Development
PageIndex MCP
by io.github.VectifyAI · v1.8.1
Reasoning-based RAG system for chatting with long PDFs. Supports local and online files.
- GitHub stars
- 365
- Transport
- stdio (local process)
- Auth
- None required
- Test status
- untested
Install & run
Run the server locally with the package command below.
terminal
$npx -y @pageindex/mcpnpm
@pageindex/mcp· stdiomcpb
https://github.com/VectifyAI/pageindex-mcp/releases/download/v1.8.1/pageindex-mcp-1.8.1.mcpb· stdioConnect this MCP server to your AI agent
MCP servers plug into any MCP-compatible client (Claude Desktop, Cursor, your own agent runtime, and more). The steps are the same everywhere:
- 1. Make sure the runtime is available. This server runs as a local process, so its package runner (e.g. npx / uvx / docker) must be installed on the machine running your agent.
- 2. Add it to your MCP client config. Point your client at the command above. Most clients accept an MCP servers map keyed by a name of your choosing.
- 3. No credentials needed. This server declares no required secrets — it should work out of the box.
- 4. Restart your client and verify.The server’s tools should appear in your agent’s tool list, ready to call.
Want this running without wiring configs yourself? Run this with Alfe →
Developmentnpmmcpb
Data from the official MCP registry · last updated 2026-05-28 · ★ 365 stars via GitHub.