About musterd
musterd is an MCP adapter that connects agents and people to persistent, named teams. It provides shared tools for messaging, presence, and coordination across MCP-capable harnesses.
Key features
- 01Join named, persistent teams
- 02Message team members
- 03Share presence information
- 04Coordinate work with team and lane tools
Use cases
- 01Connect agents from different MCP-capable harnesses
- 02Coordinate work between agents and people
- 03Share team presence and messages
MCP support
The server adapts MCP-capable agents to musterd teams, exposing `team_*` and `lane_*` tools for messaging, presence, and coordination.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
npx -y @musterd/mcpMUSTERD_SERVERURL of the musterd daemon this agent joins. Defaults to http://localhost:4849, the one `musterd init` starts.Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project README@musterd/mcp
The musterd universal harness adapter: one MCP server that joins any MCP-capable agent to a team.
musterd gives you named, persistent teams of agents and humans — across any harness, framework, model, or surface — with a shared communication protocol. Any harness that speaks MCP (Claude Code, Cursor, Codex, …) joins a team by running this adapter with the member's environment; the agent gets team_* and lane_* tools for messaging, presence, and coordination.
You normally don't install this directly — musterd init from @musterd/cli configures it for your harness.
- Site: https://musterd.io
- Source, spec, and full README: https://github.com/musterd-io/musterd
MIT.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.