mcp-schema-bloat-fixer
Reduces token costs from MCP tool schemas by analyzing bloat, compressing descriptions, and selecting only relevant tools for AI agents.
README
MCP Schema Bloat Fixer
Fight the invisible token tax that is killing your AI agents.
Repository: mcp-schema-bloat-fixer
The Problem (explained simply)
Imagine your AI agent is a smart kid trying to do homework.
But every time he starts, you force him to read a 200-page phone book of tools first.
By the time he finishes reading the phone book, he already forgot the homework question and also spent all his pocket money on “thinking tokens”.
That phone book is the tool schemas coming from MCP servers.
Many servers send 40-50% of the entire context window just on tool descriptions.
What This MCP Server Does
It gives your agent (or you) five superpowers:
| Tool | What it does (simple) |
|---|---|
analyze_schema_bloat |
Tells you which tools are the biggest space-wasters |
compress_tool_description |
Makes long tool descriptions short but still clear |
select_relevant_tools |
Picks only the 3-5 tools the agent actually needs right now |
estimate_context_cost |
Shows how many tokens (and dollars) a set of tools will cost |
generate_minimal_schema |
Creates the smallest possible version of a tool schema |
Quick Start
# Install
pip install mcp
# Run (stdio)
python -m src.server
# Or with mcpize (when available)
mcpize run .
Environment
Copy .env.example → .env if you want optional tiktoken for exact counts.
Why This Helps Entrepreneurs
- Save real money on every AI call
- Make your AI products more reliable (agents stop picking wrong tools)
- Ship faster because debugging “why did the agent fail?” becomes easier
License
MIT – build cool stuff with it.
Built as part of the Daily AI Project series for Prevalid.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
Neon Database
MCP server for interacting with Neon Management API and databases
E2B
Using MCP to run code via e2b.
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.