Create printable cryogenic lab, sample, tube and QR label sheets.
Серверы, которые подключаются к ChatGPT по ссылке или через конфиг. На карточке каждого коннектора — адрес сервера и пошаговая инструкция для ChatGPT.
Free discovery search of rights-cleared news across entitled publisher catalogs.
- Search: Search articles and content on the Free Discovery plan. Returns metadata only (no full article body). Limited to 100 queries per month.
- Search Ui: Same Free Discovery search as 'search', but returns an interactive research widget (MCP App). Metadata only (no full article body). Prefer for visual browsing; use 'search' for plain-text c
- List Publishers: Return publishers available for Free Discovery (id, name, description, description_short, domain, logo_url). Does not count against quota.
航通社官网(lishuhang.me,书航博客 + 每日 AIGC 早报)只读检索:文章与早报列表、关键词搜索、单篇全文 markdown。Streamable HTTP,免鉴权,无状态。
Read any public web page as clean, agent-ready Markdown — typically ~4x smaller than the raw HTML, so your agent burns fewer tokens per read.
- Skim Read: Fetch a public URL and return clean, agent-ready Markdown via Skim (skim402.com): strips nav, ads, and boilerplate; preserves the article body plus metadata (title, byline, published date,
- Skim Extract: Read a public URL and extract structured JSON from it via Skim (skim402.com). Either pick a preset (article, product, job, review, event, table) or supply a JSON Schema (top-level type "
- Skim Signals: Fetch the latest items from one of Skim's curated intelligence feeds (skim402.com/signals): ai-news, sec-filings, deals, research, campaign-finance, film-incentives, crypto-news, macro,
Korean export docs: agents create invoice & packing list drafts via OAuth.
Web scraping for agents: scrape, crawl, map, search and extract pages as clean markdown or JSON.
AI adult image, character and movie generator for adults (18+).
- Get Account: Start here. Credits balance, age-verification state for the caller's jurisdiction (whether NSFW media is available, and the verification URL when it is not), credit costs per image, per v
- Read Content Rules: The acceptable-use rules every prompt and image is checked against (adults only, fictional characters only, no real people, no minors, no non-consent, no violence). Read this befor
- List Characters: The user's saved characters (id, name, appearance, style, status, thumbnail). Use a character id in generate_images, generate_video and create_movie_scene for a consistent identity.
SpriteCook helps you generate 2D pixel art game assets with AI directly from your MCP client.
- Generate Game Art: Generate 2D game assets with AI, including pixel art, sprites, icons, props, and UI elements.
- Generate Tileset: Generate game tilesets from a prompt, including top-down and isometric options.
- Animate Game Art: Animate an existing SpriteCook asset into a short sprite-sheet animation.
Live and historical precious-metals spot prices, observed dealer premiums, and the Goldback rate — no auth, no key.
- Get Spot Prices: Current and previous-session spot prices for gold, silver, platinum, palladium, copper and nickel, in any supported currency and per troy ounce or gram.
- Get Observed Premiums: Rolling fine-metal-weighted median asking premiums over spot, observed from real marketplace listings rather than quoted by a dealer.
- Get Price History: Daily historical series for charting — one metal, the Goldback, or one PCGS-numbered coin at one grade.
What is Stele?
- Recall: One-call semantic + full-text recall over the graph — a ranked bundle of the decisions, tasks, risks, and documents most relevant to a question or topic. The default way to load context before
- Search: Find nodes or documents by the words they contain. Nothing here matches by meaning, so use `recall` for a natural-language question. method "keyword" (default): ranked full-text search over ac
- Fetch: Fetch one node in full by its shareable id (TASK-N/KNOW-N/COMP-N/DOC-N/NODE-N), with its edges — this is how you read a full body (recall/search return summaries). Pass version to fetch a histo
Discover free, licensed loops and analyze authorized audio for BPM, musical key and waveform data.
- Start Trial: Start a temporary, email-free Pulse trial for one URL analysis. Read trial_policy and trial_allowance for the actual duration cap and remaining attempts; an existing trial key may have a
- Estimate Cost: Estimate the cost to analyze an audio file before committing. Always call this first. Returns an estimated cost in dollars, a job_estimate_id and expires_at. Review the estimate before
- Analyze Track: Run audio analysis on a public audio URL. Requires estimate_cost to be called first (job_estimate_id). Requires PULSE_API_KEY. Before calling, you MUST confirm with the user that they h
The SVGverseAI MCP Server lets you connect your AI agents, automation workflows, or creative tools directly to SVGverseAI’s image generation engine — without…
- Create Collection: Create collection
- Generate Ai Video: Generate AI video
- Generate Blaze Image: Generate an SVG, PNG, or WebP image from a prompt using Blaze styles
Aya is an AI recruiter that interviews candidates on WhatsApp (or by web link) in English, Spanish, German, French and Portuguese, and returns a score per…
- Listar Vagas: Lists the company's job openings with their status and how many candidates each one has. Read-only. Use it to find a job id before looking at candidates or inviting someone.
