io.github.jztan/pdf-mcp

Official

by jztan · Python

Production-ready MCP server for PDF processing with intelligent caching.

Process and extract data from PDFs with intelligent caching.

Topics

aiclaudedocument-processingllmmcpmodel-context-protocolpdfpythonagentic-aicodex-clicopilotopencodemcp-servercjkocrpdf-extractionpymupdfsemantic-searchtable-extraction

README.md14 KBView on GitHub

pdf-mcp

Surgical PDF access for AI agents — search, read, and extract without flooding context.

An MCP server that lets Claude Code and other AI agents search a PDF by meaning or keyword, read only the pages that matter, and cleanly pull out tables, images, and scanned text — even from multi-column and Japanese layouts.

mcp-name: io.github.jztan/pdf-mcp

Try it in your browser

See what your AI agent sees →

Drop in any PDF and watch an agent skim it, search it, and read only the pages that matter — using a fraction of the tokens. 100% client-side, no install required.

Why pdf-mcp?

	Without pdf-mcp	With pdf-mcp
Large PDFs	Context overflow	Chunked reading
Token budgeting	Guess and overflow	Estimated tokens before reading
Finding content	Load everything	Hybrid search (BM25 keyword + semantic)
Tables	Lost in raw text	Extracted and inlined per page
Multi-column PDFs	Columns interleaved in extracted text	Column-aware reading order (`pdf-mcp[multicolumn]`)
Vertical scripts (Japanese)	Columns scrambled / glyph soup	Geometric reorder of vertical text (tategaki / 縦書き); CJK keyword search works on unspaced Japanese/Chinese/Korean text via a char-split FTS index
Images	Ignored	Extracted as PNG files
Repeated access	Re-parse every time	SQLite cache
Scanned PDFs	No text extracted	OCR via Tesseract, parallelized across pages (`pdf_read_pages(ocr=True)`)
Visual content	Must describe in words	Render page as image (`pdf_render_pages`)
Hidden / injected text	Silently ingested as if a human vetted it	Flagged as untrusted — hidden-text detection (`content_trust=True`)
Tool design	Single monolithic tool	9 specialized tools

Features

Hybrid search — find relevant pages with a question, not a page range. Combines BM25 keyword and semantic search via Reciprocal Rank Fusion
Paginated reading — fetch only the pages your agent needs; large documents don't blow your context window
OCR — scanned and image-based PDFs are fully readable and searchable via Tesseract, parallelized across pages for ~2–3x faster extraction on typical scans
Structured extraction — tables, embedded images, and table of contents returned as structured data, not text soup
Vertical-script reading order — Japanese tategaki (縦書き) reconstructed from glyph geometry into correct top-to-bottom, right-to-left order; article segmentation for dense magazine layouts; mojibake filtered
Persistent cache — SQLite-backed; re-reads are instant and survive server restarts
Secure URL fetching — HTTPS-only with SSRF protection; local network ranges are blocked
Content-trust / hidden-text detection — flags text a human reader can't see (invisible render mode, sub-point fonts, transparent or white-on-white fill, off-page) so an agent treats it as untrusted rather than vetted. pdf_info(content_trust=True) reports it; the read tools carry a hidden_text_detected flag. Flag-only — nothing is stripped. Includes a configurable, non-English injection_in_hidden phrase hint

Installation
Quick Start
Tools
Example Workflow
Configuration
Roadmap
Contributing
Security
License

Installation

bash

pip install pdf-mcp

For semantic search (adds fastembed and numpy, ~67 MB model download on first use):

bash

pip install 'pdf-mcp[semantic]'

For correct reading order on multi-column PDFs (adds pymupdf4llm, which pulls pymupdf_layout/onnxruntime):

bash

pip install 'pdf-mcp[multicolumn]'

Without it, multi-column pages fall back to positional-sort extraction, which can interleave columns.

For Japanese/Chinese/Korean PDFs, CJK keyword search works out of the box (a char-split FTS index matches unspaced CJK terms). The [cjk] extra adds semantic CJK search (embeddings); extraction works without either:

bash

pip install 'pdf-mcp[cjk]'

For OCR on scanned PDFs (requires system Tesseract):

bash

# macOS
brew install tesseract

# Ubuntu/Debian
apt install tesseract-ocr

# Windows — download the installer from:
# https://github.com/UB-Mannheim/tesseract/wiki
# Then add the install directory to your PATH.

