mcpField
B
Bot Bridge CC Helper

Bot Bridge CC Helper

Local
botbridge.devDeveloper Tools0Updated 3w ago

About Bot Bridge CC Helper

Bot Bridge CC Helper is an MCP stdio file bridge between a remote bot and a local Bot Bridge CC Helper on Windows. It is for dispatching coding tasks to the local helper and reading their progress and results; the helper install is required to run jobs.

Key features

  1. 01Check local Helper installation
  2. 02Dispatch coding tasks
  3. 03Read task progress and results
  4. 04List queued, running, and finished tasks
  5. 05Send cancellation commands

Use cases

  1. 01Send a coding task from a remote bot
  2. 02Check the progress of a running task
  3. 03Review completed task results
  4. 04Cancel a running task

MCP support

Exposes task dispatch and status operations to MCP clients over stdio. It reads and writes job files used by a local Bot Bridge CC Helper installation.

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
Packages
mcpbbotbridge-cc-helper.mcpb0.1.0

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

botbridge-cc-helper-mcp

An MCP stdio server that bridges a remote bot (any MCP client) to a local Bot Bridge CC Helper running on Windows. You dispatch a coding task into the Helper's inbox and read progress and results back out.

Independent product. This is not an Anthropic product and is not affiliated with, endorsed by, or sponsored by Anthropic. It talks to a local Bot Bridge CC Helper install that you run yourself.

Requirements

This package is a file bridge. It is useful only together with a local Bot Bridge CC Helper install — the desktop tray/daemon that actually owns the job folders and runs your local coding agent. Without that install every tool still answers, but reports that nothing is installed.

  • Node.js >= 18
  • A local Bot Bridge CC Helper install (Windows), which owns:
    • inbox\ — one JSON file per queued job
    • running\ — per-job progress while a job runs
    • done\ — final state per job
    • control\ — cancellation commands

The Helper folder defaults to %USERPROFILE%\cc-helper and can be pointed elsewhere with the CC_HELPER_HOME environment variable.

Install

npm install -g botbridge-cc-helper-mcp

Or run it without installing:

npx -y botbridge-cc-helper-mcp

Usage

The server speaks MCP over stdio, so your MCP client launches it:

{
  "mcpServers": {
    "cc-helper": {
      "command": "npx",
      "args": ["-y", "botbridge-cc-helper-mcp"],
      "env": {
        "CC_HELPER_HOME": "C:\\Users\\you\\cc-helper"
      }
    }
  }
}

CC_HELPER_HOME is optional; omit it to use %USERPROFILE%\cc-helper.

Check the install from a terminal:

npx -y botbridge-cc-helper-mcp --selftest

Tools

ToolWhat it does
cc_helper_statusReport whether a local Helper install is present and where its folders are.
cc_helper_dispatchQueue a job ({ id, title, prompt }) into inbox\ for the local Helper to pick up.
cc_helper_task_statusRead one job's state from running\ / done\.
cc_helper_list_tasksList queued, running, and finished jobs.
cc_helper_stopWrite a stop control command to cancel a running job.

Environment variables

VariableDefaultMeaning
CC_HELPER_HOME%USERPROFILE%\cc-helper on Windows, ~/cc-helper elsewhereFolder the bridge reads and writes job files in.

Source

The bridge ships byte-identical inside the Bot Bridge CC Helper VS Code extension as scripts/cc-helper-mcp.js, which is the source of truth. npm run sync refreshes bin/botbridge-cc-helper-mcp.js from it; prepack fails the build if the two ever drift apart.

License

MIT. See LICENSE.

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.