cyberchitta/llm-context.py
by Various
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
MCP
cyberchitta/llm-context.py
Added 1 June 2026
Overview
Shares code with large language models via the Model Context Protocol or clipboard. Rule-based customization lets you switch between tasks like code review and documentation. Includes smart code outlining to improve context clarity.
Best for
Best for
Developers who regularly share code with LLMs for review, documentation, or refactoring tasks.
Use cases
- Send code snippets to an LLM for review without manual copy-paste
- Automatically tailor code context for different documentation requests
- Generate structured code outlines for LLM-based refactoring
How to use
Install
uvx --from llm-context lc-mcp Tools exposed
lc_missinglc_changedlc_outlineslc_preview
Tested with
Claude Code
Example client config
{\n "mcpServers": {\n "llm-context": {\n "command": "uvx",\n "args": ["--from", "llm-context", "lc-mcp"]\n }\n }\n} Notes
Shares code with large language models via the Model Context Protocol or clipboard. Rule-based customization lets you switch between tasks like code review and documentation. Includes smart code outlining to improve context clarity.
301 stars on GitHub. Last updated 2026-05-27. Licensed Apache-2.0.
Use cases
- Send code snippets to an LLM for review without manual copy-paste
- Automatically tailor code context for different documentation requests
- Generate structured code outlines for LLM-based refactoring
Pros
- Supports multiple sharing methods (MCP and clipboard)
- Rule system makes task switching easy and repeatable
- Smart outlining reduces noise in the context sent to the LLM
Cons
- Requires Python runtime to use
- Rule configuration has a learning curve for new users
- Limited to code context sharing, not general file or data sharing
Indexed from awesome-mcp-servers-punkpeye and enriched against its public facts.
Pros
- Supports multiple sharing methods (MCP and clipboard)
- Rule system makes task switching easy and repeatable
- Smart outlining reduces noise in the context sent to the LLM
Cons
- Requires Python runtime to use
- Rule configuration has a learning curve for new users
- Limited to code context sharing, not general file or data sharing
Open-source & AI alternatives
Swap-in tools that solve the same job. Weigh the trade-offs before you commit.
oraios/serena
Various
A powerful MCP toolkit for coding, providing semantic retrieval and editing capabilities - the IDE for your agent
repowise-dev/repowise
Various
Codebase intelligence for AI and humans: code health scores, auto-generated docs, git analytics, dead code detection, and architectural decisions via MCP.
Get the free Developer’s Field Guide
A 27-page field guide to the AI coding workflow with Claude. Claude Code, MCP servers, the prompt patterns that work, and what to delegate. Free.
Enter your work email. We send it straight over, plus a few short notes worth knowing. Unsubscribe any time.
