What are the prerequisites for running Tlon MCP Server?
You need Node.js v16 or later and a running Urbit ship with its access credentials.
@jamesacklin
基本信息
An MCP (Model Context Protocol) server that provides tools for interacting with Tlon agents.
工具列表暂未提供
当前收录暂时没有可展示的工具列表,不代表服务没有工具。请查阅项目文档了解支持的能力。
工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。
An MCP (Model Context Protocol) server that provides tools for interacting with Tlon agents on an Urbit ship. It enables AI assistants to send direct messages, read DM history, and list contacts via natural language commands.
Clone the repository, run npm install, then configure environment variables (URBIT_SHIP, URBIT_CODE, URBIT_HOST, URBIT_PORT, MCP_TRANSPORT). Start with npm start (stdio transport by default) or set MCP_TRANSPORT=http for HTTP mode. Use natural language queries in an MCP client such as Claude Desktop to invoke the send-dm, read-dm-history, and list-contacts tools.
You need Node.js v16 or later and a running Urbit ship with its access credentials.
Set the environment variables `URBIT_SHIP`, `URBIT_CODE`, `URBIT_HOST`, and `URBIT_PORT` to match your Urbit ship. Optionally change `MCP_TRANSPORT` between `stdio` (default) and `http`, and set `PORT` for HTTP mode.
Add an entry to `claude_desktop_config.json` with the command `/bin/sh -c "cd /path/to/server && node index.js"` and run `npm install` before configuring.
The server supports both stdio (default) and HTTP transports, controlled by the `MCP_TRANSPORT` environment variable.
Yes – the `read-dm-history` tool accepts an optional `count` parameter (default 100, maximum 500).

Yuppsy MCP: build and publish real estate websites from your AI assistant. Yuppsy lets your AI assistant create live websites for real estate agents and individual property listings. You don't need a designer or any code
🚀 The fast, Pythonic way to build MCP servers and clients.
YC (S26) | Open Computer History | Continuously record your company computer work, map your workflows, help you find work worth automating, and power your agents' context

DeepMark helps teachers deliver rapid, consistent marking with meaningful feedback for every student — in a fraction of the time. What once took a week, now takes one free period.
A search tool helps dev to solve the naming things problem.
评论