A2CR is an MCP server for saving and resuming compact AI agent handoff state between chat windows. It stores client-encrypted WorkBaton checkpoints and temporary WorkStash notes so agents like Codex and Claude Code can continue long coding tasks without keeping full transcripts.
From the registry: Save WorkBaton checkpoints and WorkStash notes for AI agent handoffs.

$ python -m pip install --upgrade a2cr-mcphttps://pypi.org/project/a2cr-mcp/Please install the `a2cr-mcp` MCP server into my current AI client (that's you).
Required prerequisites (do these first if not already done):
- **Install Python package** — Install the A2CR MCP server from PyPI. Python 3.12 or 3.13 is recommended. Run: `python -m pip install --upgrade a2cr-mcp` (https://pypi.org/project/a2cr-mcp/)
- **Create A2CR API key** — Generate an API key from the hosted A2CR dashboard. Required to save and resume handoffs via the hosted service. (https://a2cr.app)
Canonical MCP server config (stdio transport):
- command: `a2cr-mcp`
- args: []
- required environment variables:
- `A2CR_API_KEY`: A2CR API key for authenticating to the hosted A2CR service. (example: `<your-a2cr-api-key>`)
- `A2CR_BASE_URL`: Base URL for the hosted A2CR service. The README shows the hosted public service URL and the server depends on that hosted backend in the default setup. (example: `<your-a2cr-base-url>`)
Note: The recommended install path is the Python stdio wrapper from PyPI. The README also mentions a Claude Desktop MCPB extension package, but that is a client-specific distribution path rather than the canonical MCP command/args/env shape.
Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.A2CR_API_KEYrequiredAPI key required to access the hosted A2CR service and save or resume handoff state.AI orchestration with hive-mind swarms, neural networks, and 87 MCP tools for enterprise dev.
Persistent codebase knowledge graph. Survives session restarts and context compaction.
A powerful toolkit for coding, providing semantic retrieval and editing capabilities.