"memory" matching MCP servers:

Enables agents to distill web pages into facts with citations, remember and recall project memory, and manage API keys and usage via MCP tools.

MCP server providing browser automation for AI agents, enabling actions like clicking and typing, structured data extraction, content validation, multi-step task execution, and memory enrichment from web pages.

Gives AI coding agents live, cached access to current Flutter, Dart SDK and pub.dev documentation returned as clean markdown, resolving class names, identifiers and packages on demand instead of relying on a model's memory. Also provides ranked name search over thousands of classes and a politeness layer with robots.txt compliance, throttling, conditional GETs and request budgets.

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 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.

Enables AI agents to access pay-per-call web unlocking, structured extraction, clean scraping, Python sandbox execution, persistent key-value memory, and clearinghouse task bounties, with settlement via Bitcoin Lightning L402 or Base/Solana USDC x402.

MCP server for fetching, parsing, and managing RSS feeds. Features Fetch and parse RSS/Atom feeds In-memory caching with TTL Batch fetching of multiple feeds Monitor feeds for new items Search content across multiple feeds Extract and format feed content

Enables intelligent web document scraping and conversation memory management for Cursor IDE. Supports multi-level link crawling, automatic content extraction, and organized storage of conversations and technical documentation.

An MCP server based on Puppeteer and Chrome DevTools Protocol for advanced browser debugging, performance analysis, and memory detection. It enables users to inspect DOM elements, monitor console errors, capture screenshots, and perform heap snapshot analysis through persistent browser connections.

A Chrome DevTools Protocol MCP server that enables direct browser automation with auto-discovery of interactive elements, built-in action verification, and persistent site memory across sessions.

An MCP server for deep research that performs search, scraping, synthesis, fact-checking, and persistent memory, enabling users to conduct comprehensive research tasks via Claude.

Enables MCP clients to access Toolhouse's extensive library of tools, allowing AI assistants to perform actions like web scraping, memory management, and email sending through natural language commands.

Provides 20 essential tools including HTTP requests, web search, file I/O, shell commands, and persistent memory for any MCP client, with zero configuration required.

Enables searching onion services through multiple search adapters and reading pages over Tor, with tools for fetching, status checks, link extraction, and Tor health plus content filtering and in-memory caches.

Fetches webpages—and optionally crawls linked pages up to a configurable depth—then strips noise and converts the content into clean, token-efficient Markdown with links preserved. It caches results, respects robots.txt, and streams content for low memory use, making it suited for feeding AI agents, IDEs, and LLM pipelines readable web content.

MCP server for Lightpanda headless browser enabling ultra-fast HTML extraction, markdown conversion, and JavaScript execution with 16x lower memory footprint than Chrome.

A local-first personal AI agent infrastructure that extends Claude Desktop with tools for Google services, web scraping, local memory, knowledge upload, and dynamic workflows via MCP.

Fetches web pages locally, strips noise, and converts them into clean, link-preserving Markdown so AI agents and IDE clients can crawl and extract web content with minimal token and memory overhead.

Mounts a headless, low-memory browser for agents with a text-first tool interface, enabling navigation, semantic tree/markdown extraction, structured-data scraping, screenshots, form interaction, and session capture. Reads and interactions are returned as semantic trees, markdown, or CSS-selector JSON rather than pixels, which is cheaper for a model to reason over.

250+ AI-powered MCP tools: research, write, code, translate, scrape, sentiment, vision, RAG, agent memory, marketplace, trading signals, and more. 15 models across 7 providers. Pay-per-use via API key or x402 USDC micropayments.