Skip to main content

Adapt MCP servers to many agentic framework.

Project description

MCPAdapt

PyPI version Python versions Tests License PyPI downloads GitHub Repo stars

Unlock 650+ MCP servers tools in your favorite agentic framework.

Model Context Protocol is an open-source protocol introduced by Anthropic which allows anyone to simply and quickly make tools and resources available as "MCP Servers".

Since its release more than 650 MCP servers have been created giving access to many data & tools to supported "MCP Client".

This project makes calling any MCP servers tools seemless from any agentic framework. Virtually providing your agentic worfklow access to 650+ MCP servers tools.

Look at glama.ai or smithery.ai to give you an idea of what your agent could access.

Installation Instructions

Smolagents

Smolagents 1.4.1 and above directly ships with mcpadapt integrated in their tool collections object. It means you can directly use it from smolagents:

uv add smolagents[mcp]

Other Frameworks

Each agent framework has its own set of optional dependencies to not clutter with useless dependencies. You choose the flavor you want by adding your framework in brackets in the installation command.

# with uv
uv add mcpadapt[langchain]

# or with pip
pip install mcpadapt[langchain]

Framework supported at the moment: smolagents, langchain.

You can also add multiple framework comma separated if needed.

Usage

Smolagents

Since mcpadapt is part of smolagents simple use tool collection from smolagents like:

from mcp import StdioServerParameters
from smolagents.tools import ToolCollection

serverparams = StdioServerParameters(command="uv", args=["run", "src/echo.py"])

with ToolCollection.from_mcp(serverparams) as tool_collection:
    ... # enjoy your tools!

Other Frameworks

MCPAdapt adapt any MCP servers into tools that you can use right in your agentic workflow:

from mcp import StdioServerParameters
from mcpadapt.core import MCPAdapt
from mcpadapt.smolagents_adapter import SmolAgentsAdapter

with MCPAdapt(
    # specify the command to run your favorite MCP server (support also smithery and co.)
    StdioServerParameters(command="uv", args=["run", "src/echo.py"]),

    # specify the adapter you want to use to adapt MCP into your tool in this case smolagents.
    SmolAgentsAdapter(),
) as tools:
    # enjoy your smolagents tools as if you wrote them yourself
    ...

MCP Adapt supports Smolagents, Langchain, [pydantic.dev, Llammaindex and more...]*. *coming soon.

See our examples for more details on how to use.

Contribute

If your favorite agentic framework is missing no problem add it yourself it's quite easy:

  1. create a new module in src/mcpadapt/{name_of_your_framework}_adapter.py:
class YourFrameworkAdapter(ToolAdapter):
    def adapt(
        self,
        func: Callable[[dict | None], mcp.types.CallToolResult],
        mcp_tool: mcp.types.Tool,
    ) -> YourFramework.Tool:
        # HERE implement how the adapter should convert a simple function and mcp_tool (JSON Schema)
        # into your framework tool. see smolagents_adapter.py for an example
    
    def async_adapt(
        self,
        afunc: Callable[[dict | None], Coroutine[Any, Any, mcp.types.CallToolResult]],
        mcp_tool: mcp.types.Tool,
    ) -> YourFramework.Tool:
        # if your framework supports async function even better use async_adapt.
  1. and that's it, test that your adapter is working and send us a PR to share it with the world.

Roadmap

  • initial framework for anyone to start creating adapters
  • support for smolagents
  • support for pydantic-ai
  • support for langchain
  • support for llamaindex
  • support for swarm
  • support for crewAI?
  • support for remote MCP Servers via SSE
  • support for jupyter notebook
  • add tests

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

mcpadapt-0.0.12.tar.gz (192.7 kB view details)

Uploaded Source

Built Distribution

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

mcpadapt-0.0.12-py3-none-any.whl (10.5 kB view details)

Uploaded Python 3

File details

Details for the file mcpadapt-0.0.12.tar.gz.

File metadata

  • Download URL: mcpadapt-0.0.12.tar.gz
  • Upload date:
  • Size: 192.7 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.12.9

File hashes

Hashes for mcpadapt-0.0.12.tar.gz
Algorithm Hash digest
SHA256 0a18f179357388516a28879e60f31640edf1e8d23c4f3c73d994c3da9ed0f0bb
MD5 6da3fcee6827fb7a5616aebf0a1a49af
BLAKE2b-256 a70cb8b522cb7386f097445962fa24d829a2736cfc4adaad51ced281a4412357

See more details on using hashes here.

Provenance

The following attestation bundles were made for mcpadapt-0.0.12.tar.gz:

Publisher: release.yml on grll/mcpadapt

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file mcpadapt-0.0.12-py3-none-any.whl.

File metadata

  • Download URL: mcpadapt-0.0.12-py3-none-any.whl
  • Upload date:
  • Size: 10.5 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.12.9

File hashes

Hashes for mcpadapt-0.0.12-py3-none-any.whl
Algorithm Hash digest
SHA256 574154afecc9a91474e419b4bab0f57276a30018b0efc684c781765258cfbb43
MD5 df205e9fc4b57ce40626186e319cbf4a
BLAKE2b-256 17fb92fe80366c649701a7197aa1a4ed9ff8768d32ef4b7e3317e40c969355ea

See more details on using hashes here.

Provenance

The following attestation bundles were made for mcpadapt-0.0.12-py3-none-any.whl:

Publisher: release.yml on grll/mcpadapt

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

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