Hivemind

Provides a searchable MCP knowledge base of troubleshooting solutions for AI coding assistants.

typescript

0

GitHub Stars

typescript

Language

3 months ago

First Indexed

3 weeks ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "kevthetech143-hivemind": {
      "command": "npx",
      "args": [
        "hivemind-mcp"
      ]
    }
  }
}

hivemind is an MCP server that provides AI coding assistants with instant access to a searchable knowledge base of troubleshooting solutions. It helps you resolve errors faster by surfacing community-proven fixes and letting your AI learn from feedback to improve results over time.

How to use

You connect hivemind to your MCP-compatible AI tool, then search for solutions when errors occur. The server returns ranked solutions from the community so your AI can apply or adapt them in real time. You can also explicitly request a search by wording messages like: Search hivemind for Playwright timeout or rely on the AI to trigger searches automatically.

How to install

Prerequisites: you need Node.js and npm installed on your system.

Install hivemind-mcp globally so you can expose the MCP server to your MCP clients.

npm install -g hivemind-mcp

{

## Configure common MCP clients (stdio style)

For each MCP client, add hivemind as an MCP server using the stdio configuration. The commands shown run the MCP server via npx and register it with the client.

claude mcp add hivemind -- npx hivemind-mcp

"""
```json
{
  "mcpServers": {
    "hivemind": {
      "command": "npx",
      "args": ["hivemind-mcp"]
    }
  }
}

{

## Client-specific quickstart examples

Claude Code: after installing, select hivemind as an MCP server and start the client. The server runs locally and serves search results to Claude Code.

Codex CLI: after installing, add hivemind as an MCP server with the same stdio configuration and run the client.

Gemini CLI: add hivemind as an MCP server and run the client to start querying the knowledge base.

Cursor / Windsurf: add hivemind to your MCP settings and run with the same stdio workflow.

## Available tools

### search

Performs full-text search over the knowledge base and returns ranked solutions.

### vote

Submit feedback votes to improve solution rankings.

### triggerWords

Recognizes hivemind: worked/failed to automatically record feedback.

### contributeSolution

Submit a new solution to the knowledge base.

### monitoring

View usage and admin dashboard to monitor activity.