"Adding web browsing and page reading capabilities to an agent" matching MCP servers:

Enables document conversion between PDF, DOCX, and Markdown formats to facilitate reading and editing complex files in AI tools like Claude Desktop or Cursor. It utilizes marker-pdf and pandoc to provide structured text versions of documents, helping to manage context and support unsupported file types.

Fetches a URL and returns the main content as clean Markdown, using plain HTTP when possible and headless Chromium for JavaScript-rendered or bot-protected pages.

Enables building and evaluating LangGraph agents over a protocol-level MCP server to measure failure rates across four agent topologies.

Enables ChatGPT web to use local tools like file reading, command execution, and patch application through an MCP server over OpenAI Secure MCP Tunnel.

Enables local EPUB reading with AI agents, supporting annotations, parallel editions, and MCP tools.

Enables an agent to run ten ready-made research and monitoring workflows — competitor digests, cited reports, paper alerts, market maps, regulatory and due-diligence watches — pulling from Firecrawl, Tavily, GitHub and landing results in Notion, Slack, Google Docs, Sheets and Linear. Fields are filed with the user's own keys held in the operating system keychain, and every action that creates, sends or changes anything is shown and approved first.

A 4-stage reading companion that helps users set reading goals, discover books, track progress, and deepen learning through reflection, integrated with Claude Desktop.

A mobile-first AI co-reading MCP server that lets users import novels or comics, sync reading progress with AI, and interact through comments, bookmarks, and notes.

Enables Claude Code or Codex CLI to see the exact sentence and section you are viewing in Chrome, so you can discuss books with context, take notes, and track reading progress.

Provides a hand-written MCP server integrated with a LangGraph agent to benchmark multiple agent topologies and measure their failure rates.

Enables AI agents to control a real browser via MCP tools for web navigation, interaction, page inspection, tabs, forms, files, sessions, and browser automation.

A minimal MCP server with get_weather and create_ticket tools, used for testing MCP servers across protocol, unit, eval, transport, and auth layers.

Converts URLs into clean, LLM-ready markdown, respecting robots.txt and never bypassing anti-bot measures or paywalls.

Drop a single script into a web UI and the page itself exposes DOM inspection, interaction, and diagnostic devtools to coding agents through document.modelContext, with no server, LLM, or chat UI involved. It also lets an app register its own domain-state tools, so agents can reach state that the DOM cannot reveal.

An MCP server that enables a private mobile-first reading experience in ChatGPT, managing multi-book shelves, reading progress, highlights, thoughts, and bookmarks, with secure cloud storage and AI co-reading of the current page.

Enables shared reading between humans and AI assistants, including book import, chunked reading, margin annotations, reading progress tracking, and note exchange.

MCP server for the Agent Web Combo toolkit, enabling AI agents to perform multi-source web search, page content extraction, and JavaScript-rendered page screenshotting via Kitesurf/Playwright, with optional agent-reach platform integration.

An AI reading companion that curates next books based on the Chicago Plan curriculum and tracks user reading progress with personal tokens. It offers book recommendations, logging, coaching questions, and reading reports.

An MCP server enabling AI agents to access the internet via web scraping, crawling, searching, and structured data extraction using Firecrawl.

Enables MCP-compatible agents to perform web searches via the agent-web-search engine, returning ranked results with sources.