io.github.VectifyAI/pageindex-mcp

PageIndex MCP

Is the PageIndex MCP server down? No. It is up and needs network, probed 2026-11-03.

Reasoning-based RAG system for chatting with long PDFs. Supports local and online files.

needs network probed 2026-11-14 · unchanged since 2026-11-03

MCP error -32603: fetch failed
No existing OAuth tokens found, starting fresh authentication.
Failed to initialize remote connection: TypeError: fetch failed

Run it: npx -y @pageindex/mcp@1.9.0 (stdio, probed in a container with the network off)
Host: npmjs.com
Reports itself as: pageindex-mcp 1.9.0
Capabilities: resources, tools
Repository: https://github.com/VectifyAI/pageindex-mcp
Registry: active, updated 2026-11-03 · registry entry
Changes: 2 recorded, reachable in 0 of them. A row is added when the result, the tool count or the cost changes.

Compare this server with others.

More servers

Other registry entries on npmjs.com, the ones next to this name; all of them.

Nanostores MCP io.github.Valyay/nanostores-mcp · alive
io.github.VanguardiaAI/doktor · alive
ArcSync io.github.VanLandinghamLabs/arcsync-mcp · alive
io.github.Varshavia/repomagpie · alive
VideoVector MCP Server io.github.VectorMethods/videovector-mcp-server · needs env
Vectreal io.github.Vectreal/vectreal · alive
io.github.Vedant2254/aishelf-mcp-server · alive
PDF Accessibility Audit io.github.Veduis/pdf-a11y-audit · alive

Servers that mention reasoning or chatting.

Hostlo ai.hostlo/hostlo · needs auth
PartForge ai.partforge/partforge · needs auth
AskLoop app.askloop/askloop · no DNS
app.causely/causely · needs auth
den — Korean AEC knowledge, curated archi.den/den_archi_mcp · alive
AI Reasoning Commons com.aineedhelpfromotherai/reasoning-commons · not found
Handled Locator com.handledlocal/locator · needs auth
LandingConnect com.landingconnect/landingconnect · not found

History

We add a row when the result changes. A server with no change keeps its last row.

Probed	Result	Init	Tools	Claude	o200k
2026-11-01 08:20	needs network	131 ms
2026-10-18 06:43	crashed on start	223 ms

Badge for the README

The result of the latest probe, the tool count and the token cost. The feed has an entry for every probe that changed them.

Atom feed

A mail when this server changes

Stops answering, comes back, tool set or cost changes. One confirmation mail first, a stop link in every mail.

For the publisher

The server tries to reach the network on start. The probe runs in a container with the network off, so a server that connects lazily, on the first tool call, is measured.