Meetric
    Documentation
    Go to Meetric
    HomeDocumentationMCP

    Meetric MCP

    Connect your AI assistant directly to your Meetric meeting data using the Model Context Protocol.

    Beta. This connector is read-only, the tool set may change, and rate limits apply. Please don't depend on it for production-critical automation yet.

    Overview

    MCP is an open standard that lets AI tools (like Claude, Cursor, Codex, and other MCP-compatible assistants) securely call external tools. Meetric hosts an MCP server so your assistant can read your meeting data — conversations, transcripts, summaries, insights, users, teams, and departments — either through your signed-in user permissions or through an account API token.

    https://Meetric.com/mcp JSON-RPC 2.0 over HTTPS

    How it works

    1. User sign-in mode: OAuth-capable MCP clients (including Notion) dynamically register, then open a Meetric login screen. Use your normal password, SSO, and MFA flow. The MCP can only see what your user can see.
    2. API-token mode: Admins can generate a Meetric API token (mt_…) under Settings → API tokens for service-style integrations.
    3. Your assistant calls tools/list to discover tools, then tools/call to fetch data. Every call is validated against the Meetric API and scoped to your account.

    Authentication

    Meetric MCP supports two auth modes. User sign-in uses OAuth + PKCE with Dynamic Client Registration and issues a mcp_at_… token tied to a user and account. API-token mode uses an admin-created mt_… token. Invalid or expired tokens are rejected with 401.

    Use this for personal assistants such as Claude, Notion, Cursor, and Codex. The client opens Meetric login, including password, SSO, and MFA when required. Data access follows the signed-in user's normal Meetric permissions.

    Alternative: API token

    Use this for admin-owned service integrations and automations. Paste the mt_… token into clients that support custom authorization headers.

    Get your API token

    1. Open Meetric and go to Settings → API tokens.
    2. Create a token and select scopes (e.g. conversations, transcripts, insights, users, teams, departments).
    3. Copy the mt_… value — it is shown only once.

    Connect your assistant

    Claude Desktop

    Claude Desktop runs MCP servers locally, so bridge the hosted endpoint with mcp-remote. Add this to claude_desktop_config.json (Settings → Developer → Edit Config):

    {
  "mcpServers": {
    "Meetric": {
      "command": "npx",
      "args": [
        "-y", "mcp-remote", "https://Meetric.com/mcp",
        "--header", "Authorization: Bearer mt_YOUR_TOKEN"
      ]
    }
  }
}

    Cursor

    Cursor supports remote MCP servers directly. Add this to ~/.cursor/mcp.json (or Settings → MCP):

    {
  "mcpServers": {
    "Meetric": {
      "url": "https://Meetric.com/mcp",
      "headers": { "Authorization": "Bearer mt_YOUR_TOKEN" }
    }
  }
}

    Codex (OpenAI Codex CLI)

    Add this to ~/.codex/config.toml:

    [mcp_servers.Meetric]
command = "npx"
args = ["-y", "mcp-remote", "https://Meetric.com/mcp", "--header", "Authorization: Bearer mt_YOUR_TOKEN"]

    Notion & other MCP-compatible tools

    For any assistant that supports a remote / custom MCP connector (URL + auth header), use the endpoint with a Bearer token:

    {
  "mcpServers": {
    "Meetric": {
      "url": "https://Meetric.com/mcp",
      "headers": { "Authorization": "Bearer mt_YOUR_TOKEN" }
    }
  }
}

    If the tool only supports local (stdio) MCP servers, use the mcp-remote bridge shown in the Claude example.

    Verify it works

    List the available tools from a terminal:

    curl -s https://Meetric.com/mcp \
  -H "Authorization: Bearer mt_YOUR_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"jsonrpc":"2.0","id":1,"method":"tools/list"}'

    Available tools

    ToolScopeDescription
    account_get—Get basic account and branding information for the API token account.
    users_listusersList active users in the account. Requires REST scope: users.
    teams_listteamsList teams and members in the account. Requires REST scope: teams.
    departments_listdepartmentsList enabled departments in the account. Requires REST scope: departments.
    conversations_listconversationsList recent conversations using the existing REST API filters.
    conversations_getconversationsGet one conversation by ID. Requires REST scope: conversations.
    conversations_transcripttranscriptsGet transcript for one conversation. Requires REST scope: transcripts.
    conversations_insightsinsightsGet insights/topics for one conversation. Requires REST scope: insights.
    conversations_summaryconversationsGet summary for one conversation. Requires REST scope: conversations.
    topics_listtopicsList topics (KPI-grouped insights) you can access, aggregated across your visible conversations. User-authenticated (OAuth) mode only.
    topics_drilldowntopicsDrill into a topic to get its underlying insights with source conversation references and transcript timestamps. Provide kpi_label and/or insight_type from topics_list. User-authenticated (OAuth) mode only.
    searchsearchSearch transcripts and insights (semantic + exact keyword) for words or phrases across the conversations you can access. Returns hits with conversation references + timestamps for transcript drilldown. User-authenticated (OAuth) mode only.
    conversations_recording_urlrecordingsGet recording URL for one conversation. Requires REST scope: recordings and token recording access.
    webhooks_deliveries_list—List REST webhook deliveries for this token/account.

    Limits & behavior

    • Read-only. Public Meetric tools do not modify Meetric data.
    • Account-scoped. A token only ever sees its own account's data, filtered by the token scopes.
    • Pagination. List results are capped (limit is clamped to 25); use the returned cursor for more.
    • Request size. Requests are limited to 64 KB.

    Support

    Questions or feedback? Email [email protected].

    Meetric MCP — Beta · Endpoint https://Meetric.com/mcp