An MCP server that verifies whether a claim is actually supported by the source text at a given citation — independent of what the calling LLM asserts.
A local RAG context optimizer MCP server that filters retrieved context to the minimum an LLM needs to answer correctly, using a cross-encoder and optional calibration.
MCP server for grounded agentic Q&A over customer feedback, exposing typed tools to query a feedback corpus and return answers with citations to specific record IDs or a refusal when unsupported.
Provides a local MCP server for Claude Code to retrieve relevant documentation slices from a repository's auto-generated reference docs using hybrid search (vector + BM25).