apphandoff-mcp
Hosted MCP server + coordination layer for AI coding agents (Claude Code, Cursor, Codex, Lovable) — API contracts, schema, mismatch detection, shared handoff tickets
Documentation
AppHandoff MCP Server
AppHandoff is a hosted Model Context Protocol (MCP) server and coordination layer for AI coding agents. It gives Claude Code, Cursor, Codex, Lovable, and any spec-compliant MCP client a live, structured view of your app — scanned API contracts, database schema, frontend/backend mismatch detection, and shared handoff tickets — so multiple agents coordinate instead of guessing.
Endpoint: `https://api.apphandoff.com/api/mcp-bot`
Auth: OAuth 2.1 (discovery at `/.well-known/oauth-protected-resource`) · Transport: Streamable HTTP
Quick connect
| Client | Setup |
|---|---|
| Claude Code | `claude mcp add apphandoff https://api.apphandoff.com/api/mcp-bot` |
| Cursor | `.cursor/mcp.json`: `{"mcpServers":{"apphandoff":{"url":"https://api.apphandoff.com/api/mcp-bot"}}}` |
| Codex / other MCP clients | Paste the URL into the client's MCP settings — any spec-compliant client works |
| Lovable | Connect via Lovable's MCP integration using the same URL |
One URL, no project ID in config. On first connect you authenticate via OAuth in the browser; with one accessible project the server auto-binds it to your session.
What agents get
- Contract-aware context — the real API spec, database schema, and route-level usage from a scan of your repos (`get_api_spec`, `get_db_schema`), not a hallucination.
- Mismatch detection — what the frontend expects vs what the backend provides, surfaced as facts agents can act on (`get_mismatches`).
- Handoff tickets — shared work tracking with role lifecycle (backend, frontend, QA) on a Kanban board humans supervise (`get_handoff_requests`, `get_my_workload`, `report_handoff_request`).
- Natural-language gateway — `ask_apphandoff` routes plain-English asks to the right tool, with confirmation before anything mutating.
- Deploy & health checks — pre-deploy validation and health dashboards (`deploy_check`, `get_health`).
Why a coordination layer
Frameworks like LangGraph, CrewAI, and AutoGen orchestrate agents you build. Coding agents in IDEs — Claude Code, Cursor, Codex — are agents you *use*: separate processes from separate vendors with no shared runtime. They coordinate through shared state instead: tickets, contracts, and claims on a server all of them can reach. That's what AppHandoff provides.
Docs & links
- Getting started with the MCP server
- What is the AppHandoff MCP server?
- Agent orchestration overview
- MCP server feature page
- Set up MCP with Lovable
- Pricing
© AppHandoff · apphandoff.com
Frequently asked questions
What is apphandoff-mcp?
apphandoff-mcp is Hosted MCP server + coordination layer for AI coding agents (Claude Code, Cursor, Codex, Lovable) — API contracts, schema, mismatch detection, shared handoff tickets
How do I install apphandoff-mcp?
Open the GitHub repository and follow its README. Most MCP servers are added to your client's MCP config, then called by your agent.
Is apphandoff-mcp open source?
Yes — it is hosted on GitHub at https://github.com/TeamK2K/apphandoff-mcp.
Related MCP tools
Official remote MCP server for Atlassian. Securely connect Jira, Confluence, Jira Service Management, Bitbucket, and Compass to Claude, ChatGPT, Cursor, VS Code, and other AI tools using OAuth 2.1 or API tokens.
Open-source coding agent memory. Records issues, attempts, fixes and decisions, then warns your agent before it repeats an approach that already failed. Native MCP server for Claude Code, Cursor, Antigravity and Codex. 100% local, no cloud, no telemetry. MIT.
AI Skills, MCP Tools, and CLI for Unity Engine. Full AI develop and test loop. Use cli for quick setup. Efficient token usage, advanced tools. Any C# method may be turned into a tool by a single line. Works with Claude Code, Gemini, Copilot, Cursor and any other absolutely for free.
Cut AI token costs 95%+ on code exploration. The leading MCP server for precise, symbol-level GitHub code retrieval via tree-sitter AST. Works with Claude Code, Cursor & any MCP client. 313B+ tokens saved.
Unity MCP acts as a bridge between AI assistants and your Unity Editor. Give your LLM tools to manage assets, control scenes, edit scripts, and automate tasks within Unity.
🔥 Official Firecrawl MCP Server - Adds powerful web scraping and search to Cursor, Claude and any other LLM clients.
Run your own MCP server? See who uses it and what to fix.
Measure it with TrackMCP