Home / MCP registry index / ai.ravenmcp/raven-mcp
Raven
ai.ravenmcp/raven-mcp in the official MCP registry.
Endpoint https://mcp.ravenmcp.ai/api/mcp. Source: github.com/rhinocap/raven-mcp.
The registry describes it as: Design intelligence for coding agents: audits, design systems, and a taste profile agents consult.
We read its 45 tools on 2026-10-22. Nothing in them matched our tool-poisoning rules. It also sets server instructions, text a client puts in front of the model on connect; those were read too.
A clean read means these rules found nothing, not that the server is harmless. A server can change its tools at any time, which is why the index reads it again every week.
Tools it advertises
get_principles get_pattern get_business_strategy evaluate_design search_knowledge get_checklist get_d4d_framework list_design_systems get_design_system compose_system audit_page score_page audit_parity audit_ios_a11y audit_responsive_visibility audit_contrast suggest_contrast_fix audit_url audit_content audit_typography audit_tap_targets get_brand_system generate_design_system audit_layout audit_swiftui audit_screen audit_ios_screen audit_ios_privacy audit_rn list_content_systems get_content_system get_content_principles get_content_pattern get_research_method get_metrics_framework get_service_pattern get_service_standard generate_service_blueprint get_brand_principles get_brand_trends list_creative_models list_creative_presets score_creative audit_consistency audit_video_playback
Run this server? Show the check in your README
The badge reflects the latest weekly read: 
[](https://lazaretto.dev/mcp-registry/ai-ravenmcp-raven-mcp)How this was checked
Lazaretto connects to the endpoint the way any MCP client does, asks the server to introduce itself and list its tools, and reads every name, description, parameter schema and server instruction for tool poisoning: hidden directive blocks, orders to read local secrets, parameters built to carry secrets or the conversation out, orders that redirect another server's tools, and invisible characters. It never calls a tool. What we found across the registry.
To run the same check every time Claude Code adds a server, install the free lazaretto-guard plugin. Browse every server in the index.