- Detalhar Vaga: Shows one job in detail, including the competencies Aya (the AI interviewer) evaluates and the weight of each — the criteria behind every candidate score. Read-only.
- Listar Candidatos: Lists the candidates of a job with their interview score, profile fit and pipeline stage, highest score first. Read-only. Does NOT return phone, e-mail or résumé.
tasklite.net: a hosted backend and admin for apps built by AI agents.
- List Organizations: List the organizations the authenticated user belongs to. Use the returned id as organizationId in other tools.
- Configure External Access: Read or change how EXTERNAL users (people who sign up to your app through TaskLite auth: POST /auth/register-external with this organizationId, then POST /auth/login) get in
- List Projects: List projects in an organization. The API returns 50 per page — an organization with more than that needs page 2 and beyond, so check the returned total before assuming a project does n
Teetrack is a time tracking and billing tool built for one person: freelancers, consultants, and solo agency owners who bill by the hour.
- Start Timer: Start a new timer (creates a track with no end time). Multiple timers can run concurrently. Returns the new running track.
- Stop Timer: Stop a running timer by setting its end time to now. If no id is given, stops the most recently started timer. Returns the stopped track.
- Get Running Timer: Get all currently running timers (tracks with no end time). Returns an array (empty if none active).
Query geospatial datasets, manage workflow jobs, deploy published releases, and search Tilebox docs.
Pay-per-call tools for AI agents.
- Get Product Details: Find out what a product is and what it costs, from its page URL. USE THIS WHEN you have the URL of ONE specific product — a store listing, a marketplace item, a manufacturer's pag
- Try It Free: Free. Run a real extraction against one fixed sample product page and return the result. USE THIS to decide whether the paid tools are worth paying for. It returns the identical shape get
- Compare Products: Price the same product at several stores — up to 5 URLs in ONE call and ONE payment. USE THIS WHENEVER YOU HAVE MORE THAN ONE URL. Comparing an item across stores, checking a short l
🚀 58+ REST tools · 44 MCP tools · 5,000 FREE req/day!
- Extract Url: Extract main content from a webpage URL as markdown or text.
- Extract Pdf: Extract text from a PDF file by URL.
- Embed Text: Generate text embeddings (minilm 384d or bge-large 1024d).
Universal Native Model Context Protocol (MCP) server hub providing 19 production-grade AI agent tools with sub-50ms serverless edge execution: - 📄…
- Topai Web To Markdown: Extract clean, ad-free, noise-free Markdown and metadata from any public website URL for LLM context windows.
- Topai B2b Data Leads: Search, filter, and extract verified B2B leads by industry, country, company size, and executive job role.
- Topai Company Enrichment: Deep B2B company intelligence: returns company name, sector, employee range, technographics, and contact graph from domain.
Tournride rents bikes for the Camino de Santiago, with luggage and bike transfer between stages.
- Consultar Disponibilidad Bicicletas Camino: Consulta disponibilidad en tiempo real, PRECIOS EXACTOS (calculados con el motor de reservas: bici para los días + transporte ida + transporte vuelta + desc
- Crear Presupuesto Alquiler Camino: Guarda la cotización como PRESUPUESTO en el sistema de Tournride y devuelve un enlace para que el cliente lo abra, elija talla y formalice él mismo la reserva. Llama
Transform MCP is a single MCP-native tool that turns any file into agent-ready data, called directly from your agent session with no separate pipeline to wire…
- Request File Upload Url: Upload a file to the Unstructured Platform for parsing. Returns a signed PUT URL; the agent PUTs the file bytes there, then passes the returned ``file_ref`` to ``start_transfo
- Start Transform Job: Transform files into structured output by running a configurable pipeline. Submits 1–10 inputs as one async job and returns a ``job_id`` immediately. Drive the wait via ``check_jo
- Check Job Status: Check a job's current status. Returns immediately. Works for any job — a transform job (from ``start_transform_job``) or an extraction job (from ``start_extraction_job``). Non-blocki
Create designed PowerPoint presentations from a topic, text, or a PDF, DOCX, PPTX or TXT file.
