Integrations · MCP Server

pdfAssistant with Codex

Connect pdfAssistant to Codex CLI and integrate enterprise-grade PDF processing into your development and automation workflows. Map the server endpoint, authenticate via OAuth, and start processing documents from the command line.

View Paid Plans View Setup Guide

Paid plan required · Not available on the free tier

Setup Guide

Connect in Under 60 Seconds

Three steps from the command line to a fully connected PDF toolbox.

Prerequisite: The MCP server is available on pdfAssistant paid plans only — it is not included on the free tier. You'll need an active paid subscription to authenticate Codex and use the server. See paid plans →

Add the MCP Server

Run the following command in your terminal:

codex mcp add pdfAssistant --url https://chat.pdfassistant.ai/mcp

2
Authenticate
Log in via OAuth:
```
codex mcp login pdfAssistant
```
3
Start Processing
You're connected. Describe your document processing task and Codex calls pdfAssistant's tools automatically:
- “Convert all the Word files in this directory to PDF”
- “Batch compress every PDF in this folder to under 2MB”
- “Run OCR on this scanned document and extract the text”
- “Redact all email addresses from this file using regex”

Configuration & Code

Drop-in snippets for Codex.

Copy these into your config files or tool-call payloads.

Codex config (~/.codex/config.toml)TOML

Persistent server registration. Equivalent to running codex mcp add once.

[mcp_servers.pdfAssistant]

transport = "http"

url = "https://chat.pdfassistant.ai/mcp"

Scripted batch (bash)BASH

Drive Codex non-interactively to batch-process every PDF in the current directory.

#!/usr/bin/env bash

set -euo pipefail

for f in *.pdf; do

  codex exec --server pdfAssistant \

    "Compress $f to under 2MB and save as out/$f"

done

Raw MCP tool invocationBASH

Direct JSON-RPC call against the MCP endpoint — useful for CI debugging.

curl -sS https://chat.pdfassistant.ai/mcp \

  -H "Content-Type: application/json" \

  -H "Accept: application/json, text/event-stream" \

  -H "Authorization: Bearer $PDFA_TOKEN" \

  -d '{

    "jsonrpc": "2.0",

    "id": 1,

    "method": "tools/call",

    "params": {

      "name": "ocr_pdf",

      "arguments": { "file_id": "doc_abc123", "language": "eng" }

    }

  }'

What You Can Do

Every pdfAssistant operation, available inside Codex.

The complete toolset your assistant can call once the MCP server is connected.

Category	Available Tools	Example Prompt
Convert	Word, Excel, PowerPoint to PDF; Webpage URL to PDF; HTML file to PDF; Email to PDF; PDF to Word/Excel/PowerPoint; PDF to image formats (PNG, JPEG, TIFF, GIF, BMP); Graphics to PDF	“Convert this live pricing webpage URL and this PowerPoint presentation into PDFs.”
Combine & Split	Merge multiple PDFs, Split PDF by page range, ZIP/unZIP files	“Merge these three contracts into a single file and ZIP the final output.”
Optimize	Compress PDF, Linearize PDF (web-optimize), Flatten forms, Flatten annotations, Flatten layers, Flatten transparencies, Convert colors, Convert to PDF/X, Rasterize PDF	“Compress this PDF to under 5MB and linearize it so it opens fast on the web.”
Secure & Edit	Encrypt PDF, Add restrictions, Remove encryption, Remove restrictions, Text redaction (via literal strings, presets, or regex), Add text/images to PDF, Attach files to PDF, Add watermark	“Use a regex pattern to redact all Social Security Numbers from this document text.”
Extract	Extract text, Extract images, Export form data, File read/write/append/list helpers	“Extract all the data from the form fields in this document.”
Analyze	Check document metadata (accessibility tags, security settings, creator/origin info, text-extractability status)	“Check the metadata of this file to see if it is fully tagged for accessibility.”
Sign & Forms	Digitally sign PDF, Import form data, Convert XFA to AcroForms	“Convert this old XFA form into a standard AcroForm so I can sign it.”
Archive	Convert to PDF/A (archival standard)	“Convert this contract to PDF/A for long-term archival.”

Use Case Examples

Real Codex + pdfAssistant scenarios.

Single prompts that orchestrate multiple tools end to end.

CI/CD Document Pipeline

Integrate pdfAssistant calls into your build pipeline to auto-generate, convert, or compress documentation artifacts.

Automated Compliance Processing

Script batch redaction and PDF/A conversion across document repositories from the command line.

Developer Documentation Builds

Convert Markdown or HTML documentation to PDF, compress, and publish — all from your terminal workflow.

Data Extraction Scripts

Extract form data, text, or metadata from PDFs programmatically as part of larger automation pipelines.

Security & Privacy

pdfAssistant is designed with enterprise security in mind.

SOC 2 Type 2 Compliant

Our security controls, infrastructure, and data protection practices are rigorously audited and certified to meet strict enterprise standards.

Secure OAuth 2.0 Authentication

Your pdfAssistant credentials are never exposed to your AI platform or stored locally.

Encrypted in Transit

All files and data sent to our servers are protected with TLS 1.3 encryption, the same standard used by banks and healthcare systems.

pdfAssistant Never Trains on Your Data

Your documents, prompts, and extracted data are never used by us to train AI models. Please note that what your AI platform does with data in its own environment is governed by its own privacy policy.

Also available for Claude ChatGPT ← All MCP Servers

Ready to put pdfAssistant to work in your AI assistant?

Connect once. Process forever.

View Paid Plans

MCP server access requires a paid pdfAssistant plan