Rhizome MCP

When a coding agent dies mid-task, the task frees itself.

rhizome-mcp gives autonomous coding agents crash-safe task coordination over MCP: claims are renewable expiring leases, in_progress is derived — never stored — and an interrupted attempt hands its checkpoint to whichever session picks the work up next. One static Go binary, one SQLite database per project. No daemon, no accounts, no cloud.

It works with agents from different products at once — Claude Code, Codex, GitHub Copilot, VS Code, and any other MCP-compatible client — giving them one shared, durable view of project work.

Recorded from real server output by demo/record.sh — nothing staged.

[Why](#why) · [How it compares](#how-it-compares) · [Quick start](#quick-start) · [Monitor your project](#monitor-your-project) · [MCP surface](#mcp-surface) · [Documentation](#documentation)

Why

AI coding agents are concurrent, context-limited, and interruptible. A TODO.md or a single chat context doesn't survive that. rhizome-mcp is built around those failure modes:

• Crash-safe claiming. Issues are claimed atomically with renewable leases. in_progress is never a stored status — it is derived from an active lease, so a vanished agent can't lock an issue forever. When the lease expires, the issue becomes claimable again. A partial unique index guarantees at most one active attempt per issue at the database level.
• Token-efficient by contract. Compact list projections (a 100-issue page stays under 64 KB — enforced by an integration test), graph nodes that exclude free-text bodies at the SQL layer, snippet-only search, delta sync via event IDs, and a bounded single-call work-context package.
• Durable project memory. Checkpoints with next steps, supersedable decision records, append-only event history, and FTS5 full-text search across issues, comments, decisions, and notes. A fresh session resumes from the last checkpoint instead of re-deriving state.
• Planning and dependency graphs. Cycle-checked blocks relations, epics, claimable entry-point highlighting, and atomic batch planning (up to 50 issues, 100 relations, and 20 decisions in one all-or-nothing transaction).
• Review workflow. Review requests pin an exact issue version and event position; approving changed code is structurally impossible — a stale request can only be superseded and re-pinned.

Watch a stale approval get refused

• Resource reservations. A claim can atomically reserve files, directories, globs, or logical resources (a port, a migration window, a deploy slot); an overlapping claim fails fast with the holder and its lease expiry named, instead of two agents colliding later.

Watch a reservation conflict fail a claim atomically

• Concurrency discipline throughout. Optimistic versioning on mutations, replay-safe idempotency keys, stable machine-actionable error codes.
• Human observability without a server. rhizome-mcp board prints live leases, blockers, and the review queue, or writes a self-contained HTML snapshot; the CLI reads everything as tables, JSON, or Mermaid.

This repository tracks its own backlog through the server it ships — work is selected, claimed, checkpointed, and reviewed via rhizome-mcp itself (AGENTS.md).

Use it when several agent sessions (or several agent products) work the same repository over time and you need handoffs, parallel work, and recovery after crashes or context limits.

Skip it if you need a hosted multi-user tracker with auth, permissions, and a web UI — this is a local single-developer tool by design.

How it compares

Compare agent task trackers on guarantees under failure, not on feature lists — local-first SQLite storage and MCP support are table stakes in this category.

Full comparison with sources, pinned versions, and honest "choose X if" guidance: [How rhizome-mcp compares](https://odrin.github.io/rhizome-mcp/#/compare).

Quick start

Install and run

Choose the approach that matches your workflow:

Zero-install trial via npm

Try rhizome-mcp immediately with no separate binary install, no Go toolchain:

npx rhizome-mcp serve

Works with any MCP client. See packages/npm/README.md for platform coverage. Great for quick evaluation.

Claude Code plugin

/plugin marketplace add Odrin/rhizome-mcp

/plugin install rhizome-mcp@rhizome

Registers the MCP server (via npx, no binary install) and adds the rhizome-task-workflow and rhizome-execution-plan skills. Each repository you track still needs a one-time npx rhizome-mcp init in its root.

VS Code

Install Rhizome MCP (odrin.rhizome-mcp) from the Marketplace or Open VSX. The extension bundles the platform binary, registers the MCP server automatically, and adds Rhizome: Initialize Project to the Command Palette. No terminal, no mcp.json editing. Details: docs/10-vscode-extension.md.

Prefer a standalone binary with a plain mcp.json entry instead? Install the binary below and use this one-click link: Add to VS Code.

Native binary installer

Download and install a release binary for your platform. Verifies checksums, installs to ~/.local/bin by default:

curl -fsSL https://raw.githubusercontent.com/Odrin/rhizome-mcp/main/scripts/install.sh | sh

irm https://raw.githubusercontent.com/Odrin/rhizome-mcp/main/scripts/install.ps1 | iex

Official MCP Registry

Use rhizome-mcp via the official MCP Registry, available in the Model Context Protocol registry as io.github.Odrin/rhizome-mcp for clients that consume the registry.

Initialize and connect

Initialize tracking inside your repository:

rhizome-mcp init

Then register the server with your MCP client. Automated setup for common clients:

rhizome-mcp connect claude    # Claude Code

rhizome-mcp connect codex # Codex rhizome-mcp connect vscode # VS Code (if using standalone binary instead of extension) rhizome-mcp connect json # Template for any other client

Use --print for a dry run. connect discovers your project's actual root (walking up from the current directory the same way serve does) and pins it with --project-root, so the written config works regardless of which subdirectory an MCP client later launches the server from. All four targets (claude, codex, vscode, json) agree on this. The manual equivalent for any MCP client, matching connect's own server key:

{

"mcpServers": { "rhizome-mcp": { "command": "/absolute/path/to/rhizome-mcp", "args": ["serve", "--project-root", "/absolute/path/to/your/repository"] } } }

or, via npx, without installing a binary at all:

{

"mcpServers": { "rhizome-mcp": { "command": "npx", "args": ["-y", "rhizome-mcp", "serve", "--project-root", "/absolute/path/to/your/repository"] } } }

connect detects when it is itself running through the npx rhizome-mcp wrapper and automatically emits this npx form instead of the wrapper's resolved binary path, which lives in the npx cache and goes stale on eviction or a version bump. A config written with a resolved absolute path (the default otherwise) is machine-specific and not meant to be checked in and shared across machines; pass connect TARGET --command to instead emit a bare rhizome-mcp command name that relies on PATH, for a portable config you do intend to share, provided every machine that uses it has rhizome-mcp on PATH.

Stdio is the default transport; protocol output goes to stdout, logs to stderr.

That's it — connected agents start with open_project using the absolute repository root, retain its project_ref, and pass that reference to later project-scoped calls. See the agent workflow guide for the complete workflow. The returned metadata links the rhizome://guides/agent-workflow, rhizome://guides/issue-lifecycle, and rhizome://guides/multi-agent-handoff resources, and repository agents can load the rhizome-task-workflow skill from .github/skills/.

Install the agent workflow skill

For agents that support the open [Agent Skills](https://agentskills.io