# PDF Parsing for AI Agents: The Best MCPs and When to Use Each

> Streamline your document workflows by integrating PDF parsing with the Model Context Protocol (MCP). This guide explores how to build a standardized interface that allows AI agents to extract and reason over complex PDF data with precision and ease.

_Maximem Team · April 5, 2026_

You are building an agent - a contract analyzer, a financial report summarizer or a support bot that reads uploaded documents. The requirement is simple: give it PDF access. The reality? Not so simple.

Giving an agent access to PDF content sounds like one step. It is actually four: Parse the PDF (extract text and structure), [chunk the content into meaningful segments](https://www.maximem.ai/glossary/chunking), embed the chunks as vectors and retrieve the right chunks at query time. This article covers the first step: parsing. The critical one. Because here's the thing: get parsing wrong and everything downstream suffers. Your chunks are messy. Your [embeddings](https://www.maximem.ai/glossary/embeddings) don't capture meaning. Your [retrieval returns irrelevant pages](https://www.maximem.ai/glossary/retrieval-pipeline). Get it right and the entire pipeline works. I have seen teams waste weeks on retrieval systems when the real problem was a [PDF parsing](https://www.maximem.ai/blog/mcp-servers-explained).

Here's what actually works for parsing in 2026.

# MCP Servers: Your Native Options

If you're building with Claude or another AI system that supports MCPs, you have four real contenders. Let me walk through each one because they solve different problems. (New to MCPs? Here's a guide on \[how MCP servers work\](https://www.maximem.ai/blog/guides/mcp-servers-explained).)

-   **pymupdf4llm-mcp** wraps PyMuPDF and outputs markdown optimized for language models. It's fast. The markdown formatting is genuinely useful because LLMs work better with structured text. When you need clean text extraction from PDFs that are mostly text-based (annual reports, policy documents, research papers), this is the default choice. The limitation: it struggles with complex table structures. If your PDF is a maze of multi-column tables? You'll get confused output.
    
-   **SylphxAI PDF Reader MCP** is production-ready and built for scale. It does parallel processing. We're talking 5 to 10 times faster on large documents compared to sequential approaches. The test coverage is 94 percent, which matters if you care about reliability. The trade-off: it's the newer player in this space. Smaller community. Fewer battle-tested [integrations](https://www.maximem.ai/glossary/integrations). But if you're processing hundreds of documents daily? The speed difference is real.
    
-   **AWS Labs Document Loader MCP** handles multiple formats. PDF, Word, Excel, PowerPoint, images. One MCP for everything. This appeals to teams already deep in AWS who want a single integration point rather than juggling tools. The downside is the dependency chain. It's heavier. You inherit AWS SDK overhead even if you only need PDF parsing.
    
-   **Trafflux PDF Reader MCP** uses PyPDF2 under the hood and deploys as a Docker container. It standardizes output as JSON. If your [deployment](https://www.maximem.ai/glossary/deployment) pipeline is Docker-based and you value standardized interfaces, this works. The reality though: PyPDF2 is less capable than PyMuPDF on complex layouts. It's the simpler option, which sometimes means less functionality.
    

# When You Can't Use MCPs

Not everyone is on the MCP train yet. Some teams call APIs directly. Some need specialized capabilities that MCPs haven't caught up to. That's where the other tools live.

-   **LlamaParse** (by LlamaIndex) is interesting. It takes six seconds, regardless of document size. You could feed it a 500-page financial statement or a 5-page memo. Same speed. It preserves table structures and multi-column layouts in a way that's genuinely useful. Teams using it on financial documents report 15 percent accuracy improvements on structured data extraction compared to basic parsers. There's a free tier, paid tiers for volume. Best use case: you're prototyping something quickly and you need it to work reliably on your first try.
    
-   [**Unstructured.io**](http://Unstructured.io) is the enterprise play. No-code platform. Strong OCR capabilities. 100 percent accuracy on simple tables. The problem shows up with complexity: 75 percent accuracy on complex table structures. And it's slow. 51 seconds per page. A 100-page document? That's real latency. But if you work in an organization where "ease of integration" and "AWS integration" matter more than milliseconds, this is solid.
    
-   **Docling** is the table extraction specialist. 97.9 percent accuracy on complex tables from sustainability reports, financial documents, and research papers. If your use case is "I need to reliably extract structured data from complex layouts," Docling is the answer. It's not the fastest. It's not the cheapest. It's the most accurate.
    

# The Comparison Table

Here's the practical breakdown:

![](data:image/png;base64,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)

# How to Actually Decide

This is the framework I use when someone asks me which tool to recommend:

-   **You need an MCP server and speed is your constraint?** Use SylphxAI PDF Reader.
    
-   **You need an MCP server and you want clean markdown output?** pymupdf4llm-mcp.
    
-   **You need one MCP that handles PDFs, Word docs, and images?** AWS Labs Document Loader.
    
-   **Your PDFs are financial statements or contracts with complex tables?** Docling (even if it's not an MCP).
    
-   **You're in an enterprise environment where OCR and ease of integration beat raw speed?** [Unstructured.io](http://Unstructured.io).
    
-   **You're building a prototype and you need something that works on your first attempt?** LlamaParse.
    

# What Comes Next

Here's something people miss: parsing is step one. Once you have clean text extracted, you still need to chunk it well. Not just split on character count. Actually preserve semantic boundaries. Then embed it with the right model. Then build retrieval that surfaces the right chunks at query time. Each of these steps deserves its own attention. Each one will make or break your system.

For parsing specifically, the landscape moves fast. The tools I listed today may have new competitors in six months. Vendors iterate constantly. Test on your actual PDFs before committing. What works for clean text PDFs may completely fail on scanned documents with tables. What works on 10-page reports may timeout on 500-page regulatory filings. Your actual document set is what matters.

Get parsing right. Everything else becomes simpler.

\---

**Last updated:** April 2026

Ready to build agents that actually work with documents? Test these tools with your real PDFs today. Start with the decision framework above, run a quick proof of concept, and measure extraction quality on your actual use case. Need help understanding MCP terminology? Check the [AI Glossary](https://www.maximem.ai/glossary) for quick reference.

---

Source: [https://www.maximem.ai/blog/pdf-parsing-mcp](https://www.maximem.ai/blog/pdf-parsing-mcp)
