"Optimizing AI Model Thinking, Token Usage, and Context Size" matching MCP servers:

Provides Claude plan usage data (session and weekly percentages) as an MCP tool by reading through a logged-in browser, enabling Claude to check its own remaining usage.

A local MCP proxy that strips web pages to clean text, reducing token usage for AI agents by up to 99.6%.

Provides live web and document intelligence, including search, company news, scraping, crawling, structured extraction, document parsing, brand intelligence, screenshots, website monitoring, and batch jobs.

Local-first documentation for AI agents

Enables MCP clients to look up domains, URLs, IPs/ASNs, email addresses, phone numbers, crypto wallets, and business records; run autonomous investigations; collect crawl artifacts; and perform evidence-backed scam checks with traceable provenance.

Classifies company sites as B2B or B2C and as SaaS, online store, agency, manufacturer, wholesaler, distributor, or marketplace, while matching your own buyer phrases and returning the quoted text and page as evidence. Runs deterministically on Apify, giving one row per domain with grace-free status rows for unreachable, blocked, or empty sites.

An MCP server that fetches web pages and extracts clean, AI-usable context from them, enabling tools for link discovery, content search, and integrated fetch-and-search operations.

Enables AI assistants to summarize, take notes on, and answer questions about YouTube, Bilibili, and Xiaohongshu videos by providing subtitles and local speech transcription with timestamps via MCP.

Analyze and generate robots.txt files with AI crawler awareness. Fetch any site's robots.txt, detect which AI bots (GPTBot, ClaudeBot, PerplexityBot, Google-Extended) are blocked or allowed, and generate optimized robots.txt with toggle controls for 20+ AI crawlers.

Checks a site for AI crawlers: which of 11 AI crawlers its robots.txt lets in, whether its llms.txt follows llmstxt.org, and what its home page says without scripts. Findings with evidence; no scores, no model calls, no telemetry.

Interact with WebScraping.AI API for web data extraction and scraping

Fetches and caches public site pages from llms.txt and returns structured answers with source URLs, enabling verification of claims against live public content.

Minimizes LLM token consumption via YAML serialization, HTML-to-Markdown distillation, and pre-flight token counting, with tools for web content extraction and metrics database querying.

Provides read-only MCP tools to search YouTube, retrieve video metadata, transcripts, comments, channel information, and popular videos.

Transforms social media links (TikTok, Instagram, YouTube) and videos into text context with transcription, OCR, and metadata for AI agents like Claude and Cursor.

Enables AI agents to fully control a terminal browser via MCP, navigating pages, filling forms, logging in, and managing cookies with deterministic numbered links and forms. Also provides an interactive human CLI.

A read-only MCP server that gives AI agents the web as compact, ranked, verified evidence — no API keys, no cloud retrieval, all models local.

AI text and URL summarizer that extracts key points, reduces word count, and estimates reading time, with pay-per-call via x402 micropayments.

An MCP server for lightweight browser automation using Lightpanda with Chrome fallback, providing LLM-optimized accessibility tree snapshots for precise element targeting.

Enables local Chrome control for AI clients over MCP stdio, HTTP, or CLI, exposing 20 tools to extract page text, number and click elements, type text, scroll, manage tabs, capture screenshots, and bind uploaded files to file inputs. Operations run entirely on the local machine with origin allowlists and refusal of untrusted URLs, without calling a cloud model or consuming model tokens.

Enables AI agents to search and browse comics, query rankings, album details and comments, manage favorites, and run asynchronous downloads of albums, chapters or covers with live progress tracking and post-processing into ZIP, PDF or long-image formats. It also exposes configuration, login and diagnostic capabilities plus knowledge resources, over stdio, SSE or HTTP transports.

Enables AI agents to search, filter, browse rankings, read comments, manage favorites, and download manga albums or chapters, then convert them to ZIP, PDF, or long images. Also supports download task planning, progress tracking, cancellation and retries, runtime configuration changes, account login, and API access over stdio, SSE, or HTTP transports.

Enables AI agents to search, browse rankings, view album details and comments, manage favorites, and download manga albums or individual chapters asynchronously with progress tracking, cancellation, and retry. Also supports post-processing downloads into ZIP/PDF/long images, dynamic configuration updates, account login with cookie persistence, and access to schema/reference knowledge resources over stdio, SSE, and HTTP transports.

Enables AI agents to search, browse, download, organize, and post-process comics through MCP tools, including account login, favorites, comments, rankings, configuration, and download task control. Supports stdio, SSE, and HTTP transports while exposing knowledge resources for configuration and skill reference.

Enables AI agents to search and browse manga, inspect album details, comments and rankings, manage favorites, and download albums, chapters, and covers with progress reporting, cancellation, retry, and batch task control. Also supports post-processing downloads into ZIP, PDF, or long images and dynamic runtime configuration, exposed as MCP tools and knowledge resources over stdio, SSE, and HTTP transports.

Enables AI agents to search, browse, download, favorite, comment on, and post-process comic albums via standardized MCP tools, with asynchronous download tasks, progress tracking, cancellation/retry, runtime configuration, and account login.

Exposes MCP tools that let AI agents search, browse rankings, view album details and comments, manage favorites, and download or post-process manga into ZIP, PDF, or long-image formats. It also covers runtime configuration, account login with cookie persistence, and background task control with progress tracking, cancellation, and retries.

Enables AI agents to search, browse, and download comic albums, manage favorites and comments, control download tasks, perform ZIP/PDF/long-image post-processing, and adjust runtime configuration through MCP tools and knowledge resources.

Enables AI agents to search, browse, download, post-process, and manage comic albums, comments, favorites, rankings, and account sessions through standardized MCP tools and resources.

Enables AI agents to search, browse, and retrieve comic details, comments, rankings, and favorites; download albums, photos, and covers with task control; and post-process downloads into ZIP, PDF, or long images.