Which integrations are available for this server?

Enables reading and analyzing PDF research papers directly from arXiv URLs, including page-specific reading, text searching, and metadata extraction.

How do I use MCP PDF Reader?

1. Click on "Install Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@MCP PDF Reader summarize pages 1 to 5 of research_paper.pdf" That's it! The server will respond to your query, and you can continue using it as needed. Here is a step-by-step guide with screenshots.

MCP PDF Reader

by Saqib-Aziz007

Overview Schema Related Servers Score Discussions

JavaScript

Hybrid

MCP PDF Reader Server

A Model Context Protocol (MCP) server that enables AI assistants like Claude, Windsurf, and other MCP-compatible tools to read and analyze PDF files.

Features

📄 Read PDF files from local paths or URLs
🔍 Search for specific terms within PDFs
📊 Get PDF metadata (page count, author, title, etc.)
📖 Read specific pages or page ranges
🌐 Download and analyze PDFs from the web
🤖 Seamless integration with AI assistants via MCP

Related MCP server: pdf-mcp

Installation

Using npm

npm install -g @dev.saqibaziz/mcp-pdf-reader

Using npx (no installation required)

npx @dev.saqibaziz/mcp-pdf-reader

Configuration

For Claude Desktop

Add this to your Claude Desktop configuration file:

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

{
  "mcpServers": {
    "pdf-reader": {
      "command": "npx",
      "args": ["-y", "@dev.saqibaziz/mcp-pdf-reader"]
    }
  }
}

For Windsurf

Option 1: Via Plugin Store (Coming Soon)

Open Windsurf
Click the Plugins icon in Cascade panel
Search for "PDF Reader"
Click Install

Option 2: Manual Configuration

Edit your MCP configuration file:

macOS: ~/Library/Application Support/Windsurf/User/globalStorage/codeium.codeium/mcp_config.json Windows: %APPDATA%\Windsurf\User\globalStorage\codeium.codeium\mcp_config.json Linux: ~/.config/Windsurf/User/globalStorage/codeium.codeium/mcp_config.json

{
  "mcpServers": {
    "pdf-reader": {
      "command": "npx",
      "args": ["-y", "@dev.saqibaziz/mcp-pdf-reader"]
    }
  }
}

After adding, click the refresh button in the Plugins panel.

For Cline

Add this to your MCP settings file:

{
  "mcpServers": {
    "pdf-reader": {
      "command": "npx",
      "args": ["-y", "@dev.saqibaziz/mcp-pdf-reader"]
    }
  }
}

Available Tools

The server provides the following tools to AI assistants:

`read_pdf_pages`

Read specific pages from a PDF file.

Parameters:

pdf_path (string): Path to the PDF file
pages (array): List of page numbers to read

`read_pdf_page_range`

Read a range of pages from a PDF file.

Parameters:

pdf_path (string): Path to the PDF file
start_page (number): First page to read (inclusive)
end_page (number): Last page to read (inclusive)

`search_pdf`

Search for terms in a PDF file and return pages containing them.

Parameters:

pdf_path (string): Path to the PDF file
terms (string or array): Search term(s)

`get_pdf_metadata`

Get metadata from a PDF file (page count, author, title, etc.).

Parameters:

pdf_path (string): Path to the PDF file

Usage Examples

Once configured, you can ask your AI assistant:

Local Files:

"Read pages 1-5 from document.pdf"
"Search for 'machine learning' in research.pdf"
"What's the metadata of report.pdf?"
"Read page 10 from presentation.pdf"

URLs:

"Read this PDF: https://example.com/research-paper.pdf"
"Search for 'climate change' in https://example.com/report.pdf"
"Get metadata from https://arxiv.org/pdf/2301.00001.pdf"
"Read pages 1-3 from https://example.com/whitepaper.pdf"

Development

Prerequisites

Node.js >= 18.0.0
npm or yarn

Setup

# Clone the repository
git clone https://github.com/Saqib-Aziz007/mcp-pdf-reader.git
cd mcp-pdf-reader

# Install dependencies
npm install

# Build the project
npm run build

# Run in development mode
npm run dev

Scripts

npm run build - Compile TypeScript to JavaScript
npm run dev - Watch mode for development
npm start - Run the compiled server
npm run prepare - Pre-install build hook

Technical Details

This MCP server is built with:

@modelcontextprotocol/sdk - MCP SDK for TypeScript
pdf-parse - PDF parsing library
TypeScript for type safety

Contributing

Contributions are welcome! Please feel free to submit a Pull Request.

License

MIT License - see LICENSE file for details

Author

Muhammad Saqib Aziz

Support

If you encounter any issues or have questions:

Open an issue on GitHub
Check the MCP documentation

Acknowledgments

Built with the Model Context Protocol by Anthropic.

Available Tools

4 tools

get_pdf_metadataA

Get metadata information from a PDF file without reading all content.

