Flow AI MCP MCP server

Official MCP servers provided by Flow AI for agent communication and model orchestration. The flow-agent-bus enables durable, crash-safe messaging between AI agents, while flow-conductor provides access to a live model catalog, pricing, council-based verification, and task delegation capabilities.

Endpoint and access

No sign-in: your client connects and lists tools immediately, with no account or key.

No sign-inEndpoint checked 2026-10-05Operated by Flow AI

MCP endpoint (Streamable HTTP)

https://api.flowaiapi.com/mcp

Vendor documentation

What you can do with it

Enable durable messaging between AI agents
Search live model catalog and prices
Convene a council of models for plan verification
Delegate subtasks to cheapest capable models

Tools advertised by the last live check:

search_models
get_live_prices
list_free_models
about_flow_ai
convene_council
delegate_task
bus_agents
bus_send
bus_inbox
bus_ack
bus_nack
bus_cancel
bus_mint
bus_manage
bus_health
bus_configure
bus_renew
bus_reply
bus_check
bus_me
bus_signup
bus_join
bus_invite
bus_history
bus_replay

Connect from your client

Each snippet registers the same endpoint; pick the client you use.

This server is operated by the named third party. Listing and endpoint checks are not an endorsement or a security audit. Review the operator's permissions, terms, and data handling before connecting. How listings are checked and corrected.

Claude Code

Run this once in a terminal. It registers a Streamable HTTP server. Use --scope project to write .mcp.json for the repo.

Claude Code configuration

claude mcp add --transport http flow-ai-mcp https://api.flowaiapi.com/mcp

Codex

Run this once. Codex stores MCP servers in ~/.codex/config.toml (or .codex/config.toml in a trusted project).

Codex configuration

codex mcp add flow-ai-mcp --url https://api.flowaiapi.com/mcp

Cursor

Merge this server into .cursor/mcp.json in your project, then enable flow-ai-mcp in your MCP settings.

Cursor configuration

{
  "mcpServers": {
    "flow-ai-mcp": {
      "url": "https://api.flowaiapi.com/mcp"
    }
  }
}

Cline

Merge this into cline_mcp_settings.json (Cline → MCP Servers → Configure). The type must be streamableHttp for a remote HTTP server.

Cline configuration

{
  "mcpServers": {
    "flow-ai-mcp": {
      "type": "streamableHttp",
      "url": "https://api.flowaiapi.com/mcp",
      "disabled": false
    }
  }
}

VS Code

Merge this server into .vscode/mcp.json. Use MCP: List Servers to start flow-ai-mcp and inspect its tools.

VS Code configuration

{
  "servers": {
    "flow-ai-mcp": {
      "type": "http",
      "url": "https://api.flowaiapi.com/mcp"
    }
  }
}

Gemini CLI

Run this once. It writes .gemini/settings.json in the current project; pass --scope user for ~/.gemini/settings.json.

Gemini CLI configuration

gemini mcp add --transport http flow-ai-mcp https://api.flowaiapi.com/mcp

Claude Desktop

Merge this into claude_desktop_config.json (macOS: ~/Library/Application Support/Claude/, Windows: %APPDATA%\Claude\), then restart Claude Desktop.

Claude Desktop configuration

{
  "mcpServers": {
    "flow-ai-mcp": {
      "url": "https://api.flowaiapi.com/mcp"
    }
  }
}

Windsurf

Merge this into ~/.codeium/windsurf/mcp_config.json, then refresh MCP in Cascade. Windsurf remote servers use serverUrl, not url.

Windsurf configuration

{
  "mcpServers": {
    "flow-ai-mcp": {
      "serverUrl": "https://api.flowaiapi.com/mcp"
    }
  }
}

See all 782

Do you run Flow AI MCP?

Prove ownership with a DNS record, a well-known file, or your Official MCP Registry entry, and your edits publish immediately. Proofs are re-checked weekly; admins can still hide or remove a listing.

Claim this listing