runtime-proxy-mcp
OfficialClick on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@runtime-proxy-mcpecho 'proxy auth is working'"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
proxy-mcp-runtime
A two-container runtime: a FastMCP application server, and a reverse proxy sitting in front of it that enforces bearer-token auth before traffic reaches the MCP server.
Layout
mcp-app/ FastMCP server (Streamable HTTP transport, port 8000, internal-only)
proxy/ Caddy reverse proxy (bearer-token auth, port 8080, exposed)
docker-compose.ymlmcp-app — a single-file
server.pyusing PEP 723 inline script metadata, run withuv run server.py. It's not published to the host network; onlyproxycan reach it, over themcp-netcompose network.proxy — Caddy checks the
Authorization: Bearer <token>header againstMCP_PROXY_TOKENand rejects anything else with 401 before reverse-proxying tomcp-app:8000.
Related MCP server: mempalace-mcp-http
Running it
cp .env.example .env
# edit .env and set MCP_PROXY_TOKEN to a real value, e.g.:
# openssl rand -hex 32
docker compose up --buildThe MCP endpoint is then available at http://localhost:8080/mcp, and requires:
Authorization: Bearer <MCP_PROXY_TOKEN>Any request without a matching header gets a 401 from the proxy without ever reaching the FastMCP app.
Local dev without Docker
cd mcp-app
uv run server.pyThis runs the FastMCP server directly (no proxy/auth) on http://localhost:8000/mcp.
Notes
The two example tools (
ping,echo) are placeholders — replace them with real tools inmcp-app/server.py.MCP_PROXY_TOKENis a shared secret for this local/dev setup. For anything beyond local dev, manage it with fnox and swap the Caddy static-token check for something stronger (OAuth, per-client tokens, etc.) before exposing it outside a trusted network.Lint with
ruff check .from the repo root (config inpyproject.toml).
This server cannot be deployed
Maintenance
Related MCP Connectors
MCP server for secureFlows: token-free URL builders and integration-linting tools for AI agents.
Auth Token MCP Traced Service
Hash passwords with bcrypt and issue/verify JWT session tokens over A2A + MCP.
Related MCP Servers
- FlicenseNot gradedqualityCmaintenanceHTTP bridge that exposes MCP tools via POST endpoint, enabling remote LLMs to access local functionality with bearer authentication.-
- FlicenseNot gradedqualityDmaintenanceEnables remote access to the MemPalace MCP server via HTTP, supporting bearer token authentication and concurrent clients while exposing all mempalace tools.-
- AlicenseNot gradedqualityBmaintenanceEnables serving multiple MCP toolkits behind one server with capability-based access control, so different callers see and can call only the tools they are authorized for, over stdio or streamable HTTP with bearer-token auth.MIT
- FlicenseNot gradedqualityBmaintenanceEnables deploying an always-on Streamable HTTP MCP gateway on Fly.io with optional bearer token auth, so AI clients can connect to a reliable MCP endpoint.-