeting, then listDecisions scoped to dep_jim. Your agent is now reading cross-meeting memory. Ship from here.