Nitro Launches MCP Connector for Claude AI, Unveils Document Automation Platform

Nitro Software has announced early access to Nitro MCP, a Model Context Protocol connector that integrates its document engine directly into Claude. The release marks the first phase of Nitro Automate, an intelligent document automation solution designed to run end-to-end workflows within AI agents and existing enterprise systems.

The announcement came via official press release on Business Wire, positioning the connector as a bridge between AI chat interfaces and production-grade document operations.

Here's the practical reality: instead of downloading a file, opening a separate PDF tool, running an operation, and returning to your workflow, you describe the outcome in Claude. Nitro handles the execution and returns the result. No code required. No new interface to learn.

According to Nitro's 2026 Enterprise AI Report, 75–95% of enterprise employees now use AI for document tasks, and 96% of executives use AI for work at least weekly. Yet complex document capabilities have remained largely disconnected from the AI environments where work actually happens. Employees move constantly between AI tools and document workflows—uploading files to extract and summarize, then stepping back out to review, edit, and route. That back-and-forth creates friction, delays, and in many organizations, ungoverned shadow AI activity.

Nitro MCP closes that gap by connecting its document engine to Claude through an MCP server. The connector enables teams to condense multiple document tasks into a single prompt in Claude chat, such as data entry, information extraction, agreement processing, and other document workflows.

John Fitzpatrick, CTO of Nitro Software, noted that most AI tools bolt on PDF and document operations using whatever open-source libraries happen to be available. The results are unpredictable and nowhere near best-in-class. Nitro MCP changes that by delivering Nitro's full document and workflow capabilities in a format that AI agents can use reliably.

The connector gives Claude access to document tools across five categories. Extract data: pull structured information—such as text, tables, form field values—out of PDFs and into spreadsheets, databases, or downstream workflows. Convert and transform files: convert between PDF, Word, Excel, PowerPoint, and image formats. Merge, split, compress, rotate, or delete pages. Protect and secure documents: redact sensitive content, flatten finalized files to prevent restoration, apply or remove password protection. Extract accessibility data: pull document structure and accessibility metadata from PDFs for compliance and audit preparation.

When you use Nitro MCP, your files aren't handed to Claude. The connector calls Nitro to perform the document operation and only the result needed to answer your request is returned to the agent. Your documents stay on Nitro's servers, and nothing you process is ever used to train AI models.

Early access is available now via direct download from Nitro's official page. The setup takes less than five minutes: download the signed installer, run it, sign in with your Nitro account when prompted, then point Claude at a file or folder and describe what you need. Existing Nitro customers can download immediately using their current credentials. New users can sign up for a free 14-day trial.

The Claude app marketplace listing is still pending. Nitro MCP is available today as a signed installer direct from Nitro. Early Access members get the connector first, and the company will update the page when it's live in the store. This binary download approach (a bit old-school, but it gets the tech in users' hands faster) bypasses the typical app store review timeline.

Nitro Automate, the broader platform, will extend these capabilities beyond Claude. It seamlessly integrates with custom applications using developer APIs, along with low-code and no-code automation platforms. The opportunity for organizations to unlock meaningful time savings is significant. Nitro's independent survey found that 89% of employees report saving an average of 9+ hours per week on document tasks with AI.

The company serves 67% of the Fortune 500 and millions of users worldwide. Based across the U.S., Canada, Europe, and Australia, Nitro has guided businesses through digital transformation for more than 20 years. This isn't a startup's first attempt at document AI—it's an established player extending its infrastructure into the AI agent layer.

Whether this actually reduces the cognitive load of document work, or just adds another layer of tooling to manage, remains to be seen. The technology works. The question is whether organizations will trust AI agents with sensitive document operations at scale, or keep human oversight as the final gatekeeper.

Artūras Malašauskas is an AI Systems Integrator with 20+ years of production-grade web engineering experience. He has designed, shipped, and scaled enterprise Python/PHP systems for logistics, SaaS, and public-sector clients. For the past year, he has focused exclusively on AI integrations: deploying open-source LLMs, building generative media pipelines (image, audio, video), and engineering multi-agent workflows for real production environments. His standard: reproducibility, security, cost-efficient inference—no vaporware. He documents and evaluates emerging AI tooling, separating verified capabilities from marketing noise. Technical editor at: muza-ai.eu, ai-verslas.lt, ai-naujinos.lt Connect on LinkedIn