Skip to main content
Glama
einsteindark-edgm

MCP PDF Extract

by einsteindark-edgm
OverviewSchemaRelated ServersScoreDiscussions
Python
Local

MCP PDF Extract

A Model Context Protocol (MCP) server that provides PDF document reading capabilities. This server allows MCP clients to list and read PDF documents from a specified directory.

Architecture

graph TB
    subgraph "MCP Client Layer"
        Client[MCP Client<br/>Claude Desktop / Inspector]
    end
    
    subgraph "MCP Server Layer"
        Server[MCP Documents Server<br/>mcp_documents_server.py]
        FastMCP[FastMCP Framework]
        
        Server --> FastMCP
    end
    
    subgraph "Business Logic Layer"
        PDFLoader[PDF Loader<br/>pdf.py]
        Exceptions[Exception Handler<br/>app/exceptions.py]
        
        PDFLoader --> Exceptions
    end
    
    subgraph "Data Layer"
        PDFFiles[PDF Files<br/>data/pdfs/]
        EnvConfig[Environment Config<br/>.env]
    end
    
    Client <-->|"JSON-RPC over stdio"| Server
    
    Server -->|"Tools & Resources"| PDFLoader
    PDFLoader -->|"Async Read"| PDFFiles
    PDFLoader -->|"Config"| EnvConfig
    
    style Client fill:#e1f5fe
    style Server fill:#fff3e0
    style PDFLoader fill:#f3e5f5
    style PDFFiles fill:#e8f5e9

Component Communication

sequenceDiagram
    participant C as MCP Client
    participant S as MCP Server
    participant P as PDF Loader
    participant F as File System
    
    C->>S: Initialize connection
    S-->>C: Server capabilities
    
    C->>S: List documents (resource)
    S->>P: list_available_pdfs()
    P->>F: Read directory
    F-->>P: PDF file list
    P-->>S: Document metadata
    S-->>C: Document list
    
    C->>S: Read document (tool)
    S->>P: load_pdf(doc_id)
    P->>F: Read PDF file
    P->>P: Extract text
    P-->>S: Document content
    S-->>C: PDF text content

Related MCP server: PDF Reader MCP Server

Features

  • List available PDF documents

  • Read and extract text content from PDF files

  • File size validation

  • Path traversal protection

  • Configurable PDF directory and size limits

Prerequisites

  • Python 3.10 or higher

  • uv package manager (recommended)

Installation

1. Clone the repository

cd /path/to/your/projects
git clone <repository-url>
cd MCP_pdf_extract

2. Create virtual environment and install dependencies

Using uv (recommended):

# Install uv if you haven't already
curl -LsSf https://astral.sh/uv/install.sh | sh

# Create virtual environment
uv venv

# Sync dependencies
uv sync

3. Set up environment variables

Create a .env file in the project root:

MAX_PDF_SIZE_KB=350
PDF_DIR=./data/pdfs

4. Create PDF directory

mkdir -p data/pdfs

Place your PDF files in the data/pdfs directory.

Running the Server

Basic execution

uv run python mcp_documents_server.py

Testing with MCP Inspector

To test the server with the MCP Inspector:

npx @modelcontextprotocol/inspector

In the Inspector interface:

  • Command: uv

  • Arguments: run --with mcp mcp run mcp_documents_server.py

Verify the server is running

To verify the server is responding correctly, you can send a test message:

echo '{"jsonrpc": "2.0", "method": "initialize", "params": {"capabilities": {}}, "id": 1}' | uv run python mcp_documents_server.py

You should see a JSON response from the server.

Available Resources and Tools

Resources

  • docs://documents - Lists all available PDF documents

  • docs://documents/{doc_id} - Fetches the content of a specific PDF document

Tools

  • read_doc_contents - Reads and returns the text content of a PDF document

    • Parameter: doc_id (string) - The filename of the PDF to read

Configuration

The server can be configured using environment variables:

  • PDF_DIR: Directory containing PDF files (default: ./data/pdfs)

  • MAX_PDF_SIZE_KB: Maximum allowed PDF file size in KB (default: 350)

Integration with MCP Clients

Claude Desktop

Add the following to your Claude Desktop configuration file:

macOS: ~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "pdf-extractor": {
      "command": "uv",
      "args": ["--directory", "/path/to/MCP_pdf_extract", "run", "python", "mcp_documents_server.py"],
      "env": {}
    }
  }
}

Troubleshooting

  • Ensure Python 3.10+ is installed: python --version

  • Verify uv is installed: uv --version

  • Check that PDF files are in the correct directory: ls data/pdfs/

  • Ensure the virtual environment is activated when running commands

License

[Your license here]

Available Tools

2 tools
list_available_pdfsB

List all available PDF documents that can be read.

