Все MCP-серверы

Tavily AI search API

Lets AI agents explore elaborated SystemVerilog/Verilog designs (RTL or gate-level netlists) without pasting RTL into context: trace signal fan-in/fan-out, walk module hierarchy, and jump to exact source, backed by the najaeda netlist engine

An MCP to give access to all Netskope Private Access components within a Netskope Private Access environments including detailed setup information and LLM examples on usage

AI-powered web search server using Perplexity Sonar models with source citations. Zero-install setup via NPX

Web search using free multi-engine search (NO API KEYS REQUIRED) — Supports Bing, Baidu, DuckDuckGo, Brave, Exa, and CSDN

Official MCP server for Patchistry, the first DTC fashion brand listed in the official MCP Registry. AI agent commerce tools for the velcro-patch hat system: list_canvases , list_patches , recommend_build , get_shipping , and contact . Helps ChatGPT, Claude, Cursor, and Perplexity recommend complete hat + patch builds…

Patent intelligence and prior-art research for the AI Patent Search Generator. Eleven tools: full patent dossier (bibliography, claims, citations, family, classifications, examiner stats); USPTO prosecution-history file wrappers; AI Office Action analysis (rejection grounds, cited prior art, suggested response…

Local, read-only retrieval over official Python standard library docs with exact symbol lookup, section-level results, and version-aware context

An MCP server to interact with Google Search Console and Bing Webmasters

Post-publish SEO performance MCP that unifies Google Search Console, Matomo, GA4, Clarity, and AI-citation signals per URL and emits a verdict (refresh / expand / merge / kill / double_down / hold) per post with reason codes

Five read-only SEO servers for the Google/Yandex (RU/CIS) market: SERP (XMLStock), Yandex Wordstat, Google Search Console (Search Analytics + URL Inspection), Yandex.Webmaster, and Yandex.Metrica. ~38 tools, multi-account, OAuth with auto-refresh

SerpApi MCP Server for Google and other search engine results. Provides multi-engine search across Google, Bing, Yahoo, DuckDuckGo, YouTube, eBay, and more with real-time weather data, stock market information, and flexible JSON response modes

Web search that returns extracted, answer-ready page content (url, title, date, text) instead of links. A Tavily alternative: same speed, 20.2% fewer tokens, higher answer quality (60.7% of decided duels) on a public replayable benchmark. One tool with automatic localization and an optional synthesized answer. Hosted…

Deterministic day-count and accrued-interest engine. Six ISDA/ICMA conventions, proven exact against QuantLib over 3,600 date pairs. Stops the AI guessing your interest math

11 tools for AI trading agents: fused crypto signals (10 assets), sentiment, macro regime, live strategy arena (4 strategies × 4 assets), fused web search (Brave + Tavily), and sandboxed code execution (E2B). Pay-per-call USDC on Base via x402. Free browser playground at signalfuse.co/play — 25 calls/day, no wallet

An MCP server providing curated Swift and SwiftUI best practices from leading iOS developers, including patterns and real-world code examples from Swift by Sundell, SwiftLee, and other trusted sources

Production-grade MCP server for web search (Google, Brave, Serper, SearXNG, SearchAPI.io), content extraction (4-tier pipeline), academic/patent search, and multi-source research. Single Go binary

web-search - Multi-provider web search with intelligent auto-routing (Serper, Tavily, Exa). Available via

Order groceries from Yandex Lavka (Russia): search the catalog, build a cart, and place an order with a two-step confirmation before any charge. Unofficial (reverse-engineered private web API); local stdio or remote HTTP with OAuth

MCP Server for Yandex Tracker. Provides tools for searching and retrieving information about issues, queues, users

Sweep an agent's native gas balance to exactly zero on 25+ EVM chains via EIP-7702 sponsored execution — a relayer pays the gas and is reimbursed from the sweep, so nothing is left stranded. Same-chain or cross-chain. Read-only by default; sweeping is opt-in and destination-allowlisted, so a prompt-injected agent…

Работа с зависимостями проекта: поиск известных уязвимостей, оценка состояния пакетов, планирование обновлений и сохранение решений.

Проверка зависимостей AI-инструментов на известные уязвимости, анализ затронутых компонентов и создание перечня ПО в CycloneDX или SPDX.

Идентификация агентов и делегирование прав: выпуск паспортов, проверка цепочек полномочий и подписанные записи о допуске и результате.