PDF Vector for AI agents

PDF Vector parses documents into markdown, extracts structured data, and searches academic publications and grants. Researchers and developers use it to work with papers and technical documents. Connect it once through Arc0, and your agent, or Claude, ChatGPT and Cursor, can use it through one MCP endpoint, limited to what each user approved.

Connect PDF Vector See the 10 actions ↓

DocumentsAPI keyMCP + RESTpdfvector.com

AUDIT LOG · PDF VECTORPOLICY: acme-support

09:41:07 · claude · u_8f2read

pdf_vector.search_publications

Search Publications✓ allowed · 212ms

09:41:08 · claude · u_8f2read

pdf_vector.find_citations

Find Citations✓ allowed · 164ms

09:41:09 · claude · u_8f2write

pdf_vector.ask_document

Ask Document✓ approved · approved by user

EVERY PDF VECTOR CALL, ON THE RECORD

01 · USE CASES

What agents do in PDF Vector.

Parse an academic paper

Convert a research paper PDF into structured markdown with sections preserved.

Ask a question about a document

Query a parsed document directly for an answer instead of reading it manually.

Search research grants read-only

Look up available research grants matching a topic without submitting anything.

02 · ACTIONS

10 PDF Vector actions, graded by risk.

Every PDF Vector action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.

read

Look things up. Allowed by default.

pdf_vector.find_citations
Find Citations
pdf_vector.get_paper_graph
Get Paper Graph
pdf_vector.find_similar_papers
Find Similar Papers
pdf_vector.search_publications
Search Publications
pdf_vector.search_research_grants
Search Research Grants
pdf_vector.parse_document
Parse Document
pdf_vector.extract_document
Extract Document Data
pdf_vector.fetch_publications
Fetch Publications
pdf_vector.parse_academic_paper
Parse Academic Paper

write

Create and change things. Allow, or ask the user first.

pdf_vector.ask_document
Ask Document

destructive

Delete, cancel or archive. Ask first, or deny outright.

No destructive actions.

03 · HOW IT WORKS

PDF Vector in three steps.

01Your users connect PDF VectorThey add their PDF Vector api key on Arc0 Connect, under your brand. It goes straight into the vault.
02You set the rulesReads run, and writes like “ask Document” can wait for the user to approve.
03Any agent can actYour agent calls PDF Vector through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.

POLICY.TS

await arc0.policies.set('pdf_vector', {
  read: 'allow',
  write: 'ask',        // ask_document
  destructive: 'deny',  
})

# Claude Code: the same connection, one URL
$ claude mcp add --transport http arc0 \
    https://mcp.arc0.ai/u/u_8f2

04 · AUTH AND DATA

How PDF Vector connects.

Users add their PDF Vector api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.

The same PDF Vector connection serves your agent over MCP and your own backend over REST and the proxy, so a user connects once. How Arc0 handles credentials →

AUTH: API key
CREDENTIALS: Per-tenant encrypted vault
MODEL SEES: Results only, never credentials
AUDIT LOG: Every call, on every plan

05 · WORKS WITH

Use PDF Vector from any agent.

Claude

ChatGPT

Cursor

Codex

VS Code

OpenAI Agents SDK

Claude Agent SDK

Vercel AI SDK

Mastra

LangGraph

06 · RELATED

PDF Vector and Arc0, answered.

Q01

Can I use PDF Vector with Claude, ChatGPT or Cursor?

Yes. Connect PDF Vector to Arc0 once, then add your Arc0 MCP URL to Claude, ChatGPT, Cursor, Claude Code or any other remote-MCP client. Each assistant only gets the PDF Vector actions you allow.

Q02

How do users connect PDF Vector?

Users add their PDF Vector api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.

Q03

Which PDF Vector actions can my agent take?

10 in total: 9 read, 1 write and 0 destructive, such as “ask Document”. Your policies decide which of them each agent may call.

Q04

Can I make my agent read-only in PDF Vector?

Yes. Allow read actions and deny writes in the PDF Vector policy. Your agent can still look things up, and any write it attempts is blocked and logged.

Q05

Can my own backend call PDF Vector too?

Yes. The same PDF Vector connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.

Get started

Plug PDF Vector into your agent.

Your users connect PDF Vector once, under your brand. Your agent gets 10 actions behind your policies, with every call on the record.

Connect PDF Vector Browse all apps →

Free to build · MCP + REST · Audit log on every plan