Build and evaluate MCP-capable agents with fast-agent

Build and evaluate MCP-capable agents with fast-agent

Scaffold, run, inspect, and evaluate model-agnostic agents that connect to MCP servers, skills, shell tools, and workflow packs.

Prerequisites

Python, uv, fast-agent-mcp, target model provider, optional MCP servers

Installation

Use the upstream install or setup path that matches your environment:

• uv tool install -U fast-agent-mcp
• uv pip install fast-agent-mcp # install fast-agent!
• uv run agent.py # run your first agent
• uv run agent.py --model='o3-mini?reasoning=low' # specify a model

Requirements and caveats from upstream:

• Start by installing the uv package manager for Python. Then:
• Windows Users - there are a couple of configuration changes needed for the Filesystem and Docker MCP Servers - necessary changes are detailed within the configuration files.

Basic usage or getting-started notes:

• To start an interactive session with shell support, install uv and run

• Enter a shell with !, or run shell commands e.g. ! cd web && npm run build.

• fast-agent --model opus -x --smart

• Source: https://github.com/evalstate/fast-agent

• Extracted from upstream docs: https://raw.githubusercontent.com/evalstate/fast-agent/HEAD/README.md

Documentation

• https://fast-agent.ai

Source

• Agent Skill Exchange