"How to work with local files" matching MCP servers:

Fetches a URL and returns the main content as clean Markdown, using plain HTTP when possible and headless Chromium for JavaScript-rendered or bot-protected pages.

Enables Claude to fetch web pages from the user's own local network connection instead of AI datacenter IPs, including optional authenticated sessions, with verdicts for bot challenges, login walls, and other failures.

Web search, crawling and ranking evaluation on your own YaCy peer: no API key, no central service. Results carry author-signature verdicts and declared tags.

Enables users to look up any company's Google advertising by domain or verified advertiser name, returning one row per ad with its format, first and last shown dates, creative link, and Transparency Center permalink. Also returns a per-company summary stating whether the advertiser runs Google ads, roughly how many, and in which formats, with unfiltered by region, format, recency, or ad count.

Provides persistent browser tabs with tools to read, click, type, and interact with web pages, enabling local LLM agents to perform multi-step web tasks.

MCP server for video analysis — extracts transcripts, key frames with OCR, and annotated timelines from video URLs. Supports Loom and direct video files (.mp4, .webm). Zero auth required.

MCP server that converts web page URLs to Markdown via the Zyla API.

Enables resolving the likely employer behind Gmail, Outlook, iCloud, Yahoo, and other free-mail signups by checking public Gravatar profiles, signed GitHub commits, and LinkedIn results. It returns the person’s name, employer, employer domain, confidence score, and evidence URLs.

Offline-first MCP server for TwitterAPI.io docs (endpoints, pages, blogs) with fast fuzzy search.

Enables users to check Google organic, map pack, and local finder positions for keywords across specified locations, returning per keyword/location rows with ratings, competitors, and rank changes. It runs searches from each location via Apify and can track history with a state key.

Enables assembling local business prospect lists from Google Maps searches by category and place, returning one row per business with website, phone, address, coordinates, categories, rating, review count, and weekly hours. Supports filters for minimum rating, review count, website, and phone, plus URL and category-plus-location queries, deduplication across searches, and Clay-ready output via Apify.

Enables natural-language search and retrieval of Taiwan 104 job bank listings, including job details and company-specific openings, with filters for location, salary, experience, and remote work through an MCP interface.

Provides local LLMs with web search and page fetching capabilities via MCP, with a focus on OWASP security best practices.

Give it a product and a country and it searches Google for manufacturers, wholesalers, and distributors, reads each candidate company's own website, and returns only the ones whose pages back up the claim, with quoted evidence, the domain, and a confidence score. Directories, marketplaces, and social networks are filtered out, and a free summary row reports how many sites were found and checked when nothing qualifies.

An MCP server for integrating with the Brave Search API, and it supports HTTP proxying.

A basic MCP server setup guide demonstrating how to configure and run Python-based MCP servers with integration examples for Bright Data web scraping and Apify Actors for product data collection.

Exposes three read-only MCP tools that let an assistant check whether specified AI crawlers are allowed by a site's robots.txt and how a URL responds when fetched with each bot's user-agent, fetch a page as a single named bot, and generate a robots.txt that welcomes AI crawlers.

Enables authenticated access to Yonsei LearnUs course activities, assignments, schedules, announcements, notifications, video learning status, and course materials through local stdio tools.

Enables any MCP client to run keyless multi-engine web searches with RRF fusion, fetch pages and documents as Markdown, and full-text search a local SQLite index. It keeps queries and cached content on the user's machine, degrading gracefully across engine tiers when providers are blocked or rate-limited.

MCP server for the OpenGraph.io API -- extract OG metadata, capture screenshots, scrape pages, query sites with AI, and generate branded images with iterative refinement.

Turns public websites into portable SKILL.md files via MCP using Firecrawl.

Enables reading Y Combinator's Work at a Startup job postings and company details through a logged-in session, providing structured data to AI assistants.

Enables converting a public release-note URL into ordered upgrade tasks with source excerpts, anchors, confidence, and uncertainty, without executing release text or project code.

A Model Context Protocol server that enables LLMs to retrieve web content and save it to local files for permanent storage and later access.

MCP server for fetching daily hot lists from 30+ sources with built-in caching and batch requests.

42 local SEO tools for AI assistants. SERP tracking, Google Business Profile data, review monitoring, keyword research, AI visibility scoring, geogrid rank scans, citation audits, and competitive analysis.

Enables MCP-capable agents to fetch public pages, extract business signals and FAQ content, score a local business's web presence from 0-10, and generate a sales-ready audit with ranked gaps and a recommended offer.

Enables AI agents and compatible MCP clients to fetch, search, and download web content—including .onion services—anonymously through the Tor network, using a fresh circuit per call and retrying when exit nodes are blocked.

Companion to Prerender Buddy's AI visibility and website improvement platform. Three public tools inspect crawler-readable HTTP responses and discovery files without a key. Local installations can use scoped PB keys for workspace evidence and, with content-write permission, article drafts for review.

Enables agents to fetch a public web page or WeChat article in one call and receive complete Markdown, locally saved images, JSON metadata, offline HTML, and optional PDF, with paginated continuation when output is truncated.