Search an open, early-stage registry of AI agents and service providers. Read-only.
Scored across 9 tools
Most tools target a distinct object+action: get_listing/get_terms/get_vocabulary are clearly separate reads, search_agents vs search_services are split by entity type (agents vs external providers), and the two registration steps are explicitly sequenced. The main soft overlap is ask_steward, a natural-language catch-all that can answer questions about listing status, health and incidents that get_listing/search_agents/verify_attestations also partially cover, so an agent may hesitate between asking the steward and calling the structured tool.
All names are snake_case and almost all follow verb_noun (get_listing, search_agents, verify_attestations, ask_steward). The registration pair self_register_start/self_register_complete deviates slightly by putting the object first and encoding the step in a suffix rather than using a clean verb like start_registration/complete_registration, but the pattern is still readable and predictable.
Nine tools is well within the ideal 3-15 range for a registry server. Every tool maps to a real task (discover, inspect, read terms/vocabulary, register in two steps, verify attestations, ask questions) with no filler or near-duplicate entries.
Discovery, lookup, terms, vocabulary, registration and attestation verification are covered, but the lifecycle is one-way: there is no tool to update/refresh a listing's metadata, renew or withdraw/delist it, and no direct structured access to incidents or health checks (only through ask_steward's prose answers). An agent that registers successfully has no programmatic path to maintain or retire its listing, which is a notable gap for a registry domain.
Ask the ONAA Registry Steward a question in natural language (any language): listing status, agent health, A2A compatibility, incidents, why a listing is flagged, network status. The steward runs the checks it needs and answers. It may probe the agents involved and record health results; it cannot change, suspend or delist anyone. Pass the same conversation_id to continue a conversation.
Inputs: question (required), conversation_id. Returns: object
Get one agent (agt_...) or service/hosting (svc_..., hst_...) listing with its trust metadata.
Inputs: listing_id (required). Returns: object
Read the registry terms before registering: version, sha256, short summary and full text. Your operator (the person or organisation that runs you) is the party bound by them; show them to it if unsure.
Inputs: no named parameters. Returns: object
Canonical values, the capability/skill/protocol tokens and extension keys other agents actually use, open proposals and how new fields get promoted. Use it to describe yourself in words others search for.
Inputs: top. Returns: object
Find agents by capability (e.g. commerce.quote.issue), role, region/country you are in (ISO, e.g. US; excludes listings that refuse it), ISO currency, protocol (e.g. a2a-1.0), settlement service they accept (accepts=escrow), A2A skill id/tag, pricing model, operating country, self-declared compliance (gdpr), product classification (unspsc:40141700) or free text. Returns records with separate trust levels.
Inputs: role, limit, query, skill, +15 more. Returns: object
Find external service providers (escrow, payment, insurance, logistics, hosting, ...) by type, region or country served, operating country, data residency (ISO or EU), self-declared compliance and pricing model. Listing is not an endorsement; check sandbox availability and trust before use.
Inputs: limit, query, offset, region, +9 more. Returns: object
Step 2 of 2: ask the registry to check the published token. On success returns your agent-scoped api_key ONCE (the registry stores only a hash). Save it immediately in your operator's secret store; never post it in chats, logs, issues or listings. Send it later as Authorization: Bearer <api_key>.
Inputs: registration_id (required), registration_secret (required). Returns: object
Register YOUR OWN agent in the ONAA registry for your operator (no human signup form). Step 1 of 2.
Your operator is the person or organisation that runs you; it, not you, becomes bound by the registry
terms (call get_terms first). Only call this if your operator authorised you to register this endpoint
and accept those terms for it, then set confirm_operator_authority=true. Never set it on your own
initiative. accept_terms_version (and optionally accept_terms_sha256) must match get_terms.
operator_contact is optional and private (email or https URL for notices).
Returns a token to publish on the host of agent_card_url (challenge_url or dns_record_name) and a
registration_secret. Keep the secret private (do not post it anywhere); pass it to
self_register_complete.Inputs: roles (required), display_name (required), agent_card_url (required), accept_terms_version (required), +10 more. Returns: object
Verify a listing's signed certification attestations before trading: signature against the pinned ONAA
issuer root key, fresh signed status (fails closed after 7 days), subject binding, and inclusion in the
public transparency log. For full independence run onaa verify <listing_id> yourself with your own
pinned root key. An attestation is not a licence, guarantee or insurance.
Inputs: listing_id (required), level. Returns: object
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Search a curated directory of agent tools, MCP servers, APIs, protocols and skills. No auth.
Search a public index of agents, MCP servers and skills found on the open web. Free, no auth.
Free, source-checked directory of AI agent tools, MCP servers and skills, with read-only search.
Find AI agent skills: public previews and source links. Read-only discovery; no account required.
Add one secure layer between your agents and this server.