Quick Start

Choose your MCP client below to get started:

<details open> <summary>Claude Code</summary>

bash

claude mcp add pdf-mcp -- pdf-mcp

Or add to ~/.claude.json:

json

{
  "mcpServers": {
    "pdf-mcp": {
      "command": "pdf-mcp"
    }
  }
}

</details> <details> <summary>Claude Desktop</summary>

Add to your claude_desktop_config.json:

json

{
  "mcpServers": {
    "pdf-mcp": {
      "command": "pdf-mcp"
    }
  }
}

Config file location:

macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json

Restart Claude Desktop after updating the config.

</details> <details> <summary>Visual Studio Code</summary>

Requires VS Code 1.101+ with GitHub Copilot.

CLI:

bash

code --add-mcp '{"name":"pdf-mcp","command":"pdf-mcp"}'

Command Palette:

Open Command Palette (Cmd/Ctrl+Shift+P)
Run MCP: Open User Configuration (global) or MCP: Open Workspace Folder Configuration (project-specific)

Add the configuration:

json

{
  "servers": {
    "pdf-mcp": {
      "command": "pdf-mcp"
    }
  }
}

Save. VS Code will automatically load the server.

Manual: Create .vscode/mcp.json in your workspace:

json

{
  "servers": {
    "pdf-mcp": {
      "command": "pdf-mcp"
    }
  }
}

</details> <details> <summary>Codex CLI</summary>

bash

codex mcp add pdf-mcp -- pdf-mcp

Or configure manually in ~/.codex/config.toml:

toml

[mcp_servers.pdf-mcp]
command = "pdf-mcp"

</details> <details> <summary>Kiro</summary>

Create or edit .kiro/settings/mcp.json in your workspace:

json

{
  "mcpServers": {
    "pdf-mcp": {
      "command": "pdf-mcp",
      "args": [],
      "disabled": false
    }
  }
}

Save and restart Kiro.

</details> <details> <summary>Other MCP Clients</summary>

Most MCP clients use a standard configuration format:

json

{
  "mcpServers": {
    "pdf-mcp": {
      "command": "pdf-mcp"
    }
  }
}

With uvx (for isolated environments):

json

{
  "mcpServers": {
    "pdf-mcp": {
      "command": "uvx",
      "args": ["pdf-mcp"]
    }
  }
}

</details>

Verify Installation

bash

pdf-mcp --help

Tools

The typical pattern: call pdf_info first to plan, then pdf_search to locate — its paragraph excerpts are often enough to answer directly. Use pdf_read_pages or pdf_read_all when you need deeper context.

Tool	What it does
`pdf_info`	Page count, metadata, TOC summary, scanned-page detection. Call first. Pass `content_trust=True` for a `content_trust` block (`suspicious`, `hidden_text_runs`, `hidden_chars`, `injection_in_hidden`, `pages_flagged`, `signals`); add `detail=True` for per-span `spans`.
`pdf_get_toc`	Full table of contents for documents with >50 bookmarks
`pdf_read_pages`	Read specific pages or ranges; OCR-on-demand; embedded images + tables. Always returns `hidden_text_detected` (response level) and per-page `hidden_text`; `hidden_text_detected: true` means some returned text was invisible to a human reader and should be treated as especially untrusted.
`pdf_read_all`	Read entire document in one call (byte-capped for safety). Always returns `hidden_text_detected`; `hidden_text_detected: true` means some returned text was invisible to a human reader and should be treated as especially untrusted.
`pdf_render_pages`	Render pages as PNG for vision models — diagrams, handwriting, scans
`pdf_search`	Hybrid RRF search (keyword + semantic), page or section granularity, optional paragraph excerpts
`pdf_cache_stats`	Per-document cache breakdown + total size
`pdf_cache_clear`	Clear expired or all cache entries
`server_info`	Which optional features (column-aware, OCR, semantic) and config are active. Call before feature-dependent calls.

