fast-agent
Code, Build and Evaluate agents - excellent Model and Skills/MCP/ACP/A2A Support
- 3.9k stars
- 451 forks
- 39 open issues
- Language: Python
- License: Apache-2.0
- updated
Install
local · uvx (python)claude mcp add fast-agent -- uvx fast-agent{
"mcpServers": {
"fast-agent": {
"command": "uvx",
"args": ["fast-agent"]
}
}
}{
"mcpServers": {
"fast-agent": {
"command": "uvx",
"args": ["fast-agent"]
}
}
}- Run the command above in your terminal (Claude Code), or paste the JSON config into claude_desktop_config.json (Claude Desktop).
- Replace any <placeholder> values with your API keys or paths.
- Restart Claude. The MCP server and its tools appear automatically.
Package name inferred from the repository name. Verify it exists on PyPI, or clone https://github.com/evalstate/fast-agent and follow its README.
Editor's note
Fast-agent is a Python framework for building, running, and evaluating LLM agents and multi-agent workflows from the command line. It connects to Claude and other models through the Anthropic API and supports MCP as both client and server, allowing users to connect to MCP servers via STDIO or Streamable HTTP with OAuth authentication managed through a built-in `fast-agent auth` command with KeyRing storage. The framework includes a prompt_toolkit-powered interactive terminal interface with completions and in-terminal menus, a `/skills` command for managing reusable agent capabilities defined in SKILL.md files, and a `/connect` command for attaching live MCP servers during a session. A notable standout is that fast-agent claims to be the only tool capable of inspecting Streamable HTTP Transport usage, which aids in debugging MCP compliance. Developers building agentic pipelines, evaluators testing model-tool interactions, and teams needing reproducible agent configurations stored as plain files will find the most use here. Any fast-agent setup can also be exposed as an ACP server for use with compatible clients.
2 items in this repository
Extract and analyze writing improvements from GitHub PR review comments. Use when asked to show review feedback, style changes, or editorial improvements from a GitHub pull request URL. Handles both explicit suggestions and plain text feedback. Produces structured output comparing original phrasing with reviewer suggestions to help refine future writing.
Investigate fast-agent session and history files to diagnose issues. Use when a session ended unexpectedly, when debugging tool loops, when correlating sub-agent traces with main sessions, or when analyzing conversation flow and timing. Covers session.json metadata, history JSON format, message structure, tool call/result correlation, and common failure patterns.
MCP Servers overview
What people ask about fast-agent
What is evalstate/fast-agent?
evalstate/fast-agent is mcp servers for the Claude AI ecosystem. Code, Build and Evaluate agents - excellent Model and Skills/MCP/ACP/A2A Support It has 3.9k GitHub stars and its last recorded update is dated 2026-10-23.
How do I install fast-agent?
You can install fast-agent by cloning the repository (https://github.com/evalstate/fast-agent) or following the README instructions on GitHub. ClaudeWave also provides quick install blocks on this page.
Is evalstate/fast-agent safe to use?
Our security agent has analyzed evalstate/fast-agent and assigned a Trust Score of 100/100 (tier: Verified). See the full breakdown of passed checks and flags on this page.
Who maintains evalstate/fast-agent?
evalstate/fast-agent is maintained by evalstate. The last recorded GitHub activity is dated 2026-10-23, with 39 open issues.
Are there alternatives to fast-agent?
Yes. On ClaudeWave you can browse similar mcp servers at /categories/mcp, sorted by popularity or recent activity.