MCPgee
MCPgee
MCPgeeMCPgee

LLM Shell Integration

v1.0.0•Developer Tools•stable

Connect to MCP servers right from your shell. Plugin for simonw/llm.

aiclaudegeminillmmcp
Share:
37
Stars
0
Downloads
0
Weekly
0/5
View on GitHub

What is LLM Shell Integration?

LLM Shell Integration is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to connect to mcp servers right from your shell. plugin for simonw/llm.

Connect to MCP servers right from your shell. Plugin for simonw/llm.

This server falls under the Developer Tools category on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • Connect to MCP servers right from your shell. Plugin for sim

Use Cases

Shell-based MCP client
simonw/llm integration
VirtusLab

Maintainer

LicenseApache-2.0
Languagepython
Versionv1.0.0
UpdatedMay 13, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux
View SourceBrowse All Servers

Installation

Manual Installation

npx llm-tools

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use LLM Shell Integration

llm-tools-mcp is a plugin for Simon Willison's llm CLI tool that turns it into a full MCP client, allowing you to connect to any MCP server directly from your shell and use its tools in llm prompts. It supports stdio, SSE, and streamable HTTP transports, meaning you can wire up filesystem servers, database servers, or any other MCP-compatible service and drive them from the command line. This is especially useful for developers who want to test MCP servers, script AI workflows, or use multiple LLM providers (OpenAI, Gemini, Ollama, Claude) with the same set of MCP tools.

Prerequisites

  • Python 3.9 or later
  • Simon Willison's llm CLI installed (pip install llm)
  • At least one LLM provider configured in llm (e.g., llm install llm-claude-3 and an Anthropic API key)
  • An MCP server to connect to (stdio, SSE, or HTTP)
  • An MCP-compatible client or shell environment
1

Install the llm-tools-mcp plugin

Install the plugin using the llm plugin manager. This makes the MCP tool group available in all subsequent llm invocations.

llm install llm-tools-mcp
2

Create the MCP server configuration file

Create ~/.llm-tools-mcp/mcp.json and define the MCP servers you want to connect to. The example below connects to the official filesystem MCP server.

mkdir -p ~/.llm-tools-mcp
cat > ~/.llm-tools-mcp/mcp.json << 'EOF'
{
  "servers": [
    {
      "name": "filesystem",
      "command": "npx",
      "args": ["-y", "@modelcontextprotocol/server-filesystem", "/tmp"]
    }
  ]
}
EOF
3

Verify the plugin is recognized

Run llm plugins to confirm llm-tools-mcp appears in the list of installed plugins.

llm plugins
4

Run a prompt using MCP tools

Use the -T MCP flag to enable the MCP tool group and --ta to auto-approve tool calls. The plugin dynamically loads tools from all configured MCP servers.

llm --ta -T MCP "What files are in /tmp? Show me the name of the first one."
5

Use a custom configuration path

If you want to use a different config file for a specific invocation, pass the path as an argument to the MCP tool group.

llm --ta -T 'MCP("/path/to/custom/mcp.json")' "List the available tools"

LLM Shell Integration Examples

Client configuration

Example ~/.llm-tools-mcp/mcp.json connecting to a filesystem and a SQLite MCP server.

{
  "servers": [
    {
      "name": "filesystem",
      "command": "npx",
      "args": ["-y", "@modelcontextprotocol/server-filesystem", "/home/user/projects"]
    },
    {
      "name": "sqlite",
      "command": "uvx",
      "args": ["mcp-server-sqlite", "--db-path", "/home/user/data.db"]
    }
  ]
}

Prompts to try

Once the plugin is installed and configured, try these shell commands to exercise MCP tools.

- "llm --ta -T MCP 'List all files in the project directory'"
- "llm --ta -T MCP 'Read the contents of README.md and summarize it'"
- "llm --ta -T MCP 'Query the SQLite database for all users created this month'"
- "llm --ta -T MCP 'What tools are available from the connected MCP servers?'"

Troubleshooting LLM Shell Integration

MCP tools do not appear in llm tools list

This is expected behavior — MCP tools are loaded dynamically and won't appear in the static tool list. Use --ta -T MCP in your llm command to activate them at invocation time.

Plugin fails to connect to an MCP server

Verify the command and args in mcp.json are correct and that the MCP server binary is installed. Test the server independently first with npx or uvx before wiring it through llm-tools-mcp.

Tool calls are rejected or prompt for approval repeatedly

Add the --ta flag (tool auto-approve) to your llm command to automatically approve tool calls without interactive prompts.

Frequently Asked Questions about LLM Shell Integration

What is LLM Shell Integration?

LLM Shell Integration is a Model Context Protocol (MCP) server that connect to mcp servers right from your shell. plugin for simonw/llm. It connects AI assistants to external tools and data sources through a standardized interface.

How do I install LLM Shell Integration?

Follow the installation instructions on the LLM Shell Integration GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.

Which AI clients work with LLM Shell Integration?

LLM Shell Integration works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is LLM Shell Integration free to use?

Yes, LLM Shell Integration is open source and available under the Apache-2.0 license. You can use it freely in both personal and commercial projects.

Learn More About MCP Servers

Getting Started with MCP

Set up your first MCP server in minutes

MCP Setup Guide

Configure MCP in Claude, Cursor & VS Code

All MCP Tutorials

18+ hands-on guides for developers

MCP FAQ

40+ answers about Model Context Protocol

LLM Shell Integration Alternatives — Similar Developer Tools Servers

Looking for alternatives to LLM Shell Integration? Here are other popular developer tools servers you can use with Claude, Cursor, and VS Code.

Ecc

★ 188.2k

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

Javaguide

★ 155.8k

Java 面试 & 后端通用面试指南，覆盖计算机基础、数据库、分布式、高并发、系统设计与 AI 应用开发

Gemini CLI

★ 104.5k

A secure MCP server that wraps the Google Gemini CLI, allowing clients to query Gemini models using local OAuth sessions without requiring an API key. It provides tools for model interaction and diagnostics with built-in protection against command in

Awesome MCP Servers

★ 87.3k

⭐ Curated list of Model Context Protocol (MCP) servers - tools that extend Claude Desktop, Cursor, Windsurf, and other MCP clients with custom capabilities.

MCP Servers

★ 86.0k

Model Context Protocol Servers

CC Switch

★ 77.5k

A cross-platform desktop All-in-One assistant for Claude Code, Codex, OpenCode, OpenClaw, Gemini CLI & Hermes Agent. Only official website: ccswitch.io

Browse More Developer Tools MCP Servers

Explore all developer tools servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

Developer ToolsBrowse All Servers

Quick Config Preview

{ "mcpServers": { "llm-tools": { "command": "npx", "args": ["-y", "llm-tools"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

Ready to use LLM Shell Integration?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides
Explore All ServersRead Our Guides