ParametersJSON Schema

Name	Required	Description	Default
`path`	Yes	Absolute or relative path to the PDF file, or a URL (http:// or https://)

TDQS

A3.9/5.0

Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden of behavioral disclosure. It states the tool extracts metadata 'without reading all content', which is useful behavioral context about performance/scope. However, it doesn't disclose other important traits like error handling, permission requirements, rate limits, or what specific metadata fields are returned.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, efficient sentence that front-loads the core purpose. Every word earns its place - 'Get metadata information' states the action, 'from a PDF file' specifies the resource, and 'without reading all content' provides important differentiation from sibling tools.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a single-parameter tool with 100% schema coverage but no annotations and no output schema, the description provides adequate basic context about what the tool does and its scope. However, it doesn't describe what metadata is returned or potential limitations, which would be helpful given the lack of output schema.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already fully documents the single 'path' parameter. The description doesn't add any parameter-specific information beyond what's in the schema. This meets the baseline expectation when schema coverage is high.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the specific action ('Get metadata information') and resource ('from a PDF file'), and distinguishes it from siblings by specifying 'without reading all content' - implying it's different from read_pdf, read_pdf_page, and search_pdf which likely involve content reading or searching.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides clear context about when to use this tool ('without reading all content'), suggesting it's for lightweight metadata extraction rather than full content processing. However, it doesn't explicitly state when NOT to use it or name specific alternatives among the sibling tools.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

read_pdfA

Read and extract text content from a PDF file. Returns the full text content and metadata.

ParametersJSON Schema

Name	Required	Description	Default
`path`	Yes	Absolute or relative path to the PDF file, or a URL (http:// or https://)

TDQS

A3.5/5.0

Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden. It mentions returning 'full text content and metadata', which is useful, but lacks details on error handling (e.g., invalid paths, corrupted files), performance (e.g., large file handling), or limitations (e.g., OCR support, encrypted files). The description adds some value but is incomplete for behavioral context.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two sentences with zero waste, front-loaded with the core purpose and efficiently states the return values. Every sentence earns its place by conveying essential information without redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given no annotations and no output schema, the description is moderately complete for a simple read operation. It covers the purpose and return values, but lacks details on behavioral traits (e.g., errors, limits) and output structure. It is adequate but has clear gaps in context.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, with the parameter 'path' fully documented in the schema. The description does not add any additional meaning beyond what the schema provides (e.g., no examples of path formats or URL specifics). Baseline 3 is appropriate as the schema handles parameter documentation.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the specific action ('read and extract text content') and resource ('from a PDF file'), distinguishing it from sibling tools like 'get_pdf_metadata' (metadata only), 'read_pdf_page' (single page), and 'search_pdf' (search within content). It explicitly mentions both text extraction and metadata return.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage for extracting full text and metadata from PDFs, but does not explicitly state when to use this tool versus alternatives like 'read_pdf_page' for single pages or 'search_pdf' for searching. No exclusions or prerequisites are mentioned.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

read_pdf_pageB

Read a specific page or range of pages from a PDF file.

ParametersJSON Schema

Name	Required	Description
`path`	Yes	Absolute or relative path to the PDF file, or a URL (http:// or https://)
`page`	No	Page number to read (1-indexed)
`startPage`	No	Start page for range (1-indexed)
`endPage`	No	End page for range (1-indexed)

TDQS

B3.1/5.0

Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries full burden. It states the action 'read' but doesn't disclose behavioral traits like permissions needed, file size limits, rate limits, output format (e.g., text, images), error handling, or whether it's read-only/destructive. For a tool with no annotations, this leaves significant gaps in understanding its behavior.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, efficient sentence with zero waste. It's front-loaded with the core action and resource, appropriately sized for the tool's complexity. Every word earns its place without redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given no annotations, no output schema, and 4 parameters with full schema coverage, the description is minimally adequate. It covers the basic purpose but lacks details on behavior, output, or usage context. For a read operation with no structured safety hints, it should do more to explain what 'read' entails and potential limitations.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema fully documents all 4 parameters (path, page, startPage, endPage). The description adds minimal value beyond the schema, mentioning 'page or range of pages' which aligns with parameters but doesn't provide additional syntax, constraints, or examples. Baseline 3 is appropriate as the schema does the heavy lifting.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb 'read' and the resource 'PDF file', specifying it's for 'a specific page or range of pages'. It distinguishes from sibling 'read_pdf' (likely reads entire PDF) and 'get_pdf_metadata' (metadata-focused), but doesn't explicitly mention 'search_pdf' (search-focused). The purpose is specific but could be more precise about sibling differentiation.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance on when to use this tool versus alternatives like 'read_pdf' (full PDF) or 'search_pdf' (content search). The description implies usage for partial reading but doesn't specify scenarios, prerequisites, or exclusions. It lacks explicit when/when-not instructions or named alternatives.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

search_pdfC

Search for specific text within a PDF file.

