agent-harnesses-mcp is an open-source MCP server that provides recommendations, search, and head-to-head decision guides for over 100 agent harnesses. It is designed for AI developers and researchers working with LLM-based agents, offering weekly rescoring and structured comparison tools.
agent-harnesses-mcp sits in PulseGate's Autonomous agents & workflows category. Helping users select and compare agent harnesses for LLM-based agents. It is built as an open-source project for AI developers and researchers. agent-harnesses-mcp is open source under the CC-BY-SA-4.0 license. agent-harnesses-mcp is available on the command line and API, and it can be self-hosted.
Behind agent-harnesses-mcp is Ryan Alberts, and it first shipped in 2026. Development happens publicly on GitHub with 211 stars and 74 commits in the last 90 days. Among its 6 catalogued features are MCP server, agent harness recommendations, and search. It exposes integrations via an MCP server and a public API.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do