The MCP-server-ragdocs provides tools for retrieving and processing documentation through vector search, enabling AI assistants to augment their responses with relevant documentation context. Built with TypeScript, it supports both local (Ollama) and cloud-based (OpenAI) embeddings generation, integrates with Qdrant for vector storage, and includes tools for semantic document search, URL extraction, and queue management. This implementation is particularly valuable for workflows requiring context-aware AI responses backed by specific documentation sources.
Cognium trust score
50%
Tier
Unverified
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately.
Returns 7 tools: search_skills, get_skill, list_leaderboard, get_trust_breakdown, resolve_composition, plus the ChatGPT-connector search and fetch. Every tool is annotated read-only.
Resolve this skill directly via MCP tools/call get_skill.