ISeeMP (I See Model Paths) builds a deterministic graph of source-to-context-to-sink capability paths across agent and MCP toolchains.
What it does
- Classifies tool capabilities with rule-based analysis
- Generates path graphs without requiring an LLM in the loop
- Flags high-risk combinations, including lethal-trifecta conditions
Why it matters
Most teams know which tools exist, but not how they compose into abuse paths. ISeeMP makes those paths explicit so controls can be applied where they matter.