"How to Use a Web Browser" matching MCP servers:

Enables coding agents to drive a real Chrome browser to complete natural-language web tasks and return evidence for verification.

Enables coding agents to query the dependency graph of a GitHub backlog, retrieve ordered ready work and prerequisite chains, atomically claim issues, and report blockers—so agents work in the correct order and safely in parallel.

Enables autonomous agents to anchor browser elements from vision inputs, providing stable DOM references resilient to click drift for reliable computer-use automation.

Enables AI agents to anchor visible on-screen elements to stable DOM targets, preventing click drift during browser computer-use automation.

Browser use using Typesafe's Jev model

Just to be clear about the final JSON: the MCP server is named herdr-inbox, and it enables Claude Code agents in herdr to ask questions asynchronously without stalling, with all open questions answered from one popup and answers routed back to the asking agent.

Enables AI assistants to control a web browser through Playwright-compatible tools, with an on-device decision engine for autonomous task completion and optional LLM escalation.

Enables coding agents to add a bounded semantic-judgment layer for routing, ranking, extraction, verification, and escalation, returning typed signals and review recommendations.

Enables AI agents to control a persistent Chrome browser through a local daemon, with Jev performing routine actions and the host agent handling reasoning, text, and verification.

Enables AI agents to autonomously operate web browsers through the Model Context Protocol, including navigating pages, clicking, typing, filling forms, and extracting structured data.

Enables browser automation through MCP clients like Claude or Cursor, using the client's existing LLM without requiring an additional API key.

Bridges Kimi Code CLI to OpenAI Computer Use, enabling Kimi to control local macOS applications via MCP.

Enables an LLM client to drive a real Playwright browser by stating one outcome at a time, with Typesafe System One deciding each round which element, action, and value to use, and returning a status such as done, blocked, or needs-confirmation. Also exposes tools for yes/no page checks, choosing among options, direct element actions without model calls, question-focused page reading, snapshots, screenshots, and invoking a page's own WebMCP tools.

A framework-agnostic computer-use MCP server that exposes core desktop operations (screen capture, mouse, keyboard, and file access) as standard MCP tools, enabling any MCP-compatible agent to drive a computer.

Enables MCP clients to run complete browser workflows through a single run_workflow tool, with anti-detection backends, intelligent element location, automatic retries, and session persistence.

Enables the Pi coding agent to drive Chrome through DevTools, providing browser automation tools, persistent or isolated profiles, screenshots, page analysis, and bundled agent policies.

Enables AI agents and MCP clients to translate high-level web automation goals into deterministic, resilient browser selector action sequences. It runs as a zero-dependency Python MCP server that returns structured execution plans and telemetry for agentic workflows.

Enables language models to control a real visible browser with a full set of 24 tools for navigation, clicking, form filling, screenshots, and reading page structure, while preserving login states and supporting configurable browser policies.

Enables autonomous web automation by flattening DOM trees into pruned accessibility trees, synthesizing robust CSS/XPath locators, and compiling goal-driven multi-step action plans with verification. It exposes these capabilities through MCP JSON-RPC tools for browser-oriented task execution.

This MCP server enables users to convert web page DOM structures into accessibility trees, filter non-interactive elements, generate robust CSS/XPath locators, and compile goal-driven multi-step browser automation plans with verification.