"Actual Budget" matching MCP servers:

Enables Claude Code to control your actual logged-in Chrome browser through an MV3 extension, perceiving pages as element tables and performing actions such as navigation, clicks, typing, and assertions via CDP.

Lets Claude join a real match of the shooting game as the second player and play it through a live browser, reading the arena and sending actual keyboard inputs to move and shoot.

Enables production-grade web research through MCP, combining local SearXNG search with hosted fallback providers, fetch and crawl tools, summarization, and budget guardrails.

Drives your real local Chrome with profile isolation, allowing LLMs to interact with your logged-in sessions without modifying your actual profile.

One endpoint, five search providers. Search broker for AI agents with automatic fallback, RRF ranking, and budget enforcement. The LiteLLM of web search.

Enables runtime CSS inspection of live web pages, providing computed styles, ASCII layout diagrams, overflow and scroll findings, plus browser interactions like screenshots, JavaScript evaluation, and CSS injection to debug actual rendering.

Enables AI assistants to control and inspect the user's actual Chrome browser via MCP, preserving login sessions and isolating agent tasks in background tab groups without disrupting the user's workflow.

MCP server for the MiroMiro design-extraction API. It extracts real design data from live websites—including brand colors, fonts, tokens, SVGs, images, and component code—so AI agents can build from actual values.

An MCP server that provides browser-grade web access for AI agents, using Chrome's actual network stack to bypass anti-bot protections and return clean markdown.

Bridges AI agents to a real browser using a persistent daemon and Chrome extension for driving actual login sessions, cookies, and tabs.

Enables querying Medium content through the unofficial medium2 RapidAPI, including user, article, publication, tag, and search operations, with a strict monthly budget guard and full-text content opt-in controls.

Enables LLM agents to search the web and fetch pages as clean, budget-controlled text through MCP tools.

Bridges Model Context Protocol clients to your actual Chromium browser, enabling control of tabs, reading authenticated pages, cookies, and storage, and running JavaScript on approved sites. Emphasizes security with per-site approval, high-risk action confirmations (including Touch ID on macOS), and an attested native-messaging bridge.

Give your AI coding assistant live visibility into the user's browser. Claude sees the actual DOM, console errors, and network timing instead of guessing from screenshots. Drop-in middleware for FastAPI + Flask.

Enables PraisonAI agents to solve authorized CAPTCHA challenges with a bounded one-attempt budget, structured result validation, and a human-review stop for denied, unsupported, exhausted, or malformed requests.

Enables searching tours on eto.travel using browser automation via Playwright. Supports finding a single tour or a categorized selection (budget, optimal, premium) based on filters like destination, departure city, nights, and month.

Screen-reader navigation cost analyzer. Measures how hard it is for assistive-technology users to discover, reach, and operate interactive targets on the web.

Enables AI assistants to drive a Google Flow web workspace through local login-session reuse: inspecting the account's actual models and parameters, submitting image and video generation jobs, tracking each job by persistent ID, and downloading the matching media to a specified local path with file and parameter records. Supports repeatable, multi-shot video production workflows where tracked assets are handed off to editing tools like FFmpeg.

Enables coding agents to see the UI they just changed without flooding their context window, returning a structured text summary (console errors, failed requests, overflow, layout shifts, accessibility violations) plus small crops of only the regions that changed since the last capture. All output is fitted into a chosen token budget, with captures stored on disk and evicted automatically.

An MCP server that lets AI agents read and manage Telegram Ads campaigns, including listing accounts and ads, reading stats and budgets, and creating/updating ads, CPM, status, and budget by driving the real ads.telegram.org web UI through Playwright with a reused cookie-based login session.