pdfAssistant, by Datalogics, has announced the launch of its official MCP Server, bringing more than 55 professional PDF operations directly into Claude, ChatGPT, and Codex. The server is available now on paid pdfAssistant plans and authenticates via OAuth 2.0, enabling enterprise-grade PDF processing inside AI workspaces. The launch addresses a critical gap between AI interpretation and deterministic document execution for secure, high-fidelity workflows.
Quick Intel
The pdfAssistant MCP Server divides work according to where each system excels. While the AI assistant interprets user intent, pdfAssistant executes the operation on a duplicate file with full document fidelity. This model solves core fidelity problems where removing sensitive content requires purpose-built tooling rather than visual overlays. Connected through MCP, complex tasks like redaction, OCR, watermarking, and PDF/A conversion are handled in seconds through natural language prompts inside the active conversation or terminal.
For legal and compliance teams, attorneys can prompt redaction of account numbers and SSNs with visual preview before permanent removal and tamper-evident digital signatures. Records teams can apply OCR to scanned board minutes and convert them to PDF/A for retention archiving. Business operations teams can convert documents to PDF, add confidential watermarks, and restrict printing and editing. Developer workflows in OpenAI Codex CLI can compress PDFs and convert them to PDF/A without custom scripts.
The server deliberately contains no summarization, translation, question-answering, or content generation tools. The focus is on the deterministic half: operations that produce byte-accurate files, identical results on every run, and structural changes that hold up across platforms. Capabilities include compression, permanent redaction, digital signatures, archival conversion, form data import and export, and color profile conversion.
"Most AI platforms can tell you what a document says," said Eric Shore, Chief Innovation Officer at Datalogics. "Knowing what to change is the easy half. Executing that change without breaking the structure that makes the document work is the half that requires an engine. We deliberately did not ship summarization or translation tools, because the assistant already does that well. The model handles intent. We handle fidelity. That division is the whole point."
The MCP server ships with dedicated setup guides for three leading AI platforms. pdfAssistant with Claude offers full MCP integration via Streamable HTTP transport with single CLI command setup. pdfAssistant with ChatGPT connects via Developer Mode using remote Streamable HTTP transport. pdfAssistant with Codex provides native CLI integration for build pipelines, CI/CD workflows, and scripted batch processes.
Once connected, eight tool categories become available: Convert into PDF from Word, Excel, PowerPoint, HTML, images, EML, and webpages; Convert out of PDF to Word, Excel, PowerPoint, Markdown, and image formats with CMYK control; Redact with review before commit; Secure and control access with twelve operations for passwords, restrictions, and watermarking; Sign with PFX, PKCS#12, DER and PEM credentials; Optimize and flatten with compression, linearization, rasterization, and color conversion; Extract and inspect text, images, form data, tags, fonts, and permissions; Assemble and archive with merge, split, ZIP, OCR, XFA to AcroForm conversion, and PDF/A and PDF/X standards.
Built for enterprise security requirements, file payloads are encrypted in transit using TLS 1.3, processed in encrypted storage, and permanently deleted within 24 hours. The platform maintains SOC 2 Type 2 audited controls and a strict zero data training policy, with authentication handled exclusively via OAuth 2.0.
The pdfAssistant MCP Server is now available on paid plans and can be connected in under 60 seconds, with full integration guides at pdfassistant.ai/integrations/ai-connections.
About pdfAssistant
pdfAssistant, by Datalogics, is a comprehensive AI-powered PDF platform offering document processing, automation, and analysis tools for individuals and enterprise teams. With a lineage rooted in nearly 60 years of document technology expertise and the foundational development of PDF standards, pdfAssistant delivers professional-grade PDF capabilities through an intuitive interface, a robust REST API, and now a native MCP server for AI workspace integration.