ParametersJSON Schema

Name	Required	Description
`path`	Yes	Absolute or relative path to the PDF file, or a URL (http:// or https://)
`query`	Yes	Text to search for
`caseSensitive`	No	Whether search should be case-sensitive

TDQS

C2.9/5.0

Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries full burden but offers minimal behavioral insight. It states the basic function but doesn't disclose traits like whether it's read-only, potential performance impacts, error handling, or output format. For a search tool, this leaves key operational aspects unclear.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, efficient sentence that directly states the tool's function without any fluff or redundancy. It's front-loaded with the core purpose, making it highly concise and well-structured for quick understanding.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's moderate complexity (searching PDFs) and lack of annotations or output schema, the description is insufficient. It doesn't explain what the search returns (e.g., matches, positions, context), error cases, or limitations, leaving gaps in operational context.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so parameters are well-documented in the schema itself. The description adds no additional meaning beyond implying text search functionality, which is already clear from the schema. This meets the baseline for high schema coverage without extra value.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action ('Search for specific text') and resource ('within a PDF file'), making the purpose immediately understandable. However, it doesn't explicitly differentiate from sibling tools like 'read_pdf' or 'read_pdf_page', which might also involve text extraction, so it misses full sibling distinction.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives like 'get_pdf_metadata' or 'read_pdf'. It lacks any mention of prerequisites, exclusions, or comparative contexts, leaving the agent to infer usage from tool names alone.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

A3.7/5.0

Disambiguation5/5

Each tool has a clearly distinct purpose: get_pdf_metadata retrieves metadata only, read_pdf extracts full text, read_pdf_page targets specific pages, and search_pdf finds text matches. There is no overlap in functionality, making tool selection unambiguous for an agent.

Naming Consistency5/5

All tool names follow a consistent verb_noun pattern with snake_case (e.g., get_pdf_metadata, read_pdf_page). The naming is predictable and readable throughout the set, with no deviations in style or convention.

Tool Count5/5

With 4 tools, this server is well-scoped for PDF reading operations. Each tool serves a distinct and necessary function in the domain, avoiding bloat while covering core needs like metadata extraction, full/partial text reading, and searching.

Completeness4/5

The tool set covers essential PDF reading operations effectively, including metadata, text extraction, page-specific reading, and searching. A minor gap is the lack of tools for editing or manipulating PDFs (e.g., merge, split, annotate), but for a 'reader' server, the surface is largely complete and functional.

Maintenance

ActivityInactive

ResponsivenessNo issues

Resources

Need Help?

Related Servers

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

PDF to Markdown (pdf2md.dev)
dev.pdf2md
Hosted MCP server: convert PDFs to clean, LLM-ready Markdown with tables, formulas and OCR.
AI & Machine Learning Image & Video Processing
2
PDF Redaction MCP A
com.pdf-redaction
MCP server for detecting and redacting PII (Personally Identifiable Information) in PDF documents.
File Systems Security
23
CustomGPT.ai
ai.customgpt.mcp
The CustomGPT.ai MCP server is a fully managed, RAG-powered endpoint that connects large language models with private knowledge bases and external data sources. It provides tools for retrieval-augmented generation queries (send_message), data ingestion (upload_file), and source listing, enabling AI agents to query private documents like PDFs with high accuracy and real-time citations.
RAG Systems Knowledge & Memory Search
2
driflyte-mcp-server
com.driflyte
Driflyte MCP server which lets AI assistants query topic-specific knowledge from web and GitHub.
Search Web Scraping Knowledge & Memory
211

Related MCP Servers

mcp-pdf-tools
Documentation Access Research & Data Text Summarization
seraphinerenard
A
license
A
quality
Not graded
maintenance
An MCP server that enables users to read, search, and analyze PDF documents. It provides tools for extracting text, viewing metadata, searching content with context, and generating word statistics.
Updated 7 months ago (2026-01-29 18:31 UTC)
5
pdf-mcp
Documentation Access File Systems Research & Data
I-CAN-hack
A
license
A
quality
C
maintenance
An MCP server for reading, rendering, and searching PDF files, specifically optimized for LLMs to extract text, tables, and technical diagrams. It enables metadata retrieval, multi-format text extraction, and page-to-image rendering using PyMuPDF.
Updated a month ago (2026-07-30 09:07 UTC)
5
77
MIT
pdf-mcp
File Systems App Automation
angshuman
A
license
Not graded
quality
D
maintenance
An MCP server that provides tools for reading, writing, and manipulating PDF files, including text extraction, metadata retrieval, and merging or splitting documents. It also enables users to create PDFs from plain text and convert specific pages or entire documents into images.
Updated 5 months ago (2026-03-24 02:55 UTC)
53
ISC
Docalyze
File Systems Image & Video Processing
LunarPerovskite
A
license
B
quality
D
maintenance
An MCP server that lets AI assistants read and visually analyze local documents — PDFs, Excel spreadsheets, CSV files, Word documents, PowerPoint presentations, and images.
Updated 4 months ago (2026-04-28 15:33 UTC)
4
66
MIT

Latest Blog Posts

Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)
By Om-Shree-0709 on July 25, 2026.
mcp
Agent Identity
OAuth 2.1
Your AI Chatbot Just Exposed Your CEO's Salary to an Intern
By Om-Shree-0709 on July 2, 2026.
Agent Identity
MCP Security
OAuth Delegation
Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)
By Om-Shree-0709 on June 30, 2026.
Agentic Ai
Prompt Injection
WebAssembly

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/Saqib-Aziz007/mcp-pdf-reader'

If you have feedback or need assistance with the MCP directory API, please join our Discord server