Mindmesh MCP Server

Actor system for asyncio environments

Local serverstdioPython

What is the Mindmesh MCP server?

Actor system for asyncio environments. The mindmesh mcp server wraps that behind the Model Context Protocol, so an assistant can use it through 6 defined tools rather than through you.

What it actually does

class GreeterActor(BaseActor): def on_greet(self, msg: Greet) -> str: return f"Hello, {msg.name}!"

Its toolset

Everything the assistant can do here goes through one of these:

  • asyncio — native, zero external dependencies
  • fire-and — forget (tell) and request/response (ask) messaging
  • BaseActor — Subclass BaseActor to define an actor. Each actor owns a private asyncio queue (its mailbox) and processes one message at a time - no parallelism
  • ActorHive — ActorHive is the registry and lifecycle manager. It creates, starts, and stops actors
  • ActorAddr — ActorAddr is an opaque handle to an actor. It is the only way to interact with an actor from outside. Never hold a direct reference to an actor
  • tell — Enqueues any object as a fire-and-forget message. Returns immediately

Adding it to your client

The server ships on PyPI as mindmesh, so your MCP client can launch it on demand — there is no separate build step. Add the server block to your client's configuration, restart it, and the tools register themselves.

When to reach for it

Among the team communication options, the useful question is rarely "what can it do" but "what does it cost you to run" — permissions, credentials, and how much of your context its toolset consumes. Mindmesh's toolset — asyncio, fire-and, BaseActor and 3 more — is a fair guide to whether it matches your workflow. It is maintained by Marcin Glinski; worth a glance at recent repository activity before you build anything load-bearing on it.

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

Caveats

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • MCP clients confirm each tool call by default. Leave that on until you have watched what the mindmesh mcp server does with a few real requests.

Available tools

ToolWhat it does
asyncionative, zero external dependencies
fire-andforget (tell) and request/response (ask) messaging
BaseActorSubclass BaseActor to define an actor. Each actor owns a private asyncio queue (its mailbox) and processes one message at a time - no parallelism within a single actor.
ActorHiveActorHive is the registry and lifecycle manager. It creates, starts, and stops actors.
ActorAddrActorAddr is an opaque handle to an actor. It is the only way to interact with an actor from outside. Never hold a direct reference to an actor instance.
tellEnqueues any object as a fire-and-forget message. Returns immediately.

How to install the Mindmesh MCP server

{
  "mcpServers": {
    "mindmesh-1": {
      "command": "uvx",
      "args": ["mindmesh"]
    }
  }
}

Add to claude_desktop_config.json, then restart Claude Desktop.

Example prompts to try

  • Use Mindmesh to asyncio.
  • Use Mindmesh to fire-and.
  • Use Mindmesh to BaseActor.

Frequently asked questions

It connects Mindmesh to MCP-compatible AI assistants such as Claude and Cursor, exposing 6 tools (asyncio, fire-and, BaseActor, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Mindmesh directly.