ParametersJSON Schema
NameRequiredDescriptionDefault

No parameters

TDQS

B3.3/5.0
Behavior3/5

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 tool lists PDFs, implying a read-only operation. However, it does not disclose what 'available' means, whether the list is static or dynamic, or any side effects. The description is honest but lacks depth.

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?

A single sentence of 8 words with no redundancy. Every word is necessary. It is appropriately brief for a parameterless tool.

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?

No output schema is provided, and the description does not describe the return format (e.g., file names, paths, IDs). The tool is simple, but the agent needs to know what the output looks like to use it effectively, especially to feed into the sibling 'read_doc_contents'. This gap reduces completeness.

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

Parameters4/5

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

The tool has zero parameters, so the schema is fully descriptive. The description adds slight value by stating the list is of 'all available PDF documents', implying no filtering. Baseline for 0 parameters is 4, and this is met.

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 ('List') and the resource ('all available PDF documents that can be read'). It distinguishes from the sibling tool 'read_doc_contents' by implying the listing is a precursor to reading, but does not explicitly differentiate.

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. It is implied that listing is a discovery step before reading, but there are no explicit usage contexts, prerequisites, or exclusions.

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

read_doc_contentsA

Read the contents of a PDF document and return it as a string.

ParametersJSON Schema
NameRequiredDescriptionDefault
doc_idYesPDF filename to read

TDQS

A3.5/5.0
Behavior3/5

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

No annotations exist, so the description carries full burden. It discloses the tool reads PDFs and returns a string, but does not mention behavior for non-existent files, access permissions, large file handling, or any side effects. Adequate but minimal.

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?

One sentence, front-loaded with the action verb 'Read', zero wasted words. Every element serves a purpose.

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 simple single-parameter tool with no output schema, the description is mostly adequate. It covers the core purpose and return type, but could benefit from mentioning error cases (file not found, unreadable) or that the string contains raw text from the PDF.

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 coverage is 100%, so the description adds little beyond the schema. It correctly describes the single parameter as a 'PDF filename', matching the schema's description. No additional meaning about format, path conventions, or restrictions is provided.

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 tool reads a PDF and returns its content as a string. It specifies both the file type (PDF) and the return format, distinguishing it from siblings like list_available_pdfs which lists files rather than reading them.

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 when to use this tool (after listing PDFs), but does not explicitly state when not to use it or mention alternatives. No guidance on prerequisite steps (e.g., file must exist).

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

B3.4/5.0
Disambiguation5/5

The two tools have clearly distinct purposes: one lists available PDFs, the other reads their contents. There is no overlap or ambiguity.

Naming Consistency4/5

Both tools use snake_case and follow a verb_noun pattern (read_doc_contents, list_available_pdfs). The slight inconsistency between 'doc_contents' and 'pdfs' is minor, and overall naming is predictable.

Tool Count3/5

With only 2 tools, the server is minimal. For a PDF extraction server, a few more tools (e.g., extract metadata, search text) would be expected, but the scope may be intentionally narrow.

Completeness2/5

The server lacks common operations like extracting specific pages, retrieving metadata, or searching within PDFs. The surface is incomplete for typical PDF extraction tasks.

Maintenance

ActivityInactive
ResponsivenessSyncing

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

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

Related MCP Connectors

Related MCP Servers

  • PDF Reader MCP Server

    pablontiv
    F
    license
    A
    quality
    Not graded
    maintenance
    A Model Context Protocol server that extracts and processes content from PDF documents, providing text extraction, metadata retrieval, page-level processing, and PDF validation capabilities.
    4
    1

  • MCP PDF Reader

    rturv
    A
    license
    A
    quality
    C
    maintenance
    A Model Context Protocol server that enables the extraction of text, metadata, and embedded images from PDF files. It provides tools for searching text with context, reading specific pages, and counting total pages within a document.
    7
    29
    1
    MIT

  • MCP Document Server

    watsona4
    A
    license
    Not graded
    quality
    D
    maintenance
    A secure Model Context Protocol server that enables Claude AI to list, search, and read local documents in formats such as PDF, DOCX, and XLSX. It features read-only access with path traversal protection and supports deployment via Docker with SSE or STDIO transport options.
    MIT

Latest Blog Posts

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/einsteindark-edgm/mcp-read-doc-local'

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