Build on the memory.

Your agent reads — and acts on — the memory.

Two endpoints, one contract. https://mcp.meetcrew.ai/v1 speaks MCP over Streamable HTTP; https://api.meetcrew.ai/v1 is the same memory over ordinary REST. They return the same records with the same field names, so the choice is about how your agent is built, not about what it can see. Authenticate either with a Microsoft Entra bearer token for a service principal you grant in the admin console — the same token works on both. 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. A grant also carries an access level: read serves every read, and the four actions need read and write, which your admin selects when issuing the 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.

REST — the same memory, ordinary HTTP v1

Base https://api.meetcrew.ai/v1. Every route is deployment-scoped, and the tenant is never in the path — it comes from the token. Responses carry the same records as the MCP tools above, field for field.

PATCH rather than PUT, because none of these replaces a record: every field is optional and only workflow state can change. A parameter or body field we don’t recognise is refused, not ignored — a dropped filter would return more than you asked for, and a dropped field would mean a change you believe you made didn’t happen.

Errors, limits and versioning

Failures are RFC 9457 problem documents. Match on the status code, never on the message text — wording can change without notice.

Every call on both endpoints is logged and attributable to the Entra identity that made it — reads and actions are retained differently, which matters when you are answering a question about something months old. Trust & Security has the retention periods.

Within v1 we add, we don’t remove: new fields, parameters, endpoints and enum values can appear at any time, so ignore what you don’t recognise rather than failing on it. Nothing is renamed or removed, and no status code changes meaning. A breaking change means a new prefix served alongside this one, with 90 days’ notice to the administrator who issued your grant before deprecation and at least 180 days more before v1 stops answering — announced by email and carried on every response as Deprecation and Sunset headers.

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": {
    "deployment_id": "dep_jim",
    "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"
}

Example — the same two calls over REST

Same token, same records. Only the envelope differs.

# search
curl -H "Authorization: Bearer $TOKEN" \
  "https://api.meetcrew.ai/v1/deployments/dep_jim/search?q=pricing+decision&types=decision,open_question&since=2026-06-01&limit=2"

# close an action item
curl -X PATCH -H "Authorization: Bearer $TOKEN" \
  -H "Content-Type: application/json" -d '{"status":"done"}' \
  "https://api.meetcrew.ai/v1/deployments/dep_jim/action-items/ai_3315"

// the search response — identical to the MCP result above
{
  "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"
    }
  ],
  "was_capped": false,
  "next_cursor": null
}

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 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 and its credential — paste a Key Vault secret reference, never the raw secret.
4. Stub the backend: return { "content": "Hi, I'm Jim." } and confirm it answers inside the budget on metadata.timeout_ms.
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 system + messages to compose the reply.
8. Grant your agent MCP access — create a service-principal grant in the console. Choose read and write if your agent will use the actions; read-only is the default, and the four actions are refused under it.
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.