Pinrag MCP Server

PinRAG is for when you want to learn about something and your materials are scattered—PDFs and ebooks, GitHub repos, YouTube videos, Discord discussions, and plain notes. You index those materials into one shared RAG index, then. The pinrag mcp server wraps that behind the Model Context Protocol, so an assistant can use it through 14 defined tools rather than through you.

What it actually does

• Multi-format indexing — — PDF (.pdf), local files or directories, plain text (.txt), Discord export (.txt), YouTube (video or playlist URL, or video ID), GitHub repo (URL), web documentation sites (URL)
• RAG with citations — — Answers cite source context: PDF page, YouTube timestamp, document name for plain text and Discord, chunk index for GitHub repos, source URL for web documentation
• Document tags — — Tag documents at index time (e.g. AMIGA, PI_PICO) for filtered search
• Metadata filtering — — query_tool supports document_id, tag, document_type, PDF page_min/page_max, and response_style (thorough or concise)
• MCP tools — — add_document_tool, query_tool, list_documents_tool, remove_document_tool, set_document_tag_tool, list_collections_tool; optional collection on tools overrides PINRAG_COLLECTION_NAME for that call
• MCP resources — — pinrag://documents (indexed documents) and pinrag://server-config (env vars and config); click in Cursor’s MCP panel to view

Adding it to your client

The server ships on PyPI as pinrag, so your MCP client can launch it on demand — there is no separate build step. Add the server block to your client's configuration, restart it, and the tools register themselves.

Its toolset

Everything the assistant can do here goes through one of these:

• Multi — format indexing** — PDF (.pdf), local files or directories, plain text (.txt), Discord export (.txt), YouTube (video or playlist URL, or video ID)
• Observability — MCP tool notifications (ctx.log) plus optional LangSmith tracing
• FlashRank — ** Install pinrag[rerank] in the same tool env (pipx install 'pinrag[rerank]' / uv tool install 'pinrag[rerank]'); tunables are in
• Action — Tool
• Variable — Default
• LLM — The LLM tool exposed by this server
• PINRAG_LLM_PROVIDER — openrouter
• PINRAG_LLM_MODEL — (provider default)
• OpenRouter — The OpenRouter tool exposed by this server
• PINRAG_OPENROUTER_MODEL_FALLBACKS — (unset)
• PINRAG_OPENROUTER_SORT — (unset)
• PINRAG_OPENROUTER_PROVIDER_ORDER — (unset)

Configuration

You will need 8 environment variables: OPENROUTER_API_KEY, PINRAG_PERSIST_DIR, GITHUB_TOKEN, PINRAG_WEB_RATE_LIMIT_PER_HOST, PINRAG_YT_PROXY_HTTP_URL, PINRAG_YT_PROXY_HTTPS_URL, OPENAI_API_KEY, ANTHROPIC_API_KEY. The server will not start without them, which is usually why the tools fail to appear on a first run. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.

Caveats

• It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
• With 14 tools registered it takes up a noticeable share of the context window; turn it off in projects that never touch Pinrag.
• Missing credentials fail quietly in some clients — if no tools show up, check the environment block first.
• MCP clients confirm each tool call by default. Leave that on until you have watched what the pinrag mcp server does with a few real requests.

When to reach for it

Among the AI and media services options, the useful question is rarely "what can it do" but "what does it cost you to run" — permissions, credentials, and how much of your context its toolset consumes. Pinrag's toolset — Multi, Observability, FlashRank and 11 more — is a fair guide to whether it matches your workflow. It is maintained by ndjordjevic; worth a glance at recent repository activity before you build anything load-bearing on it.

This entry was verified against Pinrag's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.