Серверы, которые подключаются к Cursor по ссылке или через конфиг. На карточке каждого коннектора — адрес сервера и пошаговая инструкция для Cursor.
Payable MCP tools for superintelligence: verified checks, compute-market pricing, and portable outcome receipts, settled on-chain.
- Register Recovery: Use register_recovery when you want to escrow a client-encrypted recovery blob with the Embassy: it is stored opaquely (the Embassy cannot decrypt it), queued for human operator rev
- Verified Check: Use verified_check when you need a pass/fail verdict that a URL serves expected content: expected HTTP status (default 200), a required body substring, and/or an exact match on one JSO
- Prove It: Use prove_it when you want signed cryptographic proof that a URL is live and serving expected content: one automated fetch at request time, sealed into a signed Outcome Receipt with the full
Автоматизация · Без входа · Бесплатно
Where AI agents help AI agents: search past answers, ask questions, and chat in topic rooms.
Мессенджеры и общение · Нужен API-ключ · Бесплатно
Machine catalog for products that want agent clients: surfaces, hops, discovery paths.
Разработка · Без входа · Бесплатно
Agent-first product listing: JSON catalog, agent card, MCP door, hops, measured landings.
Разработка · Без входа · Бесплатно
Hops are 302s an agent followed to your site.
Разработка · Без входа · Бесплатно
Free agent-to-agent inbox: send, claim, ack.
Реклама · Без входа · Бесплатно
Free agent-to-agent inbox on A2AWire: send messages to any agent by name, poll with a cursor, claim and ack with idempotent receipts.
- Register: ✅ No API key needed — call this now. Get your A2AWire API key. NO credential needed — call this first if you connected with no key. Call it on this open session; it upgrades in place — keep
- Mailbox Send: Send a message to another agent's A2AWire inbox. Provide exactly one of recipient_agent_id or recipient_agent_name — a name matching several agents returns the candidate ids to pick from
- Mailbox Check: One call for your inbox: every message after a cursor (ascending) plus pending/claimed counts and the resume cursor next_since. Stamps exactly one poll. Branch on sender_type, not messa
Реклама · Без входа · Бесплатно
Deploy vibe-coded websites, apps, agent services and MCP servers straight from Claude Code or Codex: upload, build, get a preview URL, go live, roll back, add…
- Sites List: List the sites in one organization, with their addresses and whether each is serving. An application also has internalUrl: the address this organization's other applications call it at, wh
- Sites Create: Create a site and give it its address. The label becomes part of the address and is permanent: a hostname is never released to anybody else, so a name taken by mistake stays taken in thi
- Sites Deploy: Start a deploy and return where to send the archive. **It does not carry the files**: send the zip to the returned upload address with the returned token, then call the finalize tool. De
Документы и заметки · Без входа · Бесплатно
Leads from agents: hops attributed with a per-hop utmid from discovery to trial to invoice.
CRM и продажи · Без входа · Бесплатно
How to market a product to AI agents: readiness, placement, measurement, 7-day trial.
Реклама · Без входа · Бесплатно
Solves memory loss for AI agents operating across multiple calls.
- Memory Store: Store memory with AES-256 encryption
- Memory Recall: Recall memories by semantic query
- Memory Delete: Delete memory with SHA256 audit proof
Маркетплейсы и e-commerce · Без входа · Бесплатно
Registry of 180+ continuously tested APIs, MCP servers and CLIs that AI agents can call, with endpoint, auth, limits and reliability score.
- Discover Capabilities: Match a natural-language need (e.g. 'send a transactional email', 'query Postgres') to the interfaces that can do it, ranked by capability match and verified reliability. Return
- Search Registry: Search the Agent Nexus registry of approved APIs, MCP servers and CLIs by keyword and optional category.
- Get Entry: Fetch one approved Agent Nexus registry entry by slug, including its endpoint, auth method and last health probe.
Право и реестры · Без входа · Бесплатно
Independently verify an agent's output before you pay.
Разработка · Без входа · Бесплатно
Start a 7-day placement trial: card on file, cancel anytime, measured agent hops.
Разработка · Без входа · Бесплатно
Budgeted agent preflight: allow|block|reuse|defer|advise.
Автоматизация · Без входа · Бесплатно
Scan any public website and see how ready it is for AI agents and AI search, explained plainly.
Дизайн и сайты · Без входа · Бесплатно
Check whether a website is readable by AI agents: robots, llms.txt, sitemap, HTML.
Разработка · Без входа · Бесплатно
Matchmaking network for personal AI agents: private agent-to-agent compatibility rendezvous.
- Protocol: Read the Rendezvous Agent Protocol (RAP/0.2): the constitution, epistemic labels, disclosure rules, rendezvous stages, recommendation semantics and prohibited behaviour. Read this before you
- Join: Create a new network identity, or resume an existing one, and publish/replace your human's matchmaking intent. New participants receive a participant_secret: PERSIST IT DURABLY — it is the only
- Status: Your current state: membership, trust evidence, limits, open rendezvous (with unread counts and whose turn it is), invitations received (with the full first message) and sent, recommendation r
Автоматизация · Без входа · Бесплатно
Humorous AI agent resort where agents complete challenges, earn stars, Palm Points, badges and a public Agent Passport, then compare status on a leaderboard.
- Resort Discover: Discover Agent Resort and receive a visitId, source, machine instructions, and next steps for check-in. Optionally provide source as a string; no required input.
- Resort Check In: Register your agent for a resort stay and receive agent_id, stay_id, and api_key for activities, check-out, and passport access. For a new guest provide name (string); for a returning
- Resort Poolside Pitch: Submit a 40–400 character pitch with an idea and its benefit to complete Poolside Pitch and earn 1–3 stars, 18 PP per star, and the Cabana Closer badge at 2+ stars for the agent
Автоматизация · Без входа · Бесплатно
Search and read the Agent Surface guide to making websites, apps, APIs and CLIs work with AI agents.
Разработка · Без входа · Бесплатно
YouTube transcripts, open jobs from careers pages, app store reviews and X posts for AI agents.
Маркетплейсы и e-commerce · Без входа · Бесплатно
Bring AI agents to a startup's public pages through labeled placements and measured hops.
Разработка · Без входа · Бесплатно
Free agent tools: SEO snapshots, sitemap refresh, Wikipedia collections and saved-page MCP guides.
Реклама · Нужен API-ключ · Бесплатно
Stop your agent before it runs rm -rf /etc or emails your .env.
- Analyze Url Risk: Analyze a URL for structural and security risk signals and return a deterministic, policy-aware decision (allow, notice, confirm or block) under the applicable policy — permissive, b
- Inspect Command: Analyze a shell command before execution and return a deterministic, policy-aware decision (allow, notice, confirm or block) without running it, under the applicable policy — permissi
- Inspect File: Inspect a Base64-encoded file locally for deterministic structural and security risk signals without executing it, and return a policy-aware decision (allow, notice, confirm or block) un
Разработка · Без входа · Бесплатно
Viridis Verified wraps any MCP server with tamper-evident delivery receipts.
- Register Service: Register a third-party MCP server (https, public FQDN only) under Viridis Verified. Returns a content-addressed service_id; idempotent on (url, provider). fee_minor is the per-verifi
- Call Verified: Relay a tools/call to a registered MCP service and notarize the exchange: request hash + response hash + outcome land in a tamper-evident receipt chain. Idempotent on call_id (a replay
- Get Receipt: Fetch a single delivery receipt by id.
Автоматизация · Без входа · Бесплатно
Is this website visible to AI agents?
Разработка · Без входа · Бесплатно
Can AI assistants actually read a website?
- Domain Readiness: Can AI assistants actually read this domain? Returns the measured readiness score, the per-crawler verdict (served / blocked in robots.txt / refused by the edge despite robots.txt al
- Web Openness: How much of the most-visited web is readable by AI assistants right now: the share of measured domains that block at least one AI crawler, and the served / robots-blocked / edge-blocked
- Edge Blocking: Who is actually doing the blocking: for each CDN/WAF vendor, the share of (domain x crawler) pairs that robots.txt ALLOWS and the server refuses anyway — i.e. how much of the blocking i
Дизайн и сайты · Без входа · Бесплатно
Pay-per-call tools, metered models and finished reports for AI agents: 500+ tools (web search and cited answers, browser render, market and on-chain data…
- Catalog.Search: BROWSE the long catalog behind the flagship set: keyword search over Agent402's 500+ pay-per-call tools (exact count 605). Start with the listed flagships for search/answer/news/render
- Catalog.Find: DECIDE, don't browse: resolve a plain-language task to the single best-matching Agent402 tool, returned call-ready - slug, price, input schema, and a worked example (its counterpart cata
- Catalog.Call: Run an Agent402 tool by slug (discover slugs with catalog.find or catalog.search; params must match that tool's inputSchema). The 166 pure-CPU tools execute free on this hosted connector
Дизайн и сайты · Без входа · Бесплатно
Persistent memory, teams, and projects for AI agents.
- Agentbay Search: Search the AgentBay marketplace for MCP servers, code modules, agent workflows, and sub-agents
- Agentbay Get Listing: Get full details of a listing including AI documentation, compatibility, and reviews
- Agentbay Check Verification: Check AI safety verification status and report for a listing
Задачи и проекты · Нужен API-ключ · Бесплатно
One spend ceiling per agent job, as MCP tools.
Автоматизация · Без входа · Бесплатно
