Bring Pdf Manipulation
to LlamaIndex
Learn how to connect PDF.co to LlamaIndex and start using 12 AI agent tools in minutes. Fully managed, enterprise secure, and ready to use without writing a single line of code.
What is the PDF.co MCP Server?
Connect your PDF.co account to any AI agent and take full control of your document orchestration and data extraction through natural conversation. PDF.co provides a professional-grade suite of tools for PDF manipulation, allowing you to convert files to various formats, perform high-fidelity OCR on scanned images, and manage document security directly from your chat interface.
What you can do
- Document Conversion Orchestration — Convert PDFs and images to plain text, JSON, CSV, or XML programmatically to ensure your data pipelines are always synchronized.
- High-Fidelity OCR Intelligence — Perform high-resolution OCR on scanned documents and handwritten text directly from the AI interface to extract critical metadata.
- Data Extraction & Merging — Extract tables and metadata or merge multiple PDF files via natural language to maintain a high-fidelity document repository.
- Security & Protection Control — Add or remove password protection and manage PDF security settings using simple AI commands.
- Operational Monitoring — Track background job statuses and manage account balance to ensure your document production is always optimized.
How it works
1. Subscribe to this server
2. Enter your PDF.co API Key from your dashboard settings
3. Start managing your document processing from Claude, Cursor, or any MCP-compatible client
No more manual data entry from scanned invoices. Your AI acts as a dedicated document analyst or data processing coordinator.
Who is this for?
- Data Analysts & Accountants — quickly extract tabular data from PDF reports and monitor financial records without switching apps.
- Operations Managers — automate the merging and splitting of logistics documents via natural conversation.
- Developers — integrate real-time PDF conversion and OCR capabilities directly within the chat.
Built-in capabilities (12)
Check async job status
Extract PDF metadata with AI
co account and credit balance. Get account information
Merge multiple PDFs
Perform OCR on an image
Convert PDF tables to CSV
Convert PDF to structured JSON
Convert PDF to plain text
Convert PDF to XML
Add password to PDF
Split a PDF
Remove password from PDF
Why LlamaIndex?
LlamaIndex agents combine PDF.co tool responses with indexed documents for comprehensive, grounded answers. Connect 12 tools through Vinkius and query live data alongside vector stores and SQL databases in a single turn. ideal for hybrid search, data enrichment, and analytical workflows.
- —
Data-first architecture: LlamaIndex agents combine PDF.co tool responses with indexed documents for comprehensive, grounded answers
- —
Query pipeline framework lets you chain PDF.co tool calls with transformations, filters, and re-rankers in a typed pipeline
- —
Multi-source reasoning: agents can query PDF.co, a vector store, and a SQL database in a single turn and synthesize results
- —
Observability integrations show exactly what PDF.co tools were called, what data was returned, and how it influenced the final answer
PDF.co in LlamaIndex
PDF.co and 3,400+ other MCP servers. One platform. One governance layer.
Teams that connect PDF.co to LlamaIndex through Vinkius don't need to source, host, or maintain individual MCP servers. Every tool call runs inside a hardened runtime with credential isolation, DLP, and a signed audit chain.
Raw MCP | Vinkius | |
|---|---|---|
| Server catalog | Find and host yourself | 3,400+ managed |
| Infrastructure | Self-hosted | Sandboxed V8 isolates |
| Credential handling | Plaintext in config | Vault + runtime injection |
| Data loss prevention | None | Configurable DLP policies |
| Kill switch | None | Global instant shutdown |
| Financial circuit breakers | None | Per-server limits + alerts |
| Audit trail | None | Ed25519 signed logs |
| SIEM log streaming | None | Splunk, Datadog, Webhook |
| Honeytokens | None | Canary alerts on leak |
| Custom domains | Not applicable | DNS challenge verified |
| GDPR compliance | Manual effort | Automated purge + export |
Why teams choose Vinkius for PDF.co in LlamaIndex
The PDF.co MCP Server runs on Vinkius-managed infrastructure inside AWS — a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts. All 12 tools execute in hardened sandboxes optimized for native MCP execution.
Your AI agents in LlamaIndex only access the data you authorize, with DLP that blocks sensitive information from ever reaching the model, kill switch for instant shutdown, and up to 60% token savings. Enterprise-grade infrastructure, zero maintenance.
* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure
How Vinkius secures
PDF.co for LlamaIndex
Every tool call from LlamaIndex to the PDF.co MCP Server is protected by DLP redaction, cryptographic audit chains, V8 sandbox isolation, kill switch, and financial circuit breakers.
Frequently asked questions
Can my AI automatically find and extract a specific table from a PDF?
Yes! Use the convert_to_csv or convert_to_json tools. Your agent will respond with the structured tabular data from the document in seconds, ready for analysis.
How do I find my PDF.co API Key?
Log in to your PDF.co account, navigate to the main dashboard, and you will find your unique secret API key (starting with your email reference or key string) there.
Does this support handwritten text recognition?
Absolutely. PDF.co's high-fidelity OCR engine is designed to handle both printed and handwritten text with high accuracy across multiple languages.
How does LlamaIndex connect to MCP servers?
Use the MCP client adapter to create a connection. LlamaIndex discovers all tools and wraps them as query engine tools compatible with any LlamaIndex agent.
Can I combine MCP tools with vector stores?
Yes. LlamaIndex agents can query PDF.co tools and vector store indexes in the same turn, combining real-time and embedded data for grounded responses.
Does LlamaIndex support async MCP calls?
Yes. LlamaIndex's async agent framework supports concurrent MCP tool calls for high-throughput data processing pipelines.
BasicMCPClient not found
Install: pip install llama-index-tools-mcp