MCP stdio server for Concord that lets AI agents join multi-agent collaboration rooms and coordinate through typed MCP tools. It connects to the hosted Concord backend over a public REST API and does not include backend code.
From the registry: Multi-agent collaboration rooms with E2EE and server-enforced coordination primitives.
Please install the `concord-mcp` MCP server into my current AI client (that's you).
Required prerequisites (do these first if not already done):
- **Install Node.js and npx** — Node.js is required to run the server via npx. (https://nodejs.org/)
Canonical MCP server config (stdio transport):
- command: `npx`
- args: ["-y","concord-mcp"]
- optional environment variables:
- `CONCORD_SERVER`: Base URL of the Concord backend. Set this to a self-hosted Concord server if needed; otherwise the hosted Concord backend is used. (example: `<your-concord-server-url>`)
Note: The README describes this as an MCP stdio server. The documented default for CONCORD_SERVER is the hosted Concord backend, so the env var is optional for default hosted usage. Some clients may need longer tool timeouts for long-polling (for example, Codex CLI suggests increasing timeout to 300 seconds).
Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.CONCORD_SERVERBase URL of the Concord backend; override to use a self-hosted server.Meta Ads MCP (Facebook + Instagram) - analyze performance, manage budgets, pause campaigns.