context7 MCP (0% less tokens). Quick setup: npx context7-slim --setup
npm install 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.



A token-optimized version of the Context7 Model Context Protocol (MCP) server.
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.
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.
| Metric | Original | Slim | Reduction |
|--------|----------|------|-----------|
| Tools | 2 | 2 | -0% |
| Schema Tokens | 778 | 122 | 84.3% |
| Claude Code (est.) | ~1,918 | ~1,262 | ~34.2% |
> Benchmark Info
> - Original: @upstash/context7-mcp@2.0.2
> - Schema tokens measured with tiktoken (cl100k_base)
> - Claude Code estimate includes ~570 tokens/tool overhead
``bashClaude Desktop - auto-configure
npx context7-slim --setup claude
Done! Restart your app to use context7.
$3
`bash
Claude Code (creates .mcp.json in project root)
claude mcp add context7 -s project -- npx -y context7-slim@latestWindows: use cmd /c wrapper
claude mcp add context7 -s project -- cmd /c npx -y context7-slim@latestVS Code (Copilot, Cline, Roo Code)
code --add-mcp '{"name":"context7","command":"npx","args":["-y","context7-slim@latest"]}'
`Manual Setup
Click to expand manual configuration options
$3
Add to your
claude_desktop_config.json:| OS | Path |
|----|------|
| Windows |
%APPDATA%\Claude\claude_desktop_config.json |
| macOS | ~/Library/Application Support/Claude/claude_desktop_config.json |`json
{
"mcpServers": {
"context7": {
"command": "npx",
"args": ["-y", "context7-slim@latest"]
}
}
}
`$3
Add to
.cursor/mcp.json (global) or (project):`json
{
"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) │
└─────────────────────────────────────────────────────────────────┘
`$3
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 unchangedZero functionality loss. 34.2% token savings.
Available Tool Groups
| Group | Actions |
|-------|---------|
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 testsFAQ
$3
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.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.
MCPSlim is a community project. It wraps official MCP servers transparently — the original server does all the real work.
MIT
---
Powered by MCPSlim — MCP Token Optimizer
Reduce AI context usage. Keep full functionality.