Build and ship in-product training from your AI assistant.
- List Courses: Lists every course in the workspace, newest first.
- Get Course: Fetches one course by id.
- Create Course: Creates a draft course. Screens follow the builder's shape — each has an id, title, and an array of blocks.
The official hosted MCP server for the Unipile API.
- List Endpoints: Lists all API paths and their HTTP methods with summaries, organized by path. Results can be passed directly into 'get-endpoint'.
- Get Endpoint: Gets detailed information about a specific API endpoint, including security schemes and servers
- Search Endpoints: Performs a deep search through paths, operations, and parameters to discover relevant API endpoints. Use this tool to find specific API capabilities, required parameters, or data mod
Search a library of university course materials (past exams, assignments, lab reports, lecture notes) and your uNotes flashcards and quizzes.
- Search Library: Search the public uNotes document library by title, course, or type keywords. Call it with the query alone whenever no scope id is already known — schoolId and courseId are optional na
- Get Document: Get the metadata of a single uNotes document by ID: title, type, course, school, year, season, professor, language, popularity counters, and its public URL. Use get_document_content to r
- Get Document Content: Get the full text content of a specific document, lecture session, or flashcard set. Use this when you need to read the actual content of a material to answer questions about it.
What is Unpaged?
- Document Create: Start a new whiteboard — for a plan the team should review, an architecture to show in a design review, research to map, decisions to keep. Returns the document with `rootNodeId` (the
- Document Get: Read a whole whiteboard — every canvas (node) and every element on it — to understand or extend it before editing, or to answer questions about what is on it.
- Document List: Find the user's whiteboards by title — the first call when they mention 'the roadmap board', 'the architecture board' or 'that plan we made': lists documents you own or that were shared
Call a catalog of ready-to-use APIs through one upAPI account and key, without signing up for each upstream service.
- Search Ops: Find upAPI operations to call. upAPI is an API marketplace: 44 operations across 10 categories (Communication, Data, Developer Tools, Finance, Maps, Media, SEO tools, Search, Tools, YouTub
- Call Op: Run one upAPI operation by slug. Discover slugs and their parameters with `search_ops` first. Costs the operation's own quota units per call (1 for most, more for search/browser-backed ones)
- Web Search Post: Search the web and get structured results (titles, URLs, snippets). DuckDuckGo-backed — no browser, no CAPTCHA, fast. upAPI operation `web-search.post` (Search). Costs 1 unit of month
Manage uptime monitors, incidents and status pages, and read check results, in Uptimely.
- Search Tools: Find the Uptimely MCP tools this connection can reach, returned as TypeScript declarations to call from execute_typescript. See the server instructions for the full contract.
- Execute Typescript: Run a short TypeScript program that orchestrates Uptimely MCP tools (found via search_tools) in an isolated sandbox. See the server instructions for the full contract.
Give your agent a browser that renders JavaScript: read any page as Markdown, take screenshots it can see, extract metadata, capture console errors, run…
- List Projects: The projects this token can reach, each with how many requests it has made in the last 30 days and where its results are delivered. Start here: every other tool takes a project_id from
- Get Usage: What the organization's plan allows, how much of it is left this period, and what each operation costs. Worth reading before a run of expensive calls: the operations differ by seventeen tim
- Fetch Markdown: Exposes POST /markdown. Renders the page in headless Chrome and converts its main content to clean Markdown — headings, lists, links and code kept, navigation, sidebars and cookie bann
Read-only MCP access to Vela's corpus of human experience: cited passages, coordinates, reading paths.
- Vela.Corpus.Query: Ask the corpus by COORDINATE rather than keyword. Filter works by axis weights (e.g. religion ∈ {T,s} AND work ∈ {T,s} returns the God-and-Work source set across genres), controlled
- Vela.Corpus.List Topics: List the coordinate systems the corpus can be queried through — each with its thesis, axes, and controlled vocabularies. Call this before vela.corpus.query to learn what axes
- Vela.Corpus.Describe Topic: Describe ONE topic in full — its axes and their operative definitions, its complete controlled theme and quality vocabularies, plus the vocabulary actually IN USE across th
Не нашли нужный коннектор?
Расскажите, какой сервис вам нужен, или добавьте свой MCP-сервер: проверим и опубликуем в каталоге.
Предложить коннектор