Pinrag logo

Pinrag

by ndjordjevic

Indexes scattered source material and answers questions with citations from PDFs, videos, repositories, exports, and notes.

Install Pinrag

Pick your client, then add it in one click or paste the config.

STDIOPython
~/Library/Application Support/Claude/claude_desktop_config.json
claude_desktop_config.json
{
  "mcpServers": {
    "ndjordjevic-pinrag": {
      "command": "uvx",
      "args": [
        "--refresh",
        "pinrag"
      ],
      "env": {
        "OPENROUTER_API_KEY": "YOUR_VALUE_HERE",
        "PINRAG_PERSIST_DIR": "YOUR_VALUE_HERE"
      }
    }
  }
}

Settings → Developer → Edit Config, merge this into mcpServers, then fully quit and reopen Claude Desktop.

Values are written into the snippet above so you can paste it as is. They never leave your browser.

We couldn’t confirm it starts correctly

The install command didn't complete successfully in our automated test.

uvx --refresh pinrag

Downloading cpython-3.12.14-linux-x86_64-gnu (download) (32.7MiB) Downloaded cpython-3.12.14-linux-x86_64-gnu (download) Downloading uvloop (4.2MiB) Downloading hf-xet (4.3MiB) Downloading pygments (1.2MiB) Downloading tokenizers (3.2MiB) Downloading grpcio (6.8MiB) Downloading onnxruntime (22.5MiB) Downloading anthropic (1.3MiB) Downloading pyarrow (47.8MiB) Downloading pydantic-core (2.0MiB) Downloading zstandard (5.3MiB) Downloading sqlalchemy (4.5MiB) Downloading openai (2.0MiB) Downloading

This is an experimental automated check and can have false negatives — missing environment variables, a slow cold install, etc. It doesn’t necessarily mean something’s wrong. Last checked 1mo ago.

Overview

ndjordjevic/pinrag MCP server indexes PDFs, text files, YouTube content, GitHub repositories, Discord exports, and documentation sites into a shared RAG index. It exposes MCP tools for adding, querying, listing, tagging, and removing documents, with citations tied to pages, timestamps, files, threads, URLs, or repository chunks. Local Nomic embeddings work without an embedding API key, while OpenRouter is the default LLM provider and OpenAI, Anthropic, and Cerebras are also supported. Reach for it when an assistant needs to answer questions across scattered reference material from Cursor, VS Code, or another MCP-capable client.

Use cases

  • Index technical PDFs and query them with page citations
  • Search a GitHub repository by indexing its source files
  • Summarize YouTube videos with timestamp citations
  • Filter research documents by tags or document type

Key features

  • Indexes PDFs, text, Discord exports, YouTube, GitHub, and documentation sites
  • Returns citations for retrieved source context
  • Supports document tags and metadata filters
  • Uses local Nomic embeddings by default
  • Offers optional YouTube vision enrichment
  • Exposes MCP tools, resources, and a prompt

Security & health

What it can reach and how reliably it runs — from our own checks, not the maintainer’s claims.

ActiveLast checked 2d ago

Recent health check succeeded.

21/21 checks healthy over the last 90d

Supply-chain signal

No high-severity advisories surfaced by our automated scan.

Critical 0High 0Medium 0Low 0

Scanned 5d ago via OSV.dev · pinrag (PyPI)

Adoption & maintenance

Factual signals from GitHub, npm, and our automated checks — not a rating.

GitHub stars2Stargazers on the source repository.
Last commit7mo agoMost recent push to the default branch.
Install checkInconclusiveInstall command did not finish in our automated test.
Directory activity3 viewsConfig copies, upvotes, and views on AllMCPs.

How Pinrag works

What ndjordjevic/pinrag MCP server does

ndjordjevic/pinrag MCP server builds a shared retrieval index from mixed research and development sources. Supported inputs include PDF files, ebooks, plain text files, local directories, DiscordChatExporter text files, YouTube videos or playlists, GitHub repository URLs, and web documentation sites. An assistant can then query the indexed material in natural language rather than searching each source separately.

