Mcp Checkup

io.github.yifanyifan897645Published by GitHub account yifanyifan897645v0.1.0Updated Oct 24, 2026

Analyze your MCP setup: token costs, grades, duplicates, and optimization tips

VerifiedSTDIODesktop onlyDeveloper ToolsAI & ML

Overview

AI-generated overview

Analyzes your installed MCP servers to measure their token cost, grade their efficiency, find duplicate tools, and produce an optimization report.

What you can do
It scans your MCP configuration and measures the token cost of every installed server and tool. Tools include analyze_servers for a per-server cost overview, analyze_tools for a per-tool breakdown with grades and optimization suggestions, find_duplicates for overlapping tool names, count_tokens for arbitrary text, and generate_report for a full markdown health report with A-F grades.
When to use it
Use it when your context window feels crowded by MCP servers and you want to know which ones cost the most tokens. It is meant for diagnosing the problem before deciding what to trim or optimize.
Requirements
Runs locally over stdio, typically started with npx mcp-checkup, so Node.js and network access for the package download are needed. It auto-detects .mcp.json in the current directory, the Claude Desktop config, and .cursor/mcp.json, or accepts a custom config path. No accounts, API keys, or environment variables are declared.
Before you install
It reads your local MCP configuration files, which may contain server definitions and credentials for other servers; review what those files hold before pointing the tool at them. It reports on your setup rather than changing it, so no writes to your configuration are described.

Installation

In SourceWeft

  1. Open Mcp Checkup in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

mcp-checkup

[npm version] [npm downloads] [License: MIT]

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

bash
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

GradeTokensMeaning
A≤100Excellent — minimal context cost
B≤300Good — reasonable schema size
C≤600Fair — could be optimized
D≤1000Poor — bloated schema
F>1000Failing — severely impacts context window

Per-Server Grades

GradeTotal TokensMeaning
A≤500Lean and efficient
B≤1500Reasonable
C≤3000Getting heavy
D≤6000Significant context cost
F>6000Major context window drain

Installation

Claude Desktop / Claude Code

json
{  "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

ToolPurposeApproach
mcp-checkupDiagnose token costsAnalyze & report — see exactly what each tool costs
lean-ctxReduce token usageCompress context at runtime
MCP InspectorDebug MCP serversTest connections and tool calls

Use mcp-checkup first to find the problem, then decide how to fix it.

Part of the MCP Toolkit

View all servers →

License

MIT

Source: README.md at commit 3660945

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v0.1.0LatestSep 16, 2026

Score

50% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts