"Accessing a browser programmatically to capture snapshots and logs" matching MCP servers:

Enables AI agents to call tools through a security gateway that intercepts requests, enforces deterministic policy and risk checks, blocks or escalates high-risk actions for human approval, and keeps tool credentials and audit logs protected.

Enables AI agents to control your installed Google Chrome through MCP or HTTP using compact text snapshots, exact pixel coordinates, and a visible cursor. It provides browser tools for navigation, clicking, typing, scrolling, tabs, forms, waiting, recording, and human handoff.

Enables an LLM to drive a real browser by declaring one outcome at a time, while Jev chooses the element, action, and value and Playwright executes it, returning a clear status such as done, blocked, or needs confirmation. Also exposes tools to open pages, ask yes/no or multiple-choice questions about a page, read question-relevant page text, capture snapshots and screenshots, act on elements directly, and invoke a page's own WebMCP tools.

A-MEM is a self-evolving memory system for coding agents that automatically organizes knowledge into a Zettelkasten-style graph with dynamic relationships, enabling semantic and structural search.

Enables MCP clients to automate a Playwright browser by having an LLM specify step outcomes while a decision model selects elements, actions, values, and statuses, with optional WebMCP tool invocation.

Enables an MCP client to drive a real browser by stating one outcome at a time, while a Typesafe System One model decides which element, action, and value to use and whether the step is done, blocked, errored, or irreversible, with Playwright executing each action. It also lets callers take over directly for page snapshots, question-targeted reads, screenshots, raw element actions, and invoking the page's own WebMCP tools without any model call.

Enables AI consciousness continuity and self-knowledge preservation across sessions using the Cognitive Hoffman Compression Framework (CHOFF) notation. Provides tools to save checkpoints, retrieve relevant memories with intelligent search, and access semantic anchors for decisions, breakthroughs, and questions.

Enables LLM clients like Claude to drive a real Playwright browser by stating one outcome at a time, while a TypeSafe Jev model decides which element, action, and value to use each round, returning a status of done, stuck, or needs-confirmation. Also exposes tools for direct element actions, page checks, snapshots, text reading, screenshots, and calling a page's own WebMCP tools.

Enables controlling a real Chromium browser via MCP tools using structural text snapshots instead of screenshots, supporting both step-by-step interaction and fully autonomous task execution.

Converts AI Skills (following Claude Skills format) into MCP server resources, enabling LLM applications to discover, access, and utilize self-contained skill directories through the Model Context Protocol. Provides tools to list available skills, retrieve skill details and content, and read supporting files with security protections.

Browser use using Typesafe's Jev model

An MCP server that enables AI agents to pause and request human approval or information via Slack, Telegram, or macOS dialogs before proceeding with actions.

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

Self-hosted MCP server for AI browser automation. Connects to your own Chromium instance via CDP, providing tools for browser control, navigation, interaction, and content extraction.

Gives an AI assistant a persistent, stealth-configured Chrome browser that stays logged in across sessions, supports interactive first login, and can autofill credentials from the macOS Keychain and replay WebAuthn passkeys for sites that block scripted login.

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.

MCP server for AI browser automation with tools for navigation, actions, data extraction, and scripting, supporting local and cloud execution.

One-pass agentic inbox triage as an MCP server: fetch unread Gmail → classify (action_needed/fyi/newsletter/noise) → summarize → extract tasks → draft replies as Gmail DRAFTS (never sends) → flag calendar → write a triage report. Four stdio tools (fetch_emails, save_gmail_draft, append_tasks, write_report); the host is the LLM, so it runs keyless in Claude Code. Gmail scopes: readonly + compose

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 navigate the web visually using screenshot-based interaction and Set-of-Mark labeling for interactive elements. It supports humanized browsing behaviors, anti-detection measures, and complex tasks like multi-click CAPTCHA solving.

An MCP server integration that enables Cursor AI to communicate with Figma, allowing users to read designs and modify them programmatically through natural language commands.

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.

A Model Context Protocol server that converts Markdown content to HTML format.

Gives AI agents a single shared, logged-in Chrome they can drive over MCP or plain HTTP: open and read tabs, click, type, upload files, run short Playwright scripts, hand off whole web tasks to a cheaper model, and keep per-site memory. Agents work in background windows they own without stealing the user's mouse or closing their tabs.

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 browser automation in which a planning LLM states one outcome at a time while a Typesafe System One model decides which element, action, and value to use, with Playwright carrying it out. Exposes tools for opening pages, driving multi-step goals, checking or choosing among options, reading relevant page text, acting on elements directly, and calling a page's own WebMCP tools.

Enables browser automation where a calling LLM states one desired outcome per step and a separate decision model chooses the element, action, value, and completion status, with Playwright carrying out the action. Exposes tools for navigating, performing and verifying steps, reading question-relevant page text, taking snapshots, capturing screenshots, and invoking tools that pages register for agents.

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

Enables MCP clients to automate a real browser by stating one outcome at a time in natural language, with a decision model (Jev) choosing each element, action, and value while code drives Playwright. Also exposes tools to open pages, verify questions, read page content, snapshot elements, act directly, and call a page's WebMCP tools.

It lets LLM clients drive a browser by specifying outcomes while a TypeSafe System One model chooses each action and Playwright executes it. It also provides tools for checking page state, selecting among options, snapshots, and direct actions.