Skip to content
Back to search

pageindex-mcp

MCP server for PageIndex. PageIndex is a vectorless reasoning-based RAG system which uses multi-step reasoning and tree search to retrieve information like a human expert would.

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/vectifyai--pageindex-mcp/badge.svg)](/listings/vectifyai--pageindex-mcp)

HTML

<a href="/listings/vectifyai--pageindex-mcp"><img src="/api/listings/vectifyai--pageindex-mcp/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md · README · 125 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. <div align="center">
  2. <a href="https://pageindex.ai/mcp">
  3. <img src="https://docs.pageindex.ai/images/general/mcp_banner.jpg">
  4. </a>
  5. </div>
  6. # PageIndex MCP
  7. > If you find this repo useful, please also star our **[main PageIndex repo](https://github.com/VectifyAI/PageIndex)** ⭐
  8. [![PageIndex GitHub](https://img.shields.io/badge/PageIndex_GitHub-000000?style=for-the-badge&logo=github&logoColor=white)](https://github.com/VectifyAI/PageIndex)&nbsp;&nbsp;[![PageIndex MCP Home](https://img.shields.io/badge/PageIndex_MCP-4280d3?style=for-the-badge&logo=readthedocs&logoColor=white)](https://pageindex.ai/mcp)&nbsp;&nbsp;[![PageIndex Home](https://img.shields.io/badge/PageIndex-3B82F6?style=for-the-badge&logo=homeadvisor&logoColor=white)](https://vectify.ai/pageindex)
  9. 📘 [**PageIndex**](https://github.com/VectifyAI/PageIndex) is a vectorless, reasoning-based RAG system that represents documents as hierarchical **tree structures**. It enables LLMs to navigate and retrieve information through structure and **reasoning**, not vector similarity — much like a human would retrieve information using a book's index.
  10. 🔌 [**PageIndex MCP**](https://pageindex.ai/mcp) exposes this **LLM-native, in-context tree index** directly to LLMs via MCP, allowing platforms like **Claude**, **Cursor**, and other MCP-compatible agents or LLMs to reason over document structure and retrieve the right information — without vector databases.
  11. Want to chat with long PDFs but hit context limit reached errors? Add your file to PageIndex to seamlessly chat with long PDFs on any agent/LLM platforms.
  12. ✨ Chat to long PDFs the **human-like, reasoning-based way** ✨
  13. - Support local and online PDFs
  14. - Free 1000 pages
  15. - Unlimited conversations
  16. For more information, visit the [PageIndex MCP](https://pageindex.ai/mcp) page.
  17. 💡 Looking for a fully hosted experience? Try [**PageIndex App**](https://app.pageindex.ai) 🤖: a human-like document analyst that lets you chat with long PDFs using the same agentic, reasoning-based workflow as PageIndex MCP.
  18. <p align="center">
  19. <a href="https://pageindex.ai/mcp">
  20. <img src="https://github.com/user-attachments/assets/d807d506-131d-4c7b-837c-96ab1adb2271">
  21. </a>
  22. </p>
  23. # What is PageIndex?
  24. <div align="center">
  25. <a href="https://pageindex.ai/mcp">
  26. <img src="https://docs.pageindex.ai/images/cookbook/vectorless-rag.png" width="70%">
  27. </a>
  28. </div>
  29. PageIndex is a vectorless, **reasoning-based RAG** system that generates hierarchical **tree structures** of documents and uses multi-step **reasoning** and tree search to retrieve information like a human expert would. It has the following key properties:
  30. - **Higher Accuracy**: Relevance beyond similarity
  31. - **Better Transparency**: Clear reasoning trajectory with traceable search paths
  32. - **Like A Human**: Retrieve information like a human expert navigates documents
  33. - **No Vector DB**: No extra infrastructure overhead
  34. - **No Chunking**: Preserve full document context and structure
  35. - **No Top-K**: Retrieve all relevant passages automatically
  36. ---
  37. # PageIndex MCP Setup
  38. ### For Developers
  39. Connect PageIndex to your agent framework or AI SDK via MCP. Works with [Claude Agent SDK](https://github.com/anthropics/claude-agent-sdk-python), [Vercel AI SDK](https://ai-sdk.dev/docs/ai-sdk-core/mcp-tools), [OpenAI Agents SDK](https://openai.github.io/openai-agents-python/mcp/), [LangChain](https://github.com/langchain-ai/langchain-mcp-adapters), and any MCP-compatible client. Simple API Key authentication — no OAuth flow required.
  40. 1. Go to [PageIndex Dashboard](https://developer.pageindex.ai/api-keys) to create an API Key
  41. 2. Copy the generated key
  42. 3. Add to your MCP configuration:
  43. ```json
  44. {
  45. "mcpServers": {
  46. "pageindex": {
  47. "type": "http",
  48. "url": "https://api.pageindex.ai/mcp",
  49. "headers": {
  50. "Authorization": "Bearer your_api_key"
  51. }
  52. }
  53. }
  54. }
  55. ```
  56. For more details, visit the [PageIndex API Dashboard](https://developer.pageindex.ai).
  57. ### For PageIndex App Users
  58. If you already have a [PageIndex App](https://app.pageindex.ai) account, you can connect your MCP client directly via OAuth.
  59. **Claude Desktop — One-Click Install:**
  60. Download the `.mcpb` file from [Releases](https://github.com/VectifyAI/pageindex-mcp/releases) and double-click to install. OAuth authentication is handled automatically.
  61. **Other MCP Clients:**
  62. ```json
  63. {
  64. "mcpServers": {
  65. "pageindex": {
  66. "type": "http",
  67. "url": "https://app.pageindex.ai/mcp"
  68. }
  69. }
  70. }
  71. ```
  72. **Local MCP Server (with local PDF upload):**
  73. If you need to upload local PDF files, you can run the local MCP server (requires Node.js ≥18.0.0):
  74. ```json
  75. {
  76. "mcpServers": {
  77. "pageindex": {
  78. "command": "npx",
  79. "args": ["-y", "@pageindex/mcp"]
  80. }
  81. }
  82. }
  83. ```
  84. For more details, visit [PageIndex App](https://app.pageindex.ai).
  85. # Related Links
  86. [![PageIndex Home](https://img.shields.io/badge/PageIndex_Home-3B82F6?style=for-the-badge&logo=homeadvisor&logoColor=white)](https://vectify.ai/pageindex)&nbsp;&nbsp;
  87. [![PageIndex GitHub](https://img.shields.io/badge/PageIndex_GitHub-000000?style=for-the-badge&logo=github&logoColor=white)](https://github.com/VectifyAI/PageIndex)
  88. ## License
  89. This project is licensed under the terms of the MIT open source license. Please refer to [MIT](./LICENSE) for the full terms.

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.