LLM Context
Share code with LLMs via Model Context Protocol or clipboard. Rule-based customization enables easy switching between different tasks (like code review and documentation). Includes smart code outlining.
What is LLM Context?
LLM Context is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to share code with llms via model context protocol or clipboard. rule-based customization enables easy switching between different tasks (like code review and documentation). includes smart code outlinin...
Share code with LLMs via Model Context Protocol or clipboard. Rule-based customization enables easy switching between different tasks (like code review and documentation). Includes smart code outlining.
This server falls under the Knowledge & Memory category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- Share code with LLMs via Model Context Protocol or clipboard
Use Cases
Maintainer
Works with
Installation
NPM
npx -y llm-contextManual Installation
npx -y llm-contextConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use LLM Context
LLM Context is a Python-based MCP server that gives AI coding assistants structured, task-specific access to your codebase without overwhelming them with unnecessary files. It uses composable rule profiles that you define per project, so you can instantly switch between contexts for code review, documentation writing, or feature work. The server exposes MCP tools like lc_outlines, lc_preview, and lc_missing that let Claude explore your project structure on demand rather than receiving a static paste. This makes it especially valuable in large monorepos where indiscriminate context dumps waste tokens and confuse the model.
Prerequisites
- Python 3.10+ and the uv package manager installed (https://github.com/astral-sh/uv)
- Claude Desktop or another MCP-capable client
- A local project repository to index — run lc-init from the project root
- No external API keys required — the server operates entirely on local files
Install llm-context via uv
Use the uv tool installer to make the lc-mcp binary available system-wide. This also installs the lc-init, lc-select, lc-context, and lc-outlines CLI commands.
uv tool install "llm-context>=0.6.0"Initialize a project
Run lc-init from your repository root. This creates a .llm-context/ directory containing rule profiles and copies skill files into .claude/skills/ for use with Claude Code.
cd /path/to/your/project
lc-initPreview and select files
Use lc-preview to see which files a given rule profile would include, then lc-select for interactive file selection. This lets you tune the context before sharing it.
lc-preview code-review
lc-selectAdd the server to Claude Desktop
Edit your Claude Desktop config file to register the llm-context MCP server. The server is launched via uvx so no additional path setup is needed.
Restart Claude Desktop and verify
After saving the config, restart Claude Desktop. The lc_outlines, lc_preview, and lc_missing tools should appear in Claude's tool list. Ask Claude to call lc_outlines to confirm the connection.
LLM Context Examples
Client configuration
Add this block to ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) to register the server.
{
"mcpServers": {
"llm-context": {
"command": "uvx",
"args": ["--from", "llm-context", "lc-mcp"]
}
}
}Prompts to try
Once the server is connected, use these prompts in Claude to leverage project context tools.
- "Use lc_outlines to show me the structure of this project"
- "Call lc_preview with the 'code-review' rule and tell me what files it includes"
- "Fetch the implementation of the authentication module using lc_missing"
- "Switch to the documentation rule profile and summarize the project architecture"Troubleshooting LLM Context
lc-mcp command not found after installation
Run 'uv tool update-shell' or ensure ~/.local/bin is in your PATH. You can verify with 'which lc-mcp' after sourcing your shell profile.
lc_outlines returns no files or an empty outline
Make sure lc-init was run from the project root and that a .llm-context/ directory exists. Also verify the active rule profile includes the correct file globs for your project layout.
Claude Desktop does not show the llm-context tools
Check that the config JSON is valid (no trailing commas), that uvx is in the system PATH visible to Claude Desktop, and that you fully restarted the app after editing the config.
Frequently Asked Questions about LLM Context
What is LLM Context?
LLM Context is a Model Context Protocol (MCP) server that share code with llms via model context protocol or clipboard. rule-based customization enables easy switching between different tasks (like code review and documentation). includes smart code outlining. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install LLM Context?
Install via npm with the command: npx -y llm-context. Then add the server configuration to your AI client's JSON config file (e.g., claude_desktop_config.json or .cursor/mcp.json).
Which AI clients work with LLM Context?
LLM Context works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is LLM Context free to use?
Yes, LLM Context is open source and available under the Apache 2.0 license. You can use it freely in both personal and commercial projects.
LLM Context Alternatives — Similar Knowledge & Memory Servers
Looking for alternatives to LLM Context? Here are other popular knowledge & memory servers you can use with Claude, Cursor, and VS Code.
MemPalace
★ 52.6kA local AI memory system that stores all conversations verbatim and organizes them into navigable structures. It provides 19 MCP tools for AI assistants to search and retrieve past decisions, debugging sessions, and architecture debates automatically
Kratos
★ 25.7k🏛️ Memory System for AI Coding Tools - Never explain your codebase again. MCP server with perfect project isolation, 95.8% context accuracy, and the Four Pillars Framework.
Context Mode
★ 15.4kAn MCP server that preserves LLM context by intercepting large data outputs and returning only concise summaries or relevant sections. It enables efficient sandboxed code execution, file processing, and documentation indexing across multiple programm
Memu
★ 13.7kMemory for 24/7 proactive agents like OpenClaw.
MemOS
★ 9.3kMemOS (Memory Operating System) is a memory management operating system designed for AI applications. Its goal is: to enable your AI system to have long-term memory like a human, not only remembering what users have said but also actively invoking, u
Everos
★ 5.4kBuild, evaluate, and integrate long-term memory for self-evolving agents.
Browse More Knowledge & Memory MCP Servers
Explore all knowledge & memory servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up LLM Context in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use LLM Context?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.