context7-slim

Context7 MCP server optimized for AI assistants — Reduce context window tokens by 34.2% while keeping full functionality. Compatible with Claude, ChatGPT, Gemini, Cursor, and all MCP clients.

What is context7-slim?

A token-optimized version of the Context7 Model Context Protocol (MCP) server.

The Problem

MCP tool schemas consume significant context window tokens. When AI assistants like Claude or ChatGPT load MCP tools, each tool definition takes up valuable context space.

The original @upstash/context7-mcp loads 2 tools consuming approximately ~1,918 tokens — that's space you could use for actual conversation.

The Solution

context7-slim intelligently groups 2 tools into 2 semantic operations, reducing token usage by 34.2% — with zero functionality loss.

Your AI assistant sees fewer, smarter tools. Every original capability remains available.

Performance

Benchmark Info

• Original: @upstash/context7-mcp@2.0.2
• Schema tokens measured with tiktoken (cl100k_base)
• Claude Code estimate includes ~570 tokens/tool overhead

Quick Start

One-Command Setup (Recommended)

# Claude Desktop - auto-configure
npx context7-slim --setup claude

# Cursor - auto-configure
npx context7-slim --setup cursor

# Interactive mode (choose your client)
npx context7-slim --setup

Done! Restart your app to use context7.

CLI Tools (already have CLI?)

# Claude Code (creates .mcp.json in project root)
claude mcp add context7 -s project -- npx -y context7-slim@latest

# Windows: use cmd /c wrapper
claude mcp add context7 -s project -- cmd /c npx -y context7-slim@latest

# VS Code (Copilot, Cline, Roo Code)
code --add-mcp '{"name":"context7","command":"npx","args":["-y","context7-slim@latest"]}'

Manual Setup

Claude Desktop

Add to your claude_desktop_config.json:

{
  "mcpServers": {
    "context7": {
      "command": "npx",
      "args": ["-y", "context7-slim@latest"]
    }
  }
}

Cursor

Add to .cursor/mcp.json (global) or <project>/.cursor/mcp.json (project):

{
  "mcpServers": {
    "context7": {
      "command": "npx",
      "args": ["-y", "context7-slim@latest"]
    }
  }
}

How It Works

MCPSlim acts as a transparent bridge between AI models and the original MCP server:

┌─────────────────────────────────────────────────────────────────┐
│  Without MCPSlim                                                │
│                                                                 │
│  [AI Model] ──── reads 2 tool schemas ────→ [Original MCP]    │
│             (~1,918 tokens loaded into context)                 │
├─────────────────────────────────────────────────────────────────┤
│  With MCPSlim                                                   │
│                                                                 │
│  [AI Model] ───→ [MCPSlim Bridge] ───→ [Original MCP]           │
│       │                │                      │                 │
│   Sees 2 grouped      Translates to        Executes actual   │
│   tools only         original call       tool & returns    │
│   (~1,262 tokens)                                              │
└─────────────────────────────────────────────────────────────────┘

How Translation Works

1. AI reads slim schema — Only 2 grouped tools instead of 2
2. AI calls grouped tool — e.g., interaction({ action: "click", ... })
3. MCPSlim translates — Converts to original: browser_click({ ... })
4. Original MCP executes — Real server processes the request
5. Response returned — Result passes back unchanged

Zero functionality loss. 34.2% token savings.

Available Tool Groups

Plus 2 passthrough tools — tools that don't group well are kept as-is with optimized descriptions.

Compatibility

• ✅ Full functionality — All original @upstash/context7-mcp features preserved
• ✅ All AI assistants — Works with Claude, ChatGPT, Gemini, Copilot, and any MCP client
• ✅ Drop-in replacement — Same capabilities, just use grouped action names
• ✅ Tested — Schema compatibility verified via automated tests

FAQ

Does this reduce functionality?

No. Every original tool is accessible. Tools are grouped semantically (e.g., click, hover, drag → interaction), but all actions remain available via the action parameter.

Why do AI assistants need token optimization?

AI models have limited context windows. MCP tool schemas consume tokens that could be used for conversation, code, or documents. Reducing tool schema size means more room for actual work.

Is this officially supported?

MCPSlim is a community project. It wraps official MCP servers transparently — the original server does all the real work.

License

MIT