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

Created By
sylphlaba 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 Docker, ensuring the project root directory is set correctly 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 processing 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. Reading full text from a 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 any PDF file accessible via local paths or public URLs.

  • Is PDF Reader MCP free to use?

Yes! PDF Reader MCP is open-source and free to use.

  • 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
sylphlab
Star
12
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