mcpField
B
Bothread

Bothread

Local
bothread.vercel.appAI & Agents0Updated 16w ago
DocsRepositoryVisit website

About Bothread

Bothread is a local, open-source coordination hub for multiple coding agents working on one codebase under human supervision. It prevents file-edit collisions and adds a task board, change review, and approval controls.

Key features

  1. 01Shared message thread and task board
  2. 02Prevent edit collisions with file claims
  3. 03Review Git diffs by agent
  4. 04Task hand-offs and dependencies
  5. 05Pause agents and approve risky actions
  6. 06Local SQLite storage and activity audit

Use cases

  1. 01Assign planning, coding, and testing across agents
  2. 02Coordinate agents editing one codebase
  3. 03Review agent changes and choose what to merge
  4. 04Require approval for actions such as deploys or deletions

MCP support

Bothread runs an MCP server that provides compatible coding agents with collaboration-room tools, prompts, and resources for messaging, file claims, tasks, hand-offs, and approvals. It coordinates existing agents and does not call AI models itself.

#mcp#ai-agents#multi-agent#coordination#claude-code#cursor#local#developer-tools

Configuration

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

mcp.json · Universal config
{
  "mcpServers": {
    "bothread": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote"
      ]
    }
  }
}
Run commandnpx -y mcp-remote

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npmmcp-remote

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

The maintainer has not added details yet. Check the README in the repository.

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.