fast-agent
byevalstate· 1 MCP server
> [!TIP] > Please see https://fast-agent.ai for latest documentation.
How to install fast-agent?
evalstate/fast-agent
$git clone https://github.com/evalstate/fast-agentInstalls into the current project.
›Prefer a prompt? Paste this to your agent
Install fast-agent by running `git clone https://github.com/evalstate/fast-agent`, then use it for the current task and follow its documentation at https://github.com/evalstate/fast-agent.
README.md
| 1 | <p align="center"> |
| 2 | <a href="https://pypi.org/project/fast-agent-mcp/"><img src="https://img.shields.io/pypi/v/fast-agent-mcp?color=%2334D058&label=pypi" /></a> |
| 3 | <a href="#"><img src="https://github.com/evalstate/fast-agent/actions/workflows/main-checks.yml/badge.svg" /></a> |
| 4 | <a href="https://github.com/evalstate/fast-agent/issues"><img src="https://img.shields.io/github/issues-raw/evalstate/fast-agent" /></a> |
| 5 | <a href="https://discord.gg/xg5cJ7ndN6"><img src="https://img.shields.io/discord/1358470293990936787" alt="discord" /></a> |
| 6 | <img alt="Pepy Total Downloads" src="https://img.shields.io/pepy/dt/fast-agent-mcp?label=pypi%20%7C%20downloads"/> |
| 7 | <a href="https://github.com/evalstate/fast-agent-mcp/blob/main/LICENSE"><img src="https://img.shields.io/pypi/l/fast-agent-mcp" /></a> |
| 8 | </p> |
| 9 | |
| 10 | ## Start Here |
| 11 | |
| 12 | > [!TIP] |
| 13 | > Please see https://fast-agent.ai for latest documentation. |
| 14 | |
| 15 | **`fast-agent`** is a flexible way to interact with LLMs, excellent for use as a Coding Agent, Development Toolkit, Evaluation or Workflow platform. |
| 16 | |
| 17 | To start an interactive session with shell support, install [uv](https://astral.sh/uv) and run |
| 18 | |
| 19 | ```bash |
| 20 | uvx fast-agent-mcp@latest -x |
| 21 | ``` |
| 22 | |
| 23 | To start coding with Hugging Face inference providers or use your OpenAI Codex plan: |
| 24 | |
| 25 | ```bash |
| 26 | # Code with Hugging Face Inference Providers |
| 27 | uvx fast-agent-mcp@latest --pack hf-dev |
| 28 | |
| 29 | # Code with Codex (agents optimized for OpenAI) |
| 30 | uvx fast-agent-mcp@latest --pack codex |
| 31 | ``` |
| 32 | |
| 33 | Enter a shell with `!`, or run shell commands e.g. `! cd web && npm run build`. |
| 34 | |
| 35 | Manage skills with the `/skills` command, and connect to MCP Servers with `/connect`. The default **`fast-agent`** registry contains skills to let you set up LSP, Agent and Tool Hooks, Compaction strategies, Automation and more. |
| 36 | |
| 37 | ```bash |
| 38 | # /connect supports stdio or streamable http (with OAuth) |
| 39 | |
| 40 | # Start a STDIO server |
| 41 | /connect @modelcontextprotocol/server-everything |
| 42 | |
| 43 | # Connect to a Streamable HTTP Server |
| 44 | /connect https://huggingface.co/mcp |
| 45 | ``` |
| 46 | |
| 47 | It's recommended to install **`fast-agent`** to set up the shell aliases and other tooling. |
| 48 | |
| 49 | ```bash |
| 50 | # Install fast-agent |
| 51 | uv tool install -U fast-agent-mcp |
| 52 | |
| 53 | # Run fast-agent with opus, shell support and subagent/smart mode |
| 54 | fast-agent --model opus -x --smart |
| 55 | ``` |
| 56 | |
| 57 | Use local models with the generic provider, or automatically create the correct configuration for `llama.cpp`: |
| 58 | |
| 59 | ```bash |
| 60 | fast-agent model llamacpp |
| 61 | ``` |
| 62 | |
| 63 | Any **`fast-agent`** setup or program can be used with any ACP client - the simplest way is to use `fast-agent-acp`: |
| 64 | |
| 65 | ```bash |
| 66 | # Run fast-agent inside Toad |
| 67 | toad acp "fast-agent-acp -x --model sonnet" |
| 68 | ``` |
| 69 | |
| 70 | **`fast-agent`** enables you to create and interact with sophisticated multimodal Agents and Workflows in minutes. It is the first framework with complete, end-to-end tested MCP Feature support including Sampling and Elicitations. |
| 71 | |
| 72 | `fast-agent` is CLI-first, with an optional prompt_toolkit-powered interactive terminal prompt (TUI-style input, completions, and in-terminal menus); responses can stream live to the terminal via rich without relying on full-screen curses UIs or external GUI overlays. |
| 73 | |
| 74 | <!--  --> |
| 75 | |
| 76 | The simple declarative syntax lets you concentrate on composing your Prompts and MCP Servers to [build effective agents](https://www.anthropic.com/research/building-effective-agents). |
| 77 | |
| 78 | Model support is comprehensive with native support for Anthropic, OpenAI and Google providers as well as Azure, Ollama, Deepseek and dozens of others via TensorZero. Structured Outputs, PDF and Vision support is simple to use and well tested. Passthrough and Playback LLMs enable rapid development and test of Python glue-code for your applications. |
| 79 | |
| 80 | Recent features include: |
| 81 | |
| 82 | - Agent Skills (SKILL.md) |
| 83 | - MCP-UI Support | |
| 84 | - OpenAI Apps SDK (Skybridge) |
| 85 | - Shell Mode |
| 86 | - Advanced MCP Transport Diagnsotics |
| 87 | - MCP Elicitations |
| 88 | |
| 89 | <img width="800" alt="MCP Transport Diagnostics" src="https://github.com/user-attachments/asset |
Related
6 picksType
- langchain-mcp-adaptersMake Anthropic Model Context Protocol (MCP) tools compatible with LangChain and LangGraph agents.Jul 2026
- mcporterTypeScript runtime and CLI for connecting to configured Model Context Protocol servers.Jul 2026
- mcp-proxyA MCP server which proxies requests to a remote MCP server over streamable HTTP or SSE.Jul 2026
- mcp-atlassianThe Model Context Protocol (MCP) Atlassian integration is an open-source implementation that bridges Atlassian products (Jira and Confluence) with AI language models following Anthropic's MCP specification.Jul 2026
- open-webuiOpen WebUIJul 2026
- rulesyncUnified AI rules management CLI tool that generates configuration files for various AI development toolsJul 2026
