Taichu MCP

Start with the local executable

These examples require the Taichu program. GWC for VS Code includes one for Windows x64; see the Download page for current availability.

taichu --mcp-serve

Let your MCP client launch the process. Set its working directory to the project you want to use: relative file paths and Taichu settings resolve from that directory. Startup messages go to standard error; standard output is reserved for MCP messages.

Available tools

• read_file

  Read a local file.

• write_file

  Create or replace a local file.

• edit_file

  Apply a text replacement in a local file.

• notebook_edit

  Edit cells in a notebook.

• glob

  Find files by path pattern.

• grep

  Search file contents.

• prior_art

  Search the codebase for existing implementations.

• report_findings

  Check findings in the required format. This standalone server cannot save them; see the limits below.

Connect from Codex

Add this table to ~/.codex/config.toml, replacing both example paths with your actual executable and project directory.

[mcp_servers.taichu]
command = "C:/path/to/taichu.exe"
args = ["--mcp-serve"]
cwd = "C:/path/to/project"

On other platforms, use the path to your Taichu executable. Reload the client after changing its configuration, then inspect its MCP server list. See the official Codex MCP documentation for client-specific options.

Other MCP clients

For clients that accept an mcpServers JSON object, use the same executable and flag. Start the client in your project directory, or set the server working directory using that client's configuration.

{
  "mcpServers": {
    "taichu": {
      "command": "C:/path/to/taichu.exe",
      "args": ["--mcp-serve"]
    }
  }
}

Current limits

• This server does not provide shell execution, browser automation, media generation, agent orchestration, or scheduled jobs.
• report_findings checks the input but returns persistence_unavailable because saving findings requires a Taichu session you own.
• Local tools run with the permissions of the launched process. Taichu loads the working directory's configured hooks; a pre-tool hook can block a call.
• Configure the model connection in your AI client using your provider credentials or a local model runtime.

Troubleshooting

If the server does not appear, check the executable path, the --mcp-serve flag, and the client's startup error log. If a file cannot be found, check the configured working directory. A Taichu hook may prevent a tool from running.

There is no supported public cloud API today; see the public API status notice. To configure local MCP servers in GWC for VS Code or connect AI apps through GWC Bridge, return to the MCP overview.