1
Add it to Claude Code
claude mcp add -e "INFERENCE_KEY=${INFERENCE_KEY}" -e "INFERENCE_URL=${INFERENCE_URL}" mcp-tool-search -- python main.pyRequired:
INFERENCE_KEYINFERENCE_URL2
Make your agent remember this setup
mcp-tool-search's config, env vars, and the gotchas you hit — recalled in every future Claude Code, Cursor, and Codex session.
npx conare@latestFree · one command · indexes the sessions already on disk. Set up in the browser instead →
What it does
- Dynamic tool discovery to prevent context bloat
- Supports over 10,000 tools with minimal overhead
- Three search methods: BM25, Semantic, and Regex
- REST API for registering, listing, and removing tools
Tools 4
tool_search_bm25Find tools by keyword matching.tool_search_semanticFind tools by meaning-based search.tool_search_regexFind tools by pattern matching.list_all_toolsList all registered tools.Environment Variables
INFERENCE_KEYrequiredAPI key for inference model authenticationINFERENCE_URLrequiredBase URL for the inference serviceTry it
→Search for tools related to weather forecasting.
→Find all tools that match the pattern get_.*
→I need a tool to send messages, can you find one?
→List all tools currently registered in the catalog.
Original README from dsouza-anush/mcp-tool-search
MCP Tool Search Server
The Problem: When you give Claude 50+ tools, two things break:
- Context bloat - Tool definitions eat 10-20K tokens, leaving less room for actual work
- Selection accuracy - Claude gets confused and picks wrong tools when there are too many
The Solution: Instead of loading all tools upfront, Claude searches for tools and loads only what it needs.
Without Tool Search: With Tool Search:
┌─────────────────────┐ ┌─────────────────────┐
│ Load 100 tools │ │ Load 1 search tool │
│ (20K tokens) │ │ (200 tokens) │
│ │ │ │
│ Claude picks wrong │ │ Claude searches: │
│ tool 30% of time │ │ "weather" → 2 tools │
│ │ │ │
│ Context nearly full │ │ 95% context free │
└─────────────────────┘ └─────────────────────┘
How It Works
- You register your tools with this server (via REST API)
- Claude gets access to search tools (
tool_search_bm25,tool_search_semantic,tool_search_regex) - When Claude needs a tool, it searches → gets back tool names → uses them
Three search methods:
- BM25 - Keyword matching ("weather" finds
get_weather,get_forecast) - Semantic - Meaning-based ("send a message" finds
send_email) - Regex - Pattern matching (
get_.*finds all getter tools)
Deploy to Heroku
Or manually:
heroku create my-tool-search
heroku buildpacks:set heroku/python
git push heroku main
heroku ai:models:create claude-4-sonnet --as INFERENCE
Register Your Tools
curl -X POST https://your-app.herokuapp.com/tools \
-H "Content-Type: application/json" \
-d '{
"name": "get_weather",
"description": "Get current weather for a location",
"input_schema": {
"type": "object",
"properties": {"location": {"type": "string"}},
"required": ["location"]
}
}'
Test It
export INFERENCE_KEY=$(heroku config:get INFERENCE_KEY -a my-tool-search)
export INFERENCE_URL=$(heroku config:get INFERENCE_URL -a my-tool-search)
curl -s "$INFERENCE_URL/v1/agents/heroku" \
-H "Authorization: Bearer $INFERENCE_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "claude-4-sonnet",
"messages": [{"role": "user", "content": "Find tools for checking weather"}],
"tools": [{"type": "mcp", "name": "mcp-tool-search/tool_search_semantic"}]
}'
API Reference
| Endpoint | Description |
|---|---|
POST /tools |
Register a tool |
GET /tools |
List all tools |
DELETE /tools/{name} |
Remove a tool |
GET /health |
Health check |
MCP Tools
| Tool | Use Case |
|---|---|
tool_search_bm25 |
Find tools by keywords |
tool_search_semantic |
Find tools by meaning |
tool_search_regex |
Find tools by pattern |
list_all_tools |
List all registered tools |