PDF Reader MCP Server (@shtse8/pdf-reader-mcp)

Created By
shtse8a year ago
An MCP server built with Node.js/TypeScript that allows AI agents to securely read PDF files (local or URL) and extract text, metadata, or page counts. Uses pdf-parse.
Overview

What is PDF Reader MCP?

PDF Reader MCP is a Node.js/TypeScript server that enables AI agents to securely read PDF files from local or URL sources and extract text, metadata, or page counts using the pdf-parse library.

How to use PDF Reader MCP?

To use PDF Reader MCP, configure it in your MCP host settings, either using npx or as a Docker container, ensuring the project root directory is correctly set for local file access.

Key features of PDF Reader MCP?

  • Secure project root focus to prevent unauthorized access.
  • Supports reading PDFs from both local files and public URLs.
  • Efficient text and metadata extraction using the pdf-parse library.
  • A single read_pdf tool for various extraction needs.
  • Easy integration with minimal configuration.
  • Available as a Docker image for consistent deployment.
  • Robust validation of incoming tool arguments using Zod schemas.

Use cases of PDF Reader MCP?

  1. Extracting metadata and page counts from multiple PDF files.
  2. Retrieving full text from a specific PDF document.
  3. Extracting text from specific pages of different PDF files.

FAQ from PDF Reader MCP?

  • Can PDF Reader MCP read all types of PDF files?

Yes! It can read both local and publicly accessible PDF files.

  • Is PDF Reader MCP easy to integrate into existing projects?

Yes! It is designed for easy integration with minimal setup required.

  • How does PDF Reader MCP ensure security?

It confines all local file operations to the project root directory, preventing unauthorized access.

Project Info
Created At
a year ago
Updated At
a year ago
Author Name
shtse8
Star
2
Language
TypeScript
License
MIT license

Recommend Servers

View All
Bring your real authenticated browser session to AI coding agents. Local-first MCP server + Chrome MV3 extension. No cloud. No telemetry.
@Cubenest

peek records the user's actual logged-in browser (DOM via rrweb, console events, network metadata, optional response bodies via opt-in Deep capture) through a Chrome MV3 extension. The extension ships events through a native-messaging stdio bridge to a local MCP server (peek-mcp), which persists them to a SQLite database at ~/.peek/sessions.db. AI coding agents (Claude Code, Cursor, Cline, Windsurf) read sessions from the database via 10 MCP tools: Tool What it does list_recent_sessions List recently recorded sessions (id, origin, ts, event count). get_session_summary LLM-readable narrative summary of a session. get_session_console_errors Console errors recorded in a session. get_session_network_errors Failed/notable network requests in a session. get_user_action_before_error Last N user actions before a console error. generate_playwright_repro Generate a runnable Playwright test from a session. get_dom_snapshot Reconstruct the DOM at a given timestamp. query_dom_history Timeline of attribute/text changes for a selector. request_authorization Side-panel consent for write actions (Level 3). execute_action Dispatch a UI action (gated by permission level + destructive blocklist). Why local-first matters Every other "browser session for AI" tool ships to a vendor cloud. peek's SQLite + extension live on the user's machine — no remote endpoints, no telemetry. The privacy policy (docs/peek/PRIVACY_POLICY.md) is the source of truth. Install # 1. Add the MCP server to Claude Code claude mcp add peek -- npx -y @peekdev/mcp # 2. Install the Chrome extension from the Chrome Web Store # (link added once the CWS listing is approved)

a day ago