"Connecting Feishu (Lark)" matching MCP servers:

Gives Claude a browser that thinks by connecting to Perplexity's Comet browser via Chrome DevTools Protocol, enabling AI-powered web search, navigation, reading, clicking, and screenshots while keeping Claude's context clean.

Enables browser automation through Playwright using accessibility tree snapshots instead of screenshots. Supports web scraping, form interactions, testing, and connecting to existing browser sessions with logged-in accounts.

A Model Context Protocol server that enables AI assistants to perform web automation tasks by connecting to remote Playwright/browserless instances, supporting navigation, screenshots, HTML extraction, and element interaction.

An MCP server that enables AI agents to control a real Chrome browser with full login state through 37 structured automation tools, connecting via the Playwriter extension without needing a remote debugging port.

Provides web scraping, crawling, and site mapping capabilities by connecting directly to a self-hosted Firecrawl instance. It enables users to extract website content in markdown format and manage crawling jobs without an external API key.

Enables LLMs to perform browser automation through the Playwright framework with Chrome DevTools Protocol support, connecting to existing Chrome instances for advanced web interactions and JavaScript execution.

MCP server for combined multi-portal job search, connecting StepStone, Arbeitnow, Remotive, and We Work Remotely, with robust error isolation and markdown reports. It respects portal restrictions and avoids scraping protected services.

A Model Context Protocol server that exposes DuckDuckGo web and image search to MCP clients.

Uindow ships a local MCP server (npx -y @uindow/cli mcp, stdio) that lets Claude, Cursor, VS Code, or any MCP client drive a real signed Chromium/Electron browser with genuine OS-level input. Tools exposed: app_docs, app_start, app_stop, app_status, list, create, update, delete, start, stop, status, execute, logs.

Enables proactive company exposure research by searching onion pages through Tor and permitted Telegram channels, fetching matching content with source links and timestamps, and inspecting early warning signals such as targeting, exposed information, alleged data sales, and threat activity. The same tools can be called repeatedly by monitoring agents or scheduled workflows to compare new or changed evidence.

Enables agents to transform tabular Markdown content into structured, type-inferred records with normalized formatting through an MCP-compatible interface.

Enables autonomous web form inspection and schema auto-mapping by matching input attributes, autocomplete hints, and regex validations to agent state, while also pruning DOMs and converting tables into structured JSON for web agents.

Enables autonomous web agents to prune raw HTML into accessibility-friendly semantic trees with 80%+ token reduction, auto-map form input schemas, convert HTML/Markdown tables into type-inferred JSON records, and score agent execution trajectories. Runs as a zero-dependency, stdlib-only MCP stdio server for Claude Desktop, Cursor, and Windsurf.

Enables autonomous web agents to canonicalize URLs, detect anti-crawler traps such as circular paths and infinite pagination, prune DOM tokens, auto-map forms, transform tables into JSON, and evaluate action trajectories through MCP.

Enables AI agents and MCP clients to fetch web pages and distill them into clean, token-efficient markdown by stripping cookie banners, navigation bars, and ads. Runs with zero external dependencies over JSON-RPC stdio, delivering deterministic sub-millisecond results without LLM round-trips.