LLM Context
Smart context management for LLM workflows — rule-based file selection shared via MCP or clipboard.
Add to your client
Copy the config for your MCP client and paste it into its config file.
uv tool install "llm-context>=0.6.0"Paste into ~/Library/Application Support/Claude/claude_desktop_config.json
{
"mcpServers": {
"llm-context": {
"command": "uvx",
"args": [
"--from",
"llm-context",
"lc-mcp"
]
}
}
}Requires `uv` (the Python package runner). Install it from https://docs.astral.sh/uv/ if `uvx` is not found.
Before you start
- uv / uvx installed (used to install and run the lc-* commands and the MCP server)
- A project initialized with lc-init (creates .llm-context/)
About LLM Context
LLM Context is a Python tool for sharing relevant project code with LLMs through intelligent, rule-based file selection. It supports a clipboard workflow for chat interfaces and an MCP server (lc-mcp) so AI assistants can fetch additional files and code structure during conversations. Context is described by composable YAML+Markdown rules across five categories (prompt, filter, instruction, style, excerpt), with code excerpting that extracts structure across 15+ languages to reduce token usage.
Tools & capabilities (3)
lc_outlinesGenerate excerpted context (code structure outlines) from the current rule.
lc_previewValidate a rule's effectiveness — check file selection and context size before use.
lc_missingFetch specific files or implementations on demand (by param_type and data, with a timestamp).
When to use it
- Let an AI assistant pull in additional project files mid-conversation without manual copy-paste
- Validate that a task-specific rule selects the right files and fits within token limits before generating context
- Provision focused, task-scoped context for sub-agents (e.g. refactoring, debugging authentication)
- Explore a codebase's structure via outlines while keeping token usage low
Security notes
The server exposes filesystem read access (file selection, outlines, and on-demand file fetching) scoped to the project root path you provide. It runs locally over stdio with no authentication; only grant it access to projects you intend the AI to read.
LLM Context FAQ
Do I need the MCP server, or can I just use the clipboard?
Both work. The clipboard workflow (lc-select / lc-context) requires no server. The MCP integration (lc-mcp) is recommended so the AI can fetch additional files during a conversation without manual copying.
How do I add it to Claude Desktop?
Add an mcpServers entry to claude_desktop_config.json with command "uvx" and args ["--from", "llm-context", "lc-mcp"], then restart Claude Desktop.
What are rules?
Rules are YAML+Markdown files describing what context to provide for a task. They come in five categories (prm-, flt-, ins-, sty-, exc-) and can be composed from simpler reusable rules.
Alternatives to LLM Context
Microsoft's official browser-automation MCP using Playwright's accessibility tree (no vision model).
Up-to-date, version-specific library documentation injected into your coding agent.
Pack any local or remote repository into one AI-ready file your agent can grep and read incrementally.
Compare LLM Context with: