agent-handoff-mcp
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@agent-handoff-mcpsave a checkpoint with git diff and summary for my current work"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
agent-handoff-mcp
Centralized multi-project state & handoff MCP server (Streamable HTTP). AI agents (Claude Code, Codex, Cursor, …) save checkpoints in one session and resume in another with under 500 tokens of input overhead. The full specification is captured across the guides in the Documentation section.
Quickstart
cd agent-handoff
./dev.sh # bootstraps .venv, installs dev deps, starts the server
# with the web dashboard: http://127.0.0.1:8766/
# MCP endpoint: http://127.0.0.1:8765/mcpdev.sh uses repo-local defaults (./state.db, loopback, dashboard on) and
supports --fresh, --no-dashboard, --port, --dash-port, --token,
--log, and --check (run lint+tests). See ./dev.sh --help. To run
manually instead:
python3 -m venv .venv && .venv/bin/pip install -e ".[dev]"
DATABASE_PATH=./state.db .venv/bin/python main.pyThe server listens for MCP at http://127.0.0.1:8765/mcp and exposes a
GET /health endpoint ({"status":"ok","db":"writable"}).
Related MCP server: Graph
Features
12 tools · 2 resources · 1 prompt — every command explained in
docs/mcp-usage.mdHandoff context < 500 tokens — deterministic
ceil(len/4)metric with a documented truncation orderSeed context — drop
.md/.jsonfiles in a repo's.agent-handoff/folder (glossary, API contracts, business flows) and the server folds them into the handoff summary + serves them on demandGit snapshots —
save_checkpointcapturesgit diff HEAD --statplus untracked files (capped at 200 lines / 4 KB)SQLite WAL with a single async writer connection (no
database is locked)Fail-closed auth —
Authorization: Bearer <token>required whenMCP_AUTH_TOKENis set; refuses to bind non-loopback without a tokenCode-graph integration — queries
code-review-graph+graphify, and can store per-project graphs inside the MCP database instead of each repoAuto-start — the server can spawn and supervise graph-server subprocesses
Documentation
Guide | What it covers |
Install, run, connect MCP clients, first-run walkthrough | |
The command reference: every tool, resource and prompt, with parameters, examples, responses and error codes | |
All environment variables, the auth model, and the data layout | |
Graph servers, manual start, auto-start, DB-backed per-project graphs, stale-artifact cleanup | |
Docker, systemd service, backups, Tailscale/SSH exposure, hardening | |
Done vs. planned work, PRD acceptance-criteria coverage matrix | |
Feature milestones, fixes, and known limitations |
Tests
.venv/bin/python -m pytest -qCovers the PRD acceptance criteria: migrations/WAL, path validation, git
capture, the 500-token budget, retention pruning, fail-closed auth (401s),
/health, 20 parallel mixed requests, code-graph capture, DB-backed graph
storage, and auto-start supervision.
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Servers
- AlicenseAqualityAmaintenanceLocal-first MCP server that gives any AI coding agent per-project memory, workflow intelligence, and always-on, lossless token & context optimization.37353MIT
- Alicense-qualityCmaintenanceAn MCP server that gives your agent a persistent project brain: vision, architecture decisions, conventions, roadmaps, and automatic session handoff.486MIT
- AlicenseAqualityAmaintenanceA local-first MCP server that snapshots project working state into a structured context object, enabling agents to share and resume sessions seamlessly without leaving your machine.54Apache 2.0
- AlicenseBqualityBmaintenancePersistent, branch-aware workflow state memory MCP server for AI coding assistants. Tracks tasks, accepted decisions, and active blockers to prevent session context bloat and speed up development.8184421MIT
Related MCP Connectors
User-owned memory for AI agents, Copilot, Claude, IDEs, CLIs, and chat apps over remote MCP.
The project brain for AI coding agents — memory, decisions, sprints, knowledge base via MCP.
Private-by-default, local-first memory/context/task orchestrator for MCP apps and agents.
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/zetkey/agent-handoff'
If you have feedback or need assistance with the MCP directory API, please join our Discord server