Find tools by intent, not memory.
Semantic search for MCP tools. Load 3 relevant tools instead of 77 — 95% fewer tokens, ~15ms latency, ~95% accuracy.
Setup
ollama pull nomic-embed-text
pip install -r requirements.txt
python gateway.py --sync
compass()
compass(
intent="generate an AI image",
top_k=3
)
Result
# comfy:comfy_generate 0.91
# tokens_saved: 20,500
# total_indexed: 44
Features
Stop loading all 77 tools into context. Find the right one.
Semantic Discovery
compass(intent) finds tools by meaning. Describe what you want to do — get the right tool, not a list of all of them.
95% Token Savings
38,500 tokens → 2,000 per request. HNSW vector index, nomic-embed-text, ~15ms query latency, ~95% accuracy@3.
Progressive Disclosure
compass() → describe() → execute(). Load only the schema you need, only when you actually need it.
Quick Start
Install & Index
# Prerequisites: Ollama running locally
ollama pull nomic-embed-text
# Clone and install
git clone https://github.com/mcp-tool-shop-org/tool-compass
cd tool-compass
pip install -r requirements.txt
# Build the search index
python gateway.py --sync
# Start the MCP gateway
python gateway.pyQuery by Intent
compass(
intent="I need to generate an AI image from a text description",
top_k=3,
min_confidence=0.3
)
# Returns:
# {
# "matches": [{
# "tool": "comfy:comfy_generate",
# "confidence": 0.912
# }],
# "tokens_saved": 20500
# }Gateway Tools
Nine tools — one semantic entry point for your entire MCP ecosystem.