# Beadhive

Aggregates distributed beads issue tracking across multiple repositories into one workspace for coding agents.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI · ★ 28
- Author: beadhive
- License: MIT · policy=link-only · description only; the file stays with the author
- Source: https://github.com/beadhive/beadhive
- Updated: 2026-10-24
- HTML: https://affpapa.org/en/nevibecode/mcp/beadhive

## What it does

Beadhive operates as a central bridge across decentralized issue databases powered by beads. Every tracked repository maintains an independent task ledger called a hive. The MCP server gives agents visibility into cross-project work queues without forcing you to clone every repository locally.

Behind the scenes, the tool orchestrates external utilities such as `bd`, `git`, `dolt`, `docker`, and `git-workspace`. It is an orchestrator, not a standalone tracker. Task records avoid your local `~/.beadhive/` directory; instead, issues stay in Dolt databases under `refs/dolt/data` on remote Git branches.

Running `bh` requires external tools like `bd` and `dolt` on your machine, so installing via PyPI leaves binary dependency management up to you.

## Requirements
- Needs: Python and uv (commands run via uvx)

## Install

### Claude Code (native platform)

**Platform CLI**
```bash
claude mcp add beadhive -- uvx beadhive
```
uvx runs the command named after the package; if the README names another one, use uvx --from beadhive <command>

### Codex

**Platform CLI**
```bash
codex mcp add beadhive -- uvx beadhive
```
uvx runs the command named after the package; if the README names another one, use uvx --from beadhive <command>

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "beadhive": {
            "command": "uvx",
            "args": [
                "beadhive"
            ]
        }
    }
}
```
uvx runs the command named after the package; if the README names another one, use uvx --from beadhive <command>

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "beadhive": {
            "type": "stdio",
            "command": "uvx",
            "args": [
                "beadhive"
            ]
        }
    }
}
```
uvx runs the command named after the package; if the README names another one, use uvx --from beadhive <command>

### Gemini CLI

**Platform CLI**
```bash
gemini mcp add beadhive uvx beadhive
```
uvx runs the command named after the package; if the README names another one, use uvx --from beadhive <command>

## When to use it
- track beads issues across several repositories simultaneously
- register new project repos into a shared hive workspace
- standardize issue labels across separated databases
- inspect issue lists without local checkouts of source trees

## Example prompts
- List all tasks ready for work across registered hives using bh
- Register github/org/core-service as a new beads hive
- Check current cross-repo issue status via Beadhive

## Similar
- [GitHub](https://affpapa.org/en/nevibecode/mcp/github.md) — MCP server · ★ 33918
- [GitDiagram](https://affpapa.org/en/nevibecode/mcp/gitdiagram.md) — MCP server · ★ 18446
- [Repowise](https://affpapa.org/en/nevibecode/mcp/repowise.md) — MCP server · ★ 7891
- [sem](https://affpapa.org/en/nevibecode/mcp/sem.md) — MCP server · ★ 3422
- [GitLab MCP Server](https://affpapa.org/en/nevibecode/mcp/gitlab-mcp-server.md) — MCP server · ★ 2065
- [Octocode MCP - AI Context Platform](https://affpapa.org/en/nevibecode/mcp/octocode-mcp-ai-context-platform.md) — MCP server · ★ 955

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md