RAG and semantic search via OpenViking Context Database MCP server. Query documents, search knowledge base, add files/URLs to vector memory. Use for document Q&A, knowledge management, AI agent memory, file search, semantic retrieval. Triggers on "openviking", "search documents", "semantic search", "knowledge base", "vector database", "RAG", "query pdf", "document query", "add resource".
Security Analysis
medium confidenceOpenViking appears to be a legitimate RAG/MCP setup, but it can persistently index user files or directories into agent memory and installs unpinned external code, so users should review its scope before installing.
The RAG and semantic-search purpose is coherent, but the advertised add_resource tool can add files, directories, and URLs into vector memory without documented path limits or exclusions.
The instructions are user-directed, but they do not define confirmation requirements, retention/deletion controls, path allowlists, or safety boundaries for adding local directories to the knowledge base.
The one-time setup script clones an external GitHub repository and runs uv sync. This is purpose-aligned, but the cloned source and dependency set are not pinned in the provided artifacts.
Volcengine/Ark API keys and a local MCP server are expected for embeddings and LLM answers, but the registry metadata declares no credentials or capability tags, so users may not see those requirements upfront.
The skill creates a persistent vector database/data directory for agent memory, and the artifacts do not describe retention, isolation, or cleanup behavior.
Guidance
Install only if you want an agent connected to a local OpenViking MCP knowledge base. Review or pin the cloned repository, use dedicated provider API keys, keep the server bound to localhost, and add only narrowly scoped documents you are comfortable storing in persistent vector memory.
Latest Release
v1.0.3
RAG and semantic search via OpenViking Context Database MCP server
Popular Skills
Published by @zaynjarvis on ClawHub