Example prompts:

code

"Read the PDF at /path/to/document.pdf"
"Which pages discuss supply chain risks?"
"Find sections about the training process"
"Show me what page 5 looks like"
"OCR pages 3-5 of the scanned PDF"

See docs/tool-reference.md for the complete reference — every parameter, response shape, security contract, and example. For semantic-search model selection, see docs/embedding-models.md.

Example Workflow

For a large document (e.g., a 200-page annual report):

code

User: "Summarize the risk factors in this annual report"

Agent workflow:
1. pdf_info("report.pdf")
   → 200 pages, TOC shows "Risk Factors" on page 89

2. pdf_search("report.pdf", "risk factors")
   → Matches with structural paragraph excerpts — each excerpt
     is the bullet, paragraph, or heading that matched, not a
     fixed-width window. Often enough to answer directly.

3. If excerpts are sufficient → synthesize answer

4. If more context needed:
   pdf_read_pages("report.pdf", "89-95")
   → Full page text for deeper reading

Configuration

pdf-mcp works out of the box with no configuration. To restrict which paths and URL hosts the server can access, tune cache and worker settings, or understand what's cached, see docs/configuration.md.

Access control — ~/.config/pdf-mcp/config.toml allow/deny rules for paths and URLs, plus response byte caps
Content-trust phrases — extend the hidden-text injection_in_hidden hint with your own (including non-English) phrases via [content_trust].injection_phrases
Environment variables — cache directory, TTL, and parallel OCR/render worker count
Caching — SQLite-backed persistence, what's cached, and invalidation

Roadmap

See ROADMAP.md for planned features and release history.

Contributing

Contributions are welcome. See docs/contributing.md for setup, checks, the coherence eval harness, and quality-loop guidelines.

Security

Found a vulnerability? See SECURITY.md for the threat model, reporting channel, and expected response timeline. Please do not open a public GitHub issue for unpatched security reports.

License

MIT — see LICENSE.

Blog posts

Background, benchmarks, and design notes from building pdf-mcp:

Getting started

How I Built pdf-mcp — The problem with large PDFs in AI agents and a working solution
How Claude Code Actually Reads PDFs — How AI agents use pdf-mcp tools to read and navigate PDF documents
How AI Agents Should Read PDFs: 5 Patterns That Survived Production — Five production-tested patterns for how agents should navigate PDFs at scale

Search & retrieval

Semantic vs Keyword Search for AI Agents — Benchmarks and a dual-search routing pattern: FTS5 for exact identifiers, embeddings for natural language
Hybrid Search vs Query Routing for AI Agents — Why pdf-mcp uses hybrid RRF instead of query routing: benchmarks showing RRF wins across query types
Section Chunking vs Page Chunking for AI Agents — Why section-aware search delivers full section content in one call while page-mode costs 2–6 extra tool calls per query
Section-Level RAG: Why BM25 Beat Hybrid Search in My Benchmark — Why pdf-mcp's section-grain search is BM25-only: hybrid RRF caused a 33% lexical regression at section grain, so granularity decides the search technique

Engineering & security

MCP Server Security: 8 Vulnerabilities — What we found when we audited an MCP server for security holes
Your LLM Is Free QA for Your MCP Server — Four Payload UX bugs in pdf-mcp that schema tests missed but Claude Desktop surfaced during real use

Install

Configuration

Environment variables

PDF_MCP_CACHE_DIR

Directory for storing PDF cache (default: ~/.cache/pdf-mcp)

PDF_MCP_CACHE_TTL

Cache time-to-live in hours (default: 24)

claude_desktop_config.json

{
  "mcpServers": {
    "pdf-mcp": {
      "command": "uvx",
      "args": [
        "pdf-mcp"
      ],
      "env": {
        "PDF_MCP_CACHE_DIR": "<YOUR_PDF_MCP_CACHE_DIR>",
        "PDF_MCP_CACHE_TTL": "<YOUR_PDF_MCP_CACHE_TTL>"
      }
    }
  }
}

io.github.jztan/pdf-mcp

Topics

pdf-mcp

Try it in your browser

Why pdf-mcp?

Features

Contents

Installation

Quick Start

Verify Installation

Tools

Example Workflow

Configuration

Roadmap

Contributing

Security

License

Links

Blog posts

Install

Configuration