Summary
Exposes five tools that analyze your MCP configuration to surface hidden token costs. Points at your Claude Desktop or Cursor config files, counts tokens consumed by each server and tool schema, assigns letter grades based on context window impact, and flags duplicate tool names across servers. Useful when you notice sluggish responses or hit context limits and want to see which MCP servers are burning tokens before you type anything. The analyze_tools command breaks down per-tool costs with optimization suggestions, while generate_report produces a markdown health check with actionable recommendations for trimming bloat.
Keep your Mac awake while Claude Code and 40+ AI agents run. Sleeps when they're idle.
One time payment $9 →
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →
mcp-checkup
Your MCP servers are eating your context window. Find out how much.
mcp-checkup is an MCP server that analyzes your MCP setup — measuring the token cost of every installed server and tool, finding duplicates, grading efficiency, and generating optimization reports.
Quick Start
npx mcp-checkup
Then ask your AI assistant:
"Run an MCP health check on my setup"
"How many tokens are my MCP servers using?"
"Generate an MCP health report"
Why?
Every MCP tool costs 550–1,400 tokens just for its schema. A server with 50 tools can eat 30,000+ tokens before you type anything. Most developers have no idea how much context window their MCP servers are consuming.
Real examples from the community:
- Adding GitHub MCP increased one user's token usage from 34K to 80K (source)
- One developer found 67,000 tokens consumed by just 4 servers before any conversation (source)
- Context7 (240K weekly downloads) has tool descriptions costing 3x more tokens than necessary (source)
Tools
analyze_servers
Scan your MCP config and measure the token cost of every installed server. Auto-detects config files.
"Which of my MCP servers costs the most tokens?"
analyze_tools
Deep-dive into a specific server — per-tool token costs, grades, bloated descriptions, and optimization suggestions.
"Break down the token cost of my GitHub MCP server"
find_duplicates
Find duplicate tool names across your installed servers. Redundant tools waste context for no benefit.
"Do any of my MCP servers have overlapping tools?"
count_tokens
Count tokens in any text. Useful for estimating context usage.
"How many tokens is this prompt?"
generate_report
Full markdown health report: server grades (A-F), token costs, duplicates, and actionable recommendations.
"Generate a full MCP health report"
Grading System
Per-Tool Grades
| Grade | Tokens | Meaning |
|---|---|---|
| A | ≤100 | Excellent — minimal context cost |
| B | ≤300 | Good — reasonable schema size |
| C | ≤600 | Fair — could be optimized |
| D | ≤1000 | Poor — bloated schema |
| F | >1000 | Failing — severely impacts context window |
Per-Server Grades
| Grade | Total Tokens | Meaning |
|---|---|---|
| A | ≤500 | Lean and efficient |
| B | ≤1500 | Reasonable |
| C | ≤3000 | Getting heavy |
| D | ≤6000 | Significant context cost |
| F | >6000 | Major context window drain |
Installation
Claude Desktop / Claude Code
{
"mcpServers": {
"mcp-checkup": {
"command": "npx",
"args": ["-y", "mcp-checkup"]
}
}
}
Cursor
Add to .cursor/mcp.json with the same format.
Auto-Detection
mcp-checkup automatically finds your MCP config in these locations:
.mcp.json(current directory)- Claude Desktop config (Windows/macOS/Linux)
.cursor/mcp.json
Or pass a custom path to any tool.
How It Compares
| Tool | Purpose | Approach |
|---|---|---|
| mcp-checkup | Diagnose token costs | Analyze & report — see exactly what each tool costs |
| lean-ctx | Reduce token usage | Compress context at runtime |
| MCP Inspector | Debug MCP servers | Test connections and tool calls |
Use mcp-checkup first to find the problem, then decide how to fix it.
Part of the MCP Toolkit
- webcheck-mcp — Website health analysis
- git-summary-mcp — Git repository intelligence
- mcp-checkup — MCP setup health analyzer
- dev-utils-mcp — Developer utilities
- codescan-mcp — Codebase health scanner
- deadlink-checker-mcp — Dead link detector
License
MIT
Featured
Keep your Mac awake while Claude Code and 40+ AI agents run. Sleeps when they're idle.
One time payment $9 →Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →