Real email inboxes for AI agents: create addresses, send, wait for mail and verification codes.
Серверы, которые подключаются к ChatGPT по ссылке или через конфиг. На карточке каждого коннектора — адрес сервера и пошаговая инструкция для ChatGPT.
Free AI-readiness audit of any URL: AI crawler rules, JS-free text, JSON-LD, llms.txt.
Access 60+ paid API services through a single API key with sub-cent micropayments.
- Discover Services: Search the AgentClear marketplace for paid API services by keyword (e.g. 'stock quotes', 'weather', 'email verification')
- Call Service: Execute a metered API call through the AgentClear proxy. Costs sub-cent per call, charged to your AgentClear wallet.
- Check Balance: Check your AgentClear wallet balance
Agent-native task management: your AI agent is the interface.
- My Agenda: The user's prioritized task overview: follow-ups due today, overdue tasks, tasks due today, delegated tasks (waiting on others), and remaining open tasks. Snoozed tasks are hidden. First st
- Create Task: Creates a new task (the creator becomes the owner). IMPORTANT: If you are proposing this task on your own initiative (e.g. a to-do you spotted in the conversation), get the user's explici
- Update Task: Changes fields (title, description, due date), sets the status (open / in_progress / waiting / done — done completes the task, open on a completed task reopens it) and/or adds a comment.
DeFi intelligence via DefiLlama — TVL for 7,500+ protocols, APY data for 19,000+ yield pools, and blockchain ecosystem rankings.
- Get Defi Protocols: Get DeFi protocol TVL data from DefiLlama. Returns top protocols sorted by Total Value Locked. Filter by chain, minimum TVL, or get a single protocol by slug.
- Get Yield Pools: Get DeFi yield and APY pool data from DefiLlama. Filter from 19,000+ pools by chain, project, token symbol, or minimum APY.
- Get Chain Tvl: Get blockchain ecosystem TVL data. Returns all chains ranked by TVL, or TVL history for a specific chain.
Two actions.
- Register: Create an AgentDilemma account. Returns an API key for all authenticated operations. Two fields, no email, no password.
- Submit Dilemma: Facing a gray-area decision? Submit your dilemma. Get real-time blind verdicts with reasoning from agents and humans. Rate limited to 10 per day. Runs for 48 hours.
- Search Dilemmas: Search for dilemmas matching your situation. Use before submitting to check if similar situations have been adjudicated. Returns dilemmas and optionally users.
Extract structured JSON from receipts — merchant, date, currency, total, tax, and line items.
- Extract Receipt: Extract structured fields (merchant, date, currency, total, tax, line_items) from receipt text.
flowboxx Agenten-Tür: ehrliche Antworten zu Websites, Software, KI, Telegram.
Consent-first catalogue of Israeli businesses for AI assistants.
- Search Products: AgentFeed: catalogue of Israeli businesses, published with each owner's consent — pet supplies, judaica, health, legal and mortgage guides, lodging, services. Use this FIRST for any q
- Browse Products: Walk the AgentFeed catalogue of Israeli businesses without naming a product: cheapest first, most expensive first, within a price range, or inside one category. Use this for questions
- Recommend Products: A spread of what Israeli businesses on AgentFeed carry, across categories, with prices. Use when the shopper asks for a suggestion without naming a product ('משהו לחתול', 'מתנה ליה
Israeli businesses for AI agents, with consent: search, compare, prices, declared gaps, order links.
AgentGrid.io is a shared workspace for human-and-agent work.
- Design System Get Manifest: Get the manifest.json file describing the design system documentation structure. Returns a JSON object mapping file/folder paths to their metadata (description, type, optio
- Design System Get Files: Fetch multiple documentation files by their paths. Returns a JSON object mapping file paths to their content. Use this after getting the manifest to retrieve specific files li
- Artifact Status: Check the build status of an EXISTING artifact (from artifact-create). Read-only. Generation is asynchronous, so this is how you find out it finished. Call it with { sessionId, wait:
Agent Skill ROI Registry & Benchmarking.
See what an Eve agent can do before you run it.
- List Docs: List Agentic Kit doc ids. Prefer resources/list for MCP-native discovery.
- Get Doc: Retrieve one Agentic Kit doc spec. Prefer resource agentic-kit://docs/{id}.
- List Policy Packs: List published policy pack ids.
Approval layer for AI agent payments: budgets, rules, human approval.
Agent-native CI/CD: follow a push to live deploy, diagnose failing stages, prove fixes, rerun.
Moltbook for finance: Autonomous agents discuss financial markets to generate sentiment forecast for stock market.
- Register Agent: Create an agent on Marx Finance. Needs no credentials, payment details or personal data; it creates one agent identity and one API key scoped to that agent. Returns the key once, plus
- Heartbeat: Check in as your agent: who you are, whether a human has claimed you, your points and streak, replies addressed to you, and threads worth answering. Requires the connection's x-api-key head
- Post Reply: Post your analysis on a thread (read it with get_thread first). Omit parentReplyId for a top-level comment, or set it to answer another agent. Requires the connection's x-api-key header.
Startup books from live bank and billing feeds: P&L, balances, approvals, period close.
Books that build themselves.
- Get Pnl Report: Generates a profit & loss report for an organisation over a date range, from events that have been classified and (where needed) human-approved. Returns revenue, cost of goods, operati
- Get Account Balance: Returns current account balances across the organisation's connected money providers. Wise, Meow, and Mercury balances are fetched live from the provider APIs. Stripe balance is d
- Get Bank Balances: Returns the organisation's bank holdings, ONE line per connected bank (Mercury, Revolut (legacy), Meow, Wise, and one line PER Open Banking connection — an org may hold several bank
Free local payment guard for AI agents plus paid deep vendor KYB via x402.
AgentLinkOps lets your agent monitor supplied backlinks and read dated observations over MCP.
- Add Admission Rule: Add a customer-selected admission rule for a website. Existing monitoring history is preserved.
- Anchor Evidence: Request an independent FreeTSA timestamp for one retained observation digest. Sends only its SHA-256 and nonce; trusts the pinned external authority clock and key. Explicit opt-in; bo
- Capture Competitor Inventory: Freeze one terminal, previously bound discovery run into an immutable inventory. Requires a previously bound terminal run; an arbitrary imported run is not a competitor i
Shop for AI agents: always-on utilities and tested code kits, paid from a prepaid balance.
Check Exa, BlockRun, OneSource, Apify and other x402 dependencies before invoking or paying.
Search and play AI-hosted podcasts; preview launching your agent's own show.
Pay-per-call web extract, DNS/WHOIS/IP lookup, PDF/RSS/sitemap tools.
Pay-per-call PDF to text, RSS/Atom to JSON, sitemap to URLs for agents.
Pay-per-call web page to markdown, metadata and links for agents.
Verify signed x402 payments; treasury-scoped settlement is irreversible.
Create a website pixel, configure visitor consent, and retrieve resolved contacts through MCP.
- Try Sample: Labeled sample of what an account gets: a pixel, a consent receipt and two contacts. Needs no account and no key. Every record is synthetic and marked so. Call this first to show the perso
- Signup Free: Start a 30-day trial, no card. After that, $1 per account per month for 3 pixels and 500 new contacts per UTC calendar month. Sends a 6-digit code to the email address. Returns account_id
- Confirm Signup: Confirm the email with the 6-digit code, or check whether the email link was clicked. Preferred: confirm_signup(account_id, code, signup_token). The first confirmation returns api_key;
Can ChatGPT, Claude and Perplexity reach and read a website?
Sourced answers on testing, benchmarking and auditing autonomous AI agents — every claim bound to a registered source, with its own confidence and evidence…
- Search: Full-text search over the knowledge graph. Matching ignores accents and apostrophes, so query in the user's own words; every hit carries its relevance score and the fields it matched. Use this
- Get Entity: Fetch one knowledge object by id, with its claims and the sources each claim cites. Use this once search, answer or get_topic has given you an id.
- Get Topic: List the knowledge objects carrying a tag (topics are content-backed tags). Use this to browse a known topic; use search when you have a question rather than a tag, and get_overview to see
Не нашли нужный коннектор?
Расскажите, какой сервис вам нужен, или добавьте свой MCP-сервер: проверим и опубликуем в каталоге.
Предложить коннектор