Deterministic SVG perception for LLM agents — measures, never guesses. MCP server.
Mirror renders SVG in a real browser and reports what is actually where — in grid cells and W3C color names, with prose and structured output — and it never guesses. Spatial layout constraints become unit tests. And every tool description is a claim the server proves about itself. Built for agents that can't afford to hallucinate coordinates. When an LLM agent edits an SVG, how does it know…
Verification confirms publisher identity (repo ownership), not code safety. The security scan covers known CVEs and suspicious install scripts — it cannot prove the absence of malicious code.
Mirror renders SVG in a real browser and reports what is actually where — in grid cells and W3C color names, with prose and structured output — and it never guesses. Spatial layout constraints become unit tests. And every tool description is a claim the server proves about itself. Built for agents that can't afford to hallucinate coordinates. When an LLM agent edits an SVG, how does it know whether the change worked? Today it either guesses from the source text (and hallucinates positions,…