mcpField
M
MCP stdio adapter

MCP stdio adapter

Local
github.com/jrderuiterDeveloper Tools2Updated 73w ago
Repository

About MCP stdio adapter

MCP stdio adapter proxies a remote streamable HTTP MCP server as a local stdio server. It is for applications that accept stdio MCP servers but cannot connect to remote servers directly.

Key features

  1. 01HTTP-to-stdio MCP proxy
  2. 02Connects local applications to remote servers
  3. 03Command-line and Docker usage

Use cases

  1. 01Use a remote MCP server from Zed
  2. 02Connect stdio-only applications to an HTTP server

MCP support

It presents a remote streamable HTTP MCP server to MCP clients as a local stdio MCP server.

#mcp-stdio-adapter#remote-server#stdio-adapter

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

No install method listed yet

We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.

Repository

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

MCP stdio adapter

Adapter that allows you to expose a remote MCP servers (streamable HTTP) as a local stdio MCP server. Useful for using remote MCP servers in applications that only support stdio (such as Zed).

graph LR
    remote(Remote server)
	adapter[This adapter]
	editor(Local editor)

  editor -->|stdio| adapter
	adapter -->|HTTP| remote

Usage

From the command line

You can run the proxy as follows:

SERVER_ADDRESS=http://<address-of-your-mcp-server> uv run fastmcp run main.py

or using Docker:

docker run --rm -it -e SERVER_ADDRESS=http://<your-server-address> jrderuiter/mcp-stdio-adapter
In Zed

For Zed, you can configure the proxy by adding the following context_servers entry in your settings file:

  "context_servers": {
    "<name-of-your-server>": {
      "command": {
        "path": "uv",
        "args": [
          "run",
          "--project",
          "<local-path-to-this-repo>",
          "fastmcp",
          "run",
          "<local-path-to-this-repo>/main.py"
        ],
        "env": {
          "SERVER_ADDRESS": "http://<address-of-your-server>"
        }
      }
    }

or using Docker:

  "context_servers": {
    "<name-of-your-server>": {
      "command": {
        "path": "docker",
        "args": [
          "run",
          "--rm",
          "-i",
          "-e",
          "SERVER_ADDRESS",
          "jrderuiter/mcp-stdio-adapter",
        ],
        "env": {
          "SERVER_ADDRESS": "http://<address-of-your-server>"
        }
      }
    }

Contributing

  1. Fork the repository
  2. Create a feature branch
  3. Make your changes
  4. Submit a pull request

Author

Julian de Ruiter

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.