Progress will not be saved. This browser is blocking storage (often private browsing). You can still learn, but closing the tab loses your progress.
lastmile-ai/mcp-agent
Build effective agents using Model Context Protocol and simple workflow patterns
- Stars
- 8,591
- +7 days
- —
- Forks
- 903
- Language
- Python
- License
- Apache-2.0
- Last push
- 25 Jan 2026
Summary
Summary written by AI from the README; it may be imprecise.This Python framework enables developers to build AI agents connected to Model Context Protocol servers. It provides implementations of agent workflow patterns like routers, orchestrators, and evaluators, and supports durable execution through Temporal. Developers can also expose their workflows and agents directly as standard MCP servers.
Use it when
- Build multi-agent workflows using patterns like orchestrator-workers, routers, or parallel map-reduce
- Connect LLMs to multiple MCP servers while managing server connections and tool discovery automatically
- Expose an agent or custom Python workflow as an MCP server for clients like Claude Desktop or Cursor
Install
pip
uvx mcp-agent initpip
pip install mcp-agentpip
uvx mcp-agentCommands quoted from the repo's README. Read the README before running them.
Needs a token or API key.
Stars over 90 days
Collecting: 2 of 90 days so far. The chart appears after 7 days.