{"id":"paperqa-mcp-server","name":"paperqa-mcp-server","af_score":66.2,"security_score":59.2,"reliability_score":31.2,"what_it_does":"Provides an MCP server that wraps PaperQA2 to index a local PDF library and answer questions by reading/searching/synthesizing across those papers. Indexing uses OpenAI embeddings and (optionally) other LLMs configured via environment variables; the tool is intended for use inside Claude Desktop via MCP.","best_when":"You have a stable local PDF library (e.g., Zotero storage), can run/refresh the index periodically, and are comfortable sending extracted text/chunks to external model providers for embeddings and synthesis.","avoid_when":"You cannot provide OpenAI credentials, cannot run a local indexing step, or require strict on-prem data residency where OpenAI calls are not allowed.","last_evaluated":"2026-04-04T21:49:17.603291+00:00","has_mcp":true,"has_api":false,"auth_methods":["API key via OPENAI_API_KEY (also supports ANTHROPIC_API_KEY)"],"has_free_tier":false,"known_gotchas":["Claude Desktop has a short startup timeout; initial dependency downloads can cause 'server disconnected'—pre-warm by running uvx paperqa-mcp-server once.","If too many PDFs are unindexed, the server refuses to answer and instructs running the index command first.","Claude Desktop config JSON must be valid; missing commas can prevent the MCP server from loading.","The index hash is sensitive to settings; building the index with the server's own index command is required to ensure the server finds it.","Indexing may hit external rate limits; the documented recovery is to re-run the same index command."],"error_quality":null}