https://github.com/vectifyai/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.
https://github.com/vectifyai/pageindex-mcp
Last synced: 10 days ago
JSON representation
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.
- Host: GitHub
- URL: https://github.com/vectifyai/pageindex-mcp
- Owner: VectifyAI
- License: mit
- Created: 2025-08-25T08:00:01.000Z (10 months ago)
- Default Branch: master
- Last Pushed: 2026-05-28T02:07:16.000Z (17 days ago)
- Last Synced: 2026-05-28T03:15:03.255Z (17 days ago)
- Language: TypeScript
- Homepage: https://pageindex.ai/mcp
- Size: 219 KB
- Stars: 347
- Watchers: 0
- Forks: 40
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- Changelog: CHANGELOG.md
- License: LICENSE
Awesome Lists containing this project
README
# PageIndex MCP
> If you find this repo useful, please also star our **[main PageIndex repo](https://github.com/VectifyAI/PageIndex)** ⭐
[](https://github.com/VectifyAI/PageIndex) [](https://pageindex.ai/mcp) [](https://vectify.ai/pageindex)
📘 [**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.
🔌 [**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.
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.
✨ Chat to long PDFs the **human-like, reasoning-based way** ✨
- Support local and online PDFs
- Free 1000 pages
- Unlimited conversations
For more information, visit the [PageIndex MCP](https://pageindex.ai/mcp) page.
💡 Looking for a fully hosted experience? Try [**PageIndex Chat**](https://chat.pageindex.ai) 🤖: a human-like document analyst that lets you chat with long PDFs using the same agentic, reasoning-based workflow as PageIndex MCP.
# What is PageIndex?
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:
- **Higher Accuracy**: Relevance beyond similarity
- **Better Transparency**: Clear reasoning trajectory with traceable search paths
- **Like A Human**: Retrieve information like a human expert navigates documents
- **No Vector DB**: No extra infrastructure overhead
- **No Chunking**: Preserve full document context and structure
- **No Top-K**: Retrieve all relevant passages automatically
---
# PageIndex MCP Setup
### For Developers
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.
1. Go to [PageIndex Dashboard](https://dash.pageindex.ai/api-keys) to create an API Key
2. Copy the generated key
3. Add to your MCP configuration:
```json
{
"mcpServers": {
"pageindex": {
"type": "http",
"url": "https://api.pageindex.ai/mcp",
"headers": {
"Authorization": "Bearer your_api_key"
}
}
}
}
```
For more details, visit the [PageIndex API Dashboard](https://dash.pageindex.ai).
### For PageIndex Chat Users
If you already have a [PageIndex Chat](https://chat.pageindex.ai) account, you can connect your MCP client directly via OAuth.
**Claude Desktop — One-Click Install:**
Download the `.mcpb` file from [Releases](https://github.com/VectifyAI/pageindex-mcp/releases) and double-click to install. OAuth authentication is handled automatically.
**Other MCP Clients:**
```json
{
"mcpServers": {
"pageindex": {
"type": "http",
"url": "https://chat.pageindex.ai/mcp"
}
}
}
```
**Local MCP Server (with local PDF upload):**
If you need to upload local PDF files, you can run the local MCP server (requires Node.js ≥18.0.0):
```json
{
"mcpServers": {
"pageindex": {
"command": "npx",
"args": ["-y", "@pageindex/mcp"]
}
}
}
```
For more details, visit [PageIndex Chat](https://chat.pageindex.ai).
# Related Links
[](https://vectify.ai/pageindex)
[](https://github.com/VectifyAI/PageIndex)
## License
This project is licensed under the terms of the MIT open source license. Please refer to [MIT](./LICENSE) for the full terms.