Context7 by Upstash injects up-to-date, version-specific library documentation and code examples directly into AI prompts. Eliminates hallucinated APIs and outdated code generation by pulling documentation straight from the source at query time.
Scanned 6/8/2026
Install via CLI
openskills install agentskillexchange/skills---
name: "Context7 MCP Documentation Server for LLM Code Editors"
slug: "context7-mcp-documentation-server-llm-code-editors"
description: "Context7 by Upstash injects up-to-date, version-specific library documentation and code examples directly into AI prompts. Eliminates hallucinated APIs and outdated code generation by pulling documentation straight from the source at query time."
github_stars: 51326
verification: "security_reviewed"
source: "https://github.com/upstash/context7"
category: "Library & API Reference"
framework: "MCP"
tool_ecosystem:
github_repo: "upstash/context7"
github_stars: 51326
---
# Context7 MCP Documentation Server for LLM Code Editors
Context7 by Upstash injects up-to-date, version-specific library documentation and code examples directly into AI prompts. Eliminates hallucinated APIs and outdated code generation by pulling documentation straight from the source at query time.
## Installation
Use the upstream install or setup path that matches your environment:
- npx ctx7 setup
- To remove the generated setup later, run npx ctx7 remove. If you globally installed the CLI with npm install -g ctx7, remove that package separately with npm uninstall -g ctx7.
Basic usage or getting-started notes:
- [!NOTE]
- **API Key Recommended**: Get a free API key at [context7.com/dashboard](https://context7.com/dashboard) for higher rate limits.
- Set up Context7 for your coding agents with a single command:
- Source: https://github.com/upstash/context7
- Extracted from upstream docs: https://raw.githubusercontent.com/upstash/context7/HEAD/README.md
## Source
- [Agent Skill Exchange](https://agentskillexchange.com/skills/context7-mcp-documentation-server-llm-code-editors/)
No comments yet. Be the first to comment!
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.