PDF Vector MCP server for AI agents and assistants

Securely connect your AI agents and chatbots (Claude, ChatGPT, Cursor, etc) with PDF Vector MCP or direct API to parse PDFs into markdown, extract structured data, answer document questions, and search academic publications and grants through natural language.

PDF Vector logoPDF Vector
Api Key

PDF Vector is a document parsing and vector-search service that converts PDFs into markdown and structured data. Use it to quickly find, extract, and index details from academic papers and grant documents.

10 Tools

Try PDF Vector now

Type what you want done — sign in and watch it run live in the Tool Router playground.

TOOL ROUTER PLAYGROUND
PDF Vector
Try asking
TOOLS

Supported Tools

Every PDF Vector action and event your agent gets out of the box.

Ask Document

Answer one question from a general, identity, invoice, or bank-statement document.

Extract Document Data

Extract schema-constrained structured data from a general, identity, invoice, or bank-statement document.

Fetch Publications

Resolve up to 100 publication identifiers with provider auto-detection and return both resolved records and per-identifier errors.

Find Citations

Find relevant academic citations for each sentence in a paragraph and preserve provider-specific partial errors.

Find Similar Papers

Find papers related to a seed publication using citation-network similarity, optionally including relationship edges.

Get Paper Graph

Retrieve a publication plus one independently offset-controlled page of citing papers and one page of referenced papers.

Parse Academic Paper

Resolve an academic identifier or provider URL to a public PDF and parse it to markdown.

Parse Document

Convert a general, identity, invoice, or bank-statement document to markdown; specialized documents require the auto, pro, or max model.

Search Publications

Search academic publications across selected databases and return one offset-controlled page, including any provider-specific partial errors.

Search Research Grants

Search US, EU, and UK research-grant providers and return one explicit offset-controlled page with partial provider errors.

SETUP GUIDE

Connect PDF Vector MCP Tool with your Agent

1

Install Composio

typescript
npm install @composio/core ai @ai-sdk/mcp @ai-sdk/openai
Install the Composio SDK and your agent framework
2

Create a session with MCP enabled

typescript
import { Composio } from "@composio/core";

const composio = new Composio();
const { mcp } = await composio.create("your-user-id", {
  toolkits: ["pdf_vector"],
  mcp: true,
});
Create a session scoped to PDF Vector and read its MCP URL and headers
3

Connect your agent to the MCP server

typescript
import { createMCPClient } from "@ai-sdk/mcp";
import { openai } from "@ai-sdk/openai";
import { generateText, stepCountIs } from "ai";

const client = await createMCPClient({
  transport: { type: "http", url: mcp.url, headers: mcp.headers },
});

const { text } = await generateText({
  model: openai("gpt-5.6-sol"),
  tools: await client.tools(),
  prompt: "Summarize key findings from research paper",
  stopWhen: stepCountIs(10),
});

console.log(text);
await client.close();
Pass the session's MCP URL and headers to your agent and run a PDF Vector request
SETUP GUIDE

Connect PDF Vector API Tool with your Agent

1

Install Composio

typescript
npm install @composio/core @composio/openai openai
Install the Composio SDK, the OpenAI provider, and the OpenAI SDK
2

Create a Composio session

typescript
import OpenAI from "openai";
import { Composio } from "@composio/core";
import { OpenAIResponsesProvider } from "@composio/openai";

const composio = new Composio({ provider: new OpenAIResponsesProvider() });
const client = new OpenAI();

const session = await composio.create("your-user-id", { toolkits: ["pdf_vector"] });
const tools = await session.tools();
Initialize Composio with the OpenAI Responses provider and create a session scoped to PDF Vector
3

Run PDF Vector tools with your agent

typescript
let response = await client.responses.create({
  model: "gpt-5.6-sol",
  tools,
  input: [{ role: "user", content: "Summarize key findings from research paper" }],
});

while (response.output.some((o) => o.type === "function_call")) {
  const outputs = await composio.provider.handleToolCalls(session, response.output);
  response = await client.responses.create({
    model: "gpt-5.6-sol",
    tools,
    previous_response_id: response.id,
    input: outputs,
  });
}

console.log(response.output_text);
Send a request, execute the PDF Vector tool calls through the session, and print the final answer

Why Use Composio?

AI Native PDF Vector Integration

  • Supports both PDF Vector MCP and direct API based integrations
  • Structured, LLM-friendly schemas for reliable tool execution
  • Rich coverage for reading, writing, and querying your PDF Vector data

Managed Auth

  • Built-in API key handling with secure storage
  • Central place to manage, scope, and revoke PDF Vector access
  • Per user and per environment credentials instead of hard-coded keys

Agent Optimized Design

  • Tools are tuned using real error and success rates to improve reliability over time
  • Comprehensive execution logs so you always know what ran, when, and on whose behalf

Enterprise Grade Security

  • Fine-grained RBAC so you control which agents and users can access PDF Vector
  • Scoped, least privilege access to PDF Vector resources
  • Full audit trail of agent actions to support review and compliance

Rolling this out across your team?

Give your team centralized access control across every framework with Composio’s MCP Gateway.

EXPLORE MCP GATEWAY
FAQ

Frequently asked questions

Start with PDF Vector.It takes 30 seconds.

Managed auth, hosted MCP servers, and every PDF Vector tool your agent needs.Free to start.

Start building