MCP ExplorerExplorer

Llm Tools Mcp

@rectalogicon 10 months ago
2 Apache-2.0
FreeCommunity
AI Systems
MCP toolbox plugin for llm

Overview

What is Llm Tools Mcp

llm-tools-mcp is a toolbox plugin designed for the MCP (Model Context Protocol) that facilitates the integration of various tools with the LLM (Large Language Model) command-line interface and Python API.

Use cases

Use cases for llm-tools-mcp include automating file reading tasks, integrating LLM capabilities into software applications, and enhancing data processing workflows with language models.

How to use

To use llm-tools-mcp, you can either utilize the LLM command-line tool by executing commands that interact with files or use the LLM Python API to integrate the MCP functionalities into your Python scripts.

Key features

Key features of llm-tools-mcp include support for reading files, integration with the LLM command-line tool, and the ability to run commands in a secure MCP Filesystem Server environment.

Where to use

llm-tools-mcp can be used in fields such as natural language processing, software development, and any application that requires interaction with large language models and file systems.

Content

llm-tools-mcp

PyPI
Changelog
Tests
License

MCP tools support

Usage

To use this with the LLM command-line tool:

$ echo "The magic word is frumble" > magic.txt
$ uv run llm --tool 'MCP(command="npx", args=["-y", "@modelcontextprotocol/server-filesystem", "."])' "What is the magic word in the file ./magic.txt?" --tools-debug
Secure MCP Filesystem Server running on stdio
Allowed directories: [ '/Users/aw/Projects/rectalogic/llm-tools-mcp' ]

Tool call: read_file({'path': './magic.txt'})
  "CallToolResult(meta=None, content=[TextContent(type='text', text='The magic word is frumble\\n', annotations=None)], isError=False)"

The magic word in the file `magic.txt` is **frumble**.

With the LLM Python API:

import llm
from llm_tools_mcp import MCP

model = llm.get_model("gpt-4.1-mini")

result = model.chain(
    "Example prompt goes here",
    tools=[MCP(command="npx", args=["-y", "@modelcontextprotocol/server-filesystem", "."])]
).text()

Development

To set up this plugin locally, first checkout the code. Then create a new virtual environment:

cd llm-tools-mcp
uv sync

To run the tests:

uv run pytest

Tools

No tools

Comments

Recommend MCP Servers

View All MCP Servers