"Exploring Memory Persistence in DeepSeek Technology" matching MCP servers:

Enables MCP-capable AI clients to run web searches through DeepSeek's search engine and fetch individual webpages as Markdown. Search results include relevance scores, authority, and publication times, and support advanced query syntax such as site:, lang:, and date filters.

Enables MCP clients to run web searches and fetch individual web pages as Markdown through DeepSeek's official Search/Fetch API, with freshness filtering, structured metadata such as publish date, authority and rerank scores, and raw structured output.

Enables any MCP client to drive the user's real Chrome profile through a Chrome extension bridge, with tools for navigation, accessibility snapshots, ref-based interactions, console/network reading, screenshots, tab management, and restricted script evaluation.

Enables AI agents to perform web search, page fetching, and multi-source research via the official search and fetch API, with deduplication, content limits, caching, and rate limiting.

Enables AI agents to perform real-time web search and fetch/parse webpages into clean Markdown through DeepSeek's Search and Fetch APIs. It provides configurable summaries, scoring, and robust retries for integration with MCP-compatible assistants.

Enables MCP clients to run web searches that return ranked results with titles, URLs, snippets, summaries, and optional extracted page content, and to fetch HTTP or HTTPS pages as Markdown. It runs over stdio as a zero-dependency Python server that uses DeepSeek's official APIs and any supported MCP client.

Enables MCP-compatible clients to search the web and fetch HTTP/HTTPS pages as Markdown, returning result metadata such as titles, URLs, dates, relevance, and summaries.

It enables AI agents to perform real-time web searches and fetch webpages as Markdown through stdio-exposed tools.

Exposes token-authenticated search and fetch tools over Streamable HTTP so MCP clients can run web queries and retrieve page content from an upstream search API. It adds per-profile Bearer auth, concurrency and rate limits, request-size and output caps, and sanitized errors, while requiring no model calls or client-specified upstream addresses.

DREAM LAUNCHERS INTERIORS PRIVATE LIMITED

Enables following a creator's bio link to detect their newsletter, products sold, and contact emails across supported platforms and link-in-bio pages.

Enables AI assistants to access PSG College of Technology e-campus portal data including CA marks, attendance records, timetable schedules, and course information through natural language queries.

DocPull v6 is a local-first MCP server that turns public web sources into cited, versioned context packs for AI agents, RAG systems, and developer workflows. It can fetch and sync public static and server-rendered sources such as changelogs, standards, API references, OpenAPI specs, feeds, repo/package metadata, papers, filings, pricing pages, blogs, and other web sources.

Enables any MCP host to search and retrieve public job postings from builtin.com through standard search_jobs and get_job tools, returning normalized details like title, company, location, apply URL, and remote status.

Enables Claude Code to drive your everyday logged-in browser session — opening and closing tabs, navigating, clicking, typing, scrolling, filling forms, uploading files, taking screenshots, and reading page text, console output and network requests. It runs through a local native-messaging bridge, scoping each client session to its own window behind yours.

Enables DeepSeek Harness to run seller analytics and local Wildberries/Ozon marketplace tools — such as product search, data export and XLSX delivery — through an account login and browser extension, with per-job authorization of each tool call.

Enables users to turn keywords or social media handles into finished influencer lead lists with contact details, using the Apify actor.

MCP server that exposes Abrasio as an agentic browser for AI models, allowing Claude, Cursor, and other MCP-compatible AIs to control a real web browser with anti-detection fingerprinting.

Enables searching products, viewing orders, and analyzing order trends on Amazon.in via a persistent Playwright browser session.

Provides web search and content retrieval optimized for AI coding assistants, returning full conversations and structured content from StackOverflow, GitHub Issues, arXiv, and Wikipedia in a single call.

Provides source-traceable live web search and URL extraction through Brave and Tavily, with provider status, health checks, fallback notices, and optional TaroCub guidance.

Enables agents to run web searches and fetch webpages through native Search/Fetch APIs, returning structured JSON or Markdown while applying local validation and rate limiting.

A minimal MCP server that crawls web pages using crawl4ai and returns content as markdown, deployable to Cloud Run.

Investigate any website's technology stack: CMS, eCommerce, frameworks, analytics, CRM, payments, and hosting behind any URL.

MCP server for searching Fiverr gigs, comparing freelancer packages, reading seller reviews, and exploring service categories. Provides structured tools for gig search, details, seller profiles, reviews, and category browsing with built-in anti-bot handling.

MCP server providing web search, page opening, and text finding tools for DeepSeek Harness, using DuckDuckGo first with Bing fallback and quality scoring.

Detects a company's technology stack from its public web presence. Returns structured tech signals for sales targeting and competitive analysis.

Enables live architectural reference research through OfficeNext by searching projects, reading authorship and source excerpts, and viewing selected project images in memory without creating a local content database or image archive.

Enables read-only access to Turkish technology news and forum content, including latest articles, keyword search, full article text, section listings, and current hot forum topics.

Enables AI assistants to load Pakistan Stock Exchange data such as prices, screener metrics, index constituents, sectors, filings, debt market instruments, and margin-eligible scrips into a private in-memory DuckDB. It then lets them answer natural-language questions by running constrained SQL queries over the loaded tables.