Skip to main content

Fastmcp Agents Project

Project description

FastMCP 🚀 Agents 🤖

FastMCP Agents bridges the gap between the generic tools in MCP servers and the specialized tools you need to solve your problem and gives you a straight-forward way to manage tool sprawl:

  1. It turns generic tools in any MCP server into specialized tools that you can use anywhere
  2. It can (optionally) embed an expert Agent into any MCP server

Whether you wrote the MCP server or GitHub did, FastMCP Agents can "wrap" any MCP server.

How do I use it?

Follow our quickstart guide to get started.

Why Agents as Tools?

Bad Tools make bad Agents

Every MCP Server has a set of tools. It's up to the AI Agent to figure out, based on the provided names, descriptions, and arguments for the tools, how to leverage them to solve the user's question. When there's a problem with the instructions, the AI Agent's performance suffers.

Generic Tools are Bad Tools

With MCP, you run around and hook in all of these generic Tools to your various AI Agents and you let the AI Agent decide which ones are the right ones. A simple 3 MCP Server workflow can easily have 100+ tools. Each one is a shiny distraction on the path to solving the user's problem. These tools do almost the right thing almost most of the time.

Specialized Tools don't scale

So like me, you decide that your AI Agents shouldn't have 100 tools, they should only know about the exact tools they need to complete the task at hand. So you give up on MCP servers, write all your own tools.

How's it work?!

Simply take your existing MCP Server

"mcp-server-tree-sitter": {
  "command": "uvx",
  "args": ["mcp-server-tree-sitter"]
}

And wrap it with an Agent:

"mcp-server-tree-sitter": {
  "command": "uvx",
  "args": [
    "fastmcp_agents", "cli",
    "agent",
    "--name","ask_tree_sitter",
    "--description", "Ask the tree-sitter agent to find items in the codebase.",
    "--instructions", "You are a helpful assistant that provides users a simple way to find items in their codebase.",
    "wrap", 
    "uvx", "mcp-server-tree-sitter"
  ]
}

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

fastmcp_agents-0.2.3.tar.gz (242.4 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

fastmcp_agents-0.2.3-py3-none-any.whl (84.6 kB view details)

Uploaded Python 3

File details

Details for the file fastmcp_agents-0.2.3.tar.gz.

File metadata

  • Download URL: fastmcp_agents-0.2.3.tar.gz
  • Upload date:
  • Size: 242.4 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: uv/0.7.11

File hashes

Hashes for fastmcp_agents-0.2.3.tar.gz
Algorithm Hash digest
SHA256 276f5e33aefc556a1b6eb723d338547ce22a828b6abde48296cb3c50722aec57
MD5 c9dfe5463c61dd32a53a92a8473e7ef2
BLAKE2b-256 9736cc2ffca3f10f36aeaf6d0fbdd58d2f89e4bd17c546bef98a6f50f4cc5e2a

See more details on using hashes here.

File details

Details for the file fastmcp_agents-0.2.3-py3-none-any.whl.

File metadata

File hashes

Hashes for fastmcp_agents-0.2.3-py3-none-any.whl
Algorithm Hash digest
SHA256 11bdf50414ea1b2da3460945f4644c5c19a7b56365d015add8a884dd67c28b6f
MD5 4d19ee5220a394ba407630dcce018d02
BLAKE2b-256 9637efff3bd079651d8456506011ef91b9f09efa0c66ed6db6136d845f86600b

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page