The returned answers include source-oriented citations. Depending on the input, citations can identify a PDF page, a YouTube timestamp, a text or Discord document name, a GitHub chunk index, or a documentation URL. Documents can receive tags during indexing, allowing queries to narrow results to a subject or collection of materials.

How it works

The server uses LangChain-based retrieval with Chroma storage and exposes the workflow through MCP. Documents are added with add_document_tool, searched with query_tool, inspected with list_documents_tool, and deleted with remove_document_tool. Additional tools manage document tags and collections. The use_pinrag MCP prompt can guide an assistant through querying, indexing, listing, or removing documents.

Retrieval supports structure-aware chunking by default. Optional features include FlashRank re-ranking, multi-query expansion, and parent-child chunks for PDFs. YouTube vision enrichment can combine transcript content with on-screen code, diagrams, labels, and interface text. OpenAI and Anthropic vision modes use scene keyframes and require the optional vision dependencies and ffmpeg; OpenRouter native video mode avoids local video download and ffmpeg.

Queries can filter by document ID, tag, document type, and PDF page range. The response style can be set to thorough or concise. Local Nomic embeddings are used by default, with model weights downloaded and cached on first use. The LLM provider and model are configurable through environment variables.

Setup and configuration

Install uv, ensure uvx is available on the PATH, and configure the server in the MCP client’s environment block. The standard editor command uses uvx with the pinrag package. Set OPENROUTER_API_KEY when using the default OpenRouter provider and choose an absolute PINRAG_PERSIST_DIR for stored index data. The server does not load .env files when launched by an editor.

Cursor configuration uses an mcpServers object. VS Code GitHub Copilot configuration uses a top-level servers object. The ndjordjevic/pinrag MCP server also offers a streamable HTTP mode through pinrag server, with the MCP endpoint available at the configured host and port.

GitHub indexing accepts repository URLs and optional branch, inclusion, and exclusion patterns. GITHUB_TOKEN can provide access to private repositories or reduce rate-limit issues; PinRAG does not provide OAuth. Large GitHub files above the configured size limit are skipped.

Tools and capabilities

  • Index local files, directories, PDFs, URLs, videos, playlists, repositories, and documentation sites.
  • Query indexed content with metadata and page-range filters.
  • List indexed documents, chunk counts, metadata, and optional tag-filtered results.
  • Remove documents using their exact indexed document IDs.
  • Set document tags and list available collections.
  • Read pinrag://documents and pinrag://server-config MCP resources.
  • Optionally trace activity with LangSmith and receive MCP tool log notifications.

The ndjordjevic/pinrag MCP server is suited to the 🔎 end to end RAG platforms category because ingestion, persistent indexing, retrieval, filtering, and citation display are handled through one MCP-based workflow.

Reviews

No reviews yet — be the first to share how it worked for you.

Frequently Asked Questions about Pinrag

Install uv, ensure uvx is on your PATH, and add a PinRAG MCP entry that runs uvx with the pinrag package.

Yes. The README provides a Cursor configuration using the mcpServers object and the uvx command.

It supports PDFs, plain text and Discord export files, local directories, YouTube videos or playlists, GitHub repository URLs, and web documentation sites.

Yes. Citations can point to PDF pages, YouTube timestamps, document names, GitHub chunk indexes, or documentation source URLs.

No. Local Nomic embeddings are the default and require no API key, although the first run downloads approximately 270 MB of model weights.

Related MCP servers

Add a badge to your READMEShow it’s listed — live SVG, Markdown or HTML.

AllMCPs Directory Badge

Full Badge Customizer

Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.

Badge Style:
Live Dynamic SVG PreviewPinrag AllMCPs Directory Badge
Markdown (GitHub README)
[![AllMCPs](https://allmcps.com/api/badge/ndjordjevic-pinrag?style=directory)](https://allmcps.com/mcp/ndjordjevic-pinrag)
HTML Embed
<a href="https://allmcps.com/mcp/ndjordjevic-pinrag"><img src="https://allmcps.com/api/badge/ndjordjevic-pinrag?style=directory" alt="Pinrag on AllMCPs" /></a>