Коннекторы: Открытые данные
37 готовых коннекторов в категории «Открытые данные» — всего 430 MCP-инструментов: Twilio Segment, Firecrawl, Hugging Face. Вставьте учётные данные, и агент сможет их вызывать. Писать MCP-сервер не нужно.
Let your AI use Google Gemini with your own API key: ask Gemini models questions, analyse images and PDFs from a link, count tokens, create embeddings, and generate or edit pictures with Nano Banana that appear right in the chat.
Fast, cheap yes/no, classification and rating decisions for AI agents with Jev, TypeSafe's System One model: typed answers with calibrated probabilities in about 300 ms, instead of a paragraph to parse.
Let your AI use the OpenAI API with your own key: ask GPT models through the Responses API, analyse pictures from a link, generate and edit images that appear right in the chat, create embeddings, check content with moderation, and read models, files and batch jobs.
Find and run Apify's ready-made scrapers for search engines, maps, social media and online shops, and pull their results into Claude, ChatGPT or Copilot through Apify's official MCP server.
Read Hacker News (stories, comments, users, top/new/best/ask/show/job lists) from any AI agent via the official Firebase API. 8 tools, no auth.
Let your AI create images and videos on Higgsfield with your own API key: SOUL portraits, Marketing Studio and Ads Studio product images, Seedance, Kling 3.0 and Cinema Studio videos, and 80+ other models, with price estimates before each run, status polling and cancel.
Let your AI create images, videos and music on Kie.ai with your own key: Nano Banana, GPT Image, Veo 3.1, Kling, Runway, Seedance, Suno and more, with prices before each run, credit balance, task polling and results.
Read Archer IRM (formerly RSA Archer) GRC data through its REST and Content APIs: applications, levels, fields and values lists, plus risk, control, finding and incident records searched with OData. Session login with an Archer account.
Speech to text with AssemblyAI: transcribe audio and video files from a link with speaker labels, language detection, PII redaction, summaries, chapters, entities and sentiment, read transcripts as text, sentences, paragraphs or SRT/VTT subtitles, search words, translate or identify speakers, ask an LLM about a transcript, and create streaming tokens. US or EU data residency. Paid per hour of audio, with free credit for new accounts.
Read Baserow tables, fields, and rows from Baserow Cloud or a self-hosted instance. 4 generic read-only tools using database-token authentication.
Public blockchain data from BlockCypher for Bitcoin, Litecoin, Dogecoin, Dash and Ethereum: chain state and fee estimates, blocks, address balances, address transaction histories, single transactions and the mempool. Read-only, works without a token on the free tier.
Give your AI live web search from Brave's independent index: page text ready for grounding (LLM Context), web, news, image and video search, places and points of interest, autosuggest, spellcheck and AI answers. Read-only, needs a Brave Search API key.
Query CoinGecko (crypto prices, market data, historical, exchanges, NFT floor prices) from any AI agent. 8 tools, optional API-key auth.
Suggest and look up Russian addresses, companies and sole proprietors by INN or OGRN (ЕГРЮЛ/ЕГРИП), banks by BIC, full names and emails, reverse geocode coordinates, find the city of an IP and search Russian reference lists with DaData. Optional paid standardisation of addresses, phones and names, switched off until you allow it.
Deepgram speech AI with your own API key: transcribe recordings from a URL with speaker labels, summaries, topics and sentiment, analyze text, turn text into speech with Aura voices, and check models, keys, usage, requests and credit balances.
Official statistics of the European Union from Eurostat: read any of about 8,000 datasets (GDP, inflation, unemployment, population, energy, environment, regional NUTS data) with country, period and dimension filters, inspect a dataset's dimensions, codes and availability through SDMX, look up code lists, follow the daily update feed and query detailed Comext trade data. Free, no API key.
Search the web, scrape any page into clean text or structured data, crawl whole sites and run multi-source web research from Claude, ChatGPT or Copilot through Firecrawl's official MCP server.
Let your AI create images, videos, music and text with GenAPI's 330 models (Nano Banana, GPT Image, Flux, Kling, Veo, Sora, Suno, GPT, Claude, DeepSeek) from one ruble balance: prices before each run, balance, status polling and results.
Resolve a GTIN / EAN / UPC / ISBN barcode to product information using free public product databases (Open Food Facts, UPCitemdb, Open Beauty Facts, Google Books). No API key required. Covers food & CPG, general retail, cosmetics, and books.
Solana blockchain data through Helius: SOL and token balances, NFTs and tokens of a wallet (DAS API), readable transaction history, single transactions, wallet identity and funding source. Read-only.
Let your AI explore the Hugging Face Hub with your own access token: find and compare models, datasets, Spaces, papers and collections, look inside datasets row by row, read files from any repository, and chat with open models through Inference Providers.
Let your AI use Mistral AI with your own API key: ask Mistral models, complete code with Codestral, read PDFs and scans with Mistral OCR, create embeddings, moderate content, search the web through conversations and agents, and check files and batch jobs.
Search worldwide news headlines, sources and articles from newsapi.org via any AI agent. 3 tools, API-key auth.
Read NocoDB workspaces, bases, tables, and records from NocoDB Cloud or a self-hosted instance. 7 read-only tools using xc-token API key authentication against the v3 REST API.
По категориям
- Электронная коммерция64
- Бухгалтерия38
- CRM38
- Открытые данные37
- Инфраструктура29
- Мессенджеры29
- Продуктивность25
- Аналитика24
- ERP23
- Управление проектами23
- Платежи22
- HR20
- Мониторинг19
- Базы данных18
- Финансы17
- Логистика16
- Поддержка клиентов15
- Электронная почта14
- Автоматизация маркетинга13
- Соцсети13
- Обогащение данных12
- Издательство12
- Спорт12
- Хранение файлов12
- Планирование11
- Электронная подпись10
- Учёт времени10
- Реклама9
- Госсектор9
- Банки6
- CMS6
- Формы и опросы6
- ITSM6
- База знаний6
- Карты5
- Выездное обслуживание4
- Общепит4
- Документооборот3
- Недвижимость3
- Транспорт3
- Путешествия3
- Строительство2
- Здравоохранение2
- Игры1
- Удалённый доступ1
- Оптовая торговля1
Все 37 коннекторов от A до Z
- Apify
- Archer IRM
- AssemblyAI
- Baserow
- BlockCypher
- Brave Search
- CoinGecko
- DaData
- Deepgram
- Eurostat
- Firecrawl
- GenAPI
- Google Gemini API
- GTIN / Barcode Lookup
- Hacker News
- Helius
- Higgsfield
- Hugging Face
- Jev by TypeSafe
- Kie.ai
- Mistral AI
- NewsAPI
- NocoDB
- OCR.space
- Ollama
- OpenAI API
- OpenRouter
- OpenWeather
- Perplexity API
- Replicate
- SerpApi
- Serply
- Stability AI
- Tavily
- Twilio Segment
- xAI Grok
- You.com
Нет нужного коннектора? Добавь его одним JSON.
Каждый адаптер — это один JSON-файл в packages/backend/src/adapters/. Скопируй существующий, поменяйте endpoint и auth, открой PR — параметризованный тест проверит его при сборке.
// adapters/de/my-adapter.json
{
"slug": "my-erp",
"name": "My ERP",
"category": "erp",
"authType": "BEARER_TOKEN",
"tools": [/* ... */]
}