A2CR MCP Server

Save WorkBaton checkpoints and WorkStash notes for AI agent handoffs.

Remote serverstreamable-httpPython

What is the A2CR MCP server?

If you already use A2CR, the a2cr mcp server is the piece that lets your assistant work with it directly. Save WorkBaton checkpoints and WorkStash notes for AI agent handoffs.

What the server does

A2CR is an open-source local MCP workspace for AI agent handoffs. It lets Codex, Claude Code, Cursor, and other MCP-capable agents save WorkBaton checkpoints, store temporary WorkStash notes, coordinate through WorkThreads, and resume long coding work from a fresh AI window.

Installation

Because this one is hosted, setup is mostly authentication — you point your client at the endpoint and approve access. Nothing runs on your machine, so there is no runtime to keep patched.

Available tools

The toolset is worth reading before you wire it up, because it tells you what the integration is really for:

  • explain_a2cr_flows — explain when to use WorkBaton, WorkStash, or WorkThreads
  • get_account_limits — show current local workspace limits for Slots, retention, and WorkStash
  • should_save_workbaton — advise whether a compact WorkBaton checkpoint is useful now
  • save_context — save a WorkBaton checkpoint in the local workspace
  • resume_context — find and load the right WorkBaton for a fresh AI window
  • load_context — load a specific Slot number or named WorkBaton
  • list_contexts — list active WorkBaton Slots
  • delete_context — delete a named WorkBaton Slot
  • should_use_work_stash — advise whether a supporting note belongs in WorkStash
  • store_work_stash — store a temporary supporting note in the local workspace
  • get_work_stash — retrieve a referenced WorkStash entry
  • list_work_stash — list WorkStash metadata and quota usage

Credentials and setup notes

Configuration is passed through the environment: A2CR_LOCAL_DB, A2CR_UI_URL. Treat anything key-shaped as a real credential — scope it to the minimum the server needs, and rotate it if it ever lands in a shared config.

Worth knowing first

  • Your data travels to the provider's service, so the usual questions apply about what you send and what they retain.
  • With 13 tools registered it takes up a noticeable share of the context window; turn it off in projects that never touch A2CR.
  • Missing credentials fail quietly in some clients — if no tools show up, check the environment block first.
  • Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.

Where it fits

This sits in the planning and project tracking group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. A2CR's toolset — explain_a2cr_flows, get_account_limits, should_save_workbaton and 10 more — is a fair guide to whether it matches your workflow. It is maintained by a2cr; worth a glance at recent repository activity before you build anything load-bearing on it.

This entry was verified against A2CR's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.

Available tools

ToolWhat it does
explain_a2cr_flowsexplain when to use WorkBaton, WorkStash, or WorkThreads.
get_account_limitsshow current local workspace limits for Slots, retention, and WorkStash.
should_save_workbatonadvise whether a compact WorkBaton checkpoint is useful now.
save_contextsave a WorkBaton checkpoint in the local workspace.
resume_contextfind and load the right WorkBaton for a fresh AI window.
load_contextload a specific Slot number or named WorkBaton.
list_contextslist active WorkBaton Slots.
delete_contextdelete a named WorkBaton Slot.
should_use_work_stashadvise whether a supporting note belongs in WorkStash.
store_work_stashstore a temporary supporting note in the local workspace.
get_work_stashretrieve a referenced WorkStash entry.
list_work_stashlist WorkStash metadata and quota usage.
delete_work_stashdelete a WorkStash entry that is no longer needed.

How to install the A2CR MCP server

Generic MCP JSON:

```json
{
  "mcpServers": {
    "a2cr": {
      "command": "a2cr-mcp",
      "args": [],
      "env": {
        "A2CR_LOCAL_DB": "/optional/path/to/a2cr.db"
      }
    }
  }
}

Configuration as documented by the project. Restart the client after saving.

Configuration

VariableDescriptionRequired
A2CR_LOCAL_DBConfiguration value read at startup.Optional
A2CR_UI_URLEndpoint or connection string the server talks to.Yes

Example prompts to try

  • Use A2CR to explain a2cr flows.
  • Use A2CR to get account limits.
  • Use A2CR to should save workbaton.

Frequently asked questions

It connects A2CR to MCP-compatible AI assistants such as Claude and Cursor, exposing 13 tools (explain_a2cr_flows, get_account_limits, should_save_workbaton, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with A2CR directly.