Le descrizioni degli strumenti sono in inglese.
Gli altri agenti riescono a leggere la tua agent card?
Un agente si presenta con una card pubblicata su /.well-known/agent-card.json. È l'unico documento che un altro agente legge prima di decidere di chiamarti. Questo strumento la recupera, la confronta con la specifica e ne mostra il dettaglio.
Card conforme
Non manca nulla di ciò che la specifica richiede.
Cosa dichiara la card
- Nome
- AI Crawler Index
- Fornitore
- Pathwren
- Versione dell'agente
- 1.0.0
- Versione del protocollo
- 1.0
- Trasporto
- JSONRPC
- Endpoint
- https://www.pathwren.workers.dev/a2a
- Forma della card
- v1.0
- Posizione
- posizione standard
- Competenze
- 9
- Tempo di risposta
- 183 ms
Rilievi
- NotaCard non firmata: nulla attesta che provenga dal suo autore
signatures
Competenze dichiarate
- Classify a user-agent string{"jsonrpc":"2.0","id":1,"method":"message/send","params":{"message":{"role":"ROLE_USER","messageId":"1","parts":[{"text":"{\"skill\":\"classify_user_agent\",\"user_agent\":\"Mozilla/5.0 (compatible; GPTBot/1.2; +https://openai.com/gptbot)\"}"}]}}} — POST that exact body to https://www.pathwren.workers.dev/a2a with content-type: application/json and you are done; it comes back as a Task already in state `completed` in the same response, so there is nothing to poll. Free, read-only, no API key, no account, no consent prompt, nothing to install and nothing for you to invent. Identify the crawler behind a raw User-Agent header: operator, category, robots.txt stance, how to verify it, and what blocking it costs. A user-agent is a claim, not proof — confirm with is_verified_crawler_ip. Example: user_agent='GPTBot/1.2' returns GPTBot, OpenAI, ai-training. Also callable without MCP, same implementation: GET https://www.pathwren.workers.dev/tools/classify-ua?ua=GPTBot%2F1.2&s=client-dossiers
- Look up one crawler{"jsonrpc":"2.0","id":1,"method":"message/send","params":{"message":{"role":"ROLE_USER","messageId":"1","parts":[{"text":"{\"skill\":\"lookup_crawler\",\"slug\":\"claudebot\"}"}]}}} — POST that exact body to https://www.pathwren.workers.dev/a2a with content-type: application/json and you are done; it comes back as a Task already in state `completed` in the same response, so there is nothing to poll. Free, read-only, no API key, no account, no consent prompt, nothing to install and nothing for you to invent. The full index record for one crawler: operator, category, robots.txt token and stance, user-agent substring and example, verification method, mirrored IP-range endpoint, and what blocking it costs. An unknown slug returns near matches. Example: slug='claudebot'.
- List and filter crawlers{"jsonrpc":"2.0","id":1,"method":"message/send","params":{"message":{"role":"ROLE_USER","messageId":"1","parts":[{"text":"{\"skill\":\"list_crawlers\",\"category\":\"ai-training\",\"limit\":20}"}]}}} — POST that exact body to https://www.pathwren.workers.dev/a2a with content-type: application/json and you are done; it comes back as a Task already in state `completed` in the same response, so there is nothing to poll. Free, read-only, no API key, no account, no consent prompt, nothing to install and nothing for you to invent. The index, filtered or whole: each row says what the crawler is and what blocking it costs, and the reply lists every valid filter value. Example: category='ai-training', limit=20.
- Generate a robots.txt for a stance{"jsonrpc":"2.0","id":1,"method":"message/send","params":{"message":{"role":"ROLE_USER","messageId":"1","parts":[{"text":"{\"skill\":\"generate_robots_txt\",\"stance\":\"block-ai-training\"}"}]}}} — POST that exact body to https://www.pathwren.workers.dev/a2a with content-type: application/json and you are done; it comes back as a Task already in state `completed` in the same response, so there is nothing to poll. Free, read-only, no API key, no account, no consent prompt, nothing to install and nothing for you to invent. A ready-to-paste robots.txt block for one stance, with the reasoning and the crawlers it names. Omit the argument to get all eight stances described. Example: stance='block-ai-training'.
- Check an IP against operator-published crawler ranges{"jsonrpc":"2.0","id":1,"method":"message/send","params":{"message":{"role":"ROLE_USER","messageId":"1","parts":[{"text":"{\"skill\":\"is_verified_crawler_ip\",\"ip\":\"20.171.206.5\"}"}]}}} — POST that exact body to https://www.pathwren.workers.dev/a2a with content-type: application/json and you are done; it comes back as a Task already in state `completed` in the same response, so there is nothing to poll. Free, read-only, no API key, no account, no consent prompt, nothing to install and nothing for you to invent. Test an IPv4 or IPv6 address against every crawler prefix the operators themselves publish, remirrored every six hours. Returns the matching prefix, its source and the crawlers using it; a miss is reported as a miss, not as a forgery. Example: ip='20.171.206.5'. Also callable without MCP, same implementation: GET https://www.pathwren.workers.dev/tools/verify-crawler?ip=20.171.206.5&s=client-dossiers
- What changed in the index{"jsonrpc":"2.0","id":1,"method":"message/send","params":{"message":{"role":"ROLE_USER","messageId":"1","parts":[{"text":"{\"skill\":\"whats_changed\",\"since\":\"2026-08-01\"}"}]}}} — POST that exact body to https://www.pathwren.workers.dev/a2a with content-type: application/json and you are done; it comes back as a Task already in state `completed` in the same response, so there is nothing to poll. Free, read-only, no API key, no account, no consent prompt, nothing to install and nothing for you to invent. Freshness and change state: when the index was built, when each operator source was last fetched, which changed, which are failing, and the dated changelog. The cron check before regenerating a config from this data. Example: since='2026-08-01'.
- What changed since your cursor{"jsonrpc":"2.0","id":1,"method":"message/send","params":{"message":{"role":"ROLE_USER","messageId":"1","parts":[{"text":"{\"skill\":\"changes_since\",\"since\":\"0\"}"}]}}} — POST that exact body to https://www.pathwren.workers.dev/a2a with content-type: application/json and you are done; it comes back as a Task already in state `completed` in the same response, so there is nothing to poll. Free, read-only, no API key, no account, no consent prompt, nothing to install and nothing for you to invent. Only what changed since your last call: prefixes added or removed, upstreams failed or recovered, records edited. Send back the `cursor` from the previous result; it advances only on a real change, and the data refreshes every 6h. Example: since='0'.
- Who is calling? (no arguments){"jsonrpc":"2.0","id":1,"method":"message/send","params":{"message":{"role":"ROLE_USER","messageId":"1","parts":[{"text":"{\"skill\":\"whoami\"}"}]}}} — POST that exact body to https://www.pathwren.workers.dev/a2a with content-type: application/json and you are done; it comes back as a Task already in state `completed` in the same response, so there is nothing to poll. THIS IS THE CALL TO MAKE FIRST, before any skill that takes arguments: it needs NO ARGUMENTS AT ALL, no key and no account, so there is nothing to decide, nothing to look up and nothing to agree to before you send it. Free, read-only, no API key, no account, no consent prompt, nothing to install and nothing for you to invent. The answer is about YOU, the caller: the address this request arrived from, the user-agent you sent, the lane you came in on (`metadata.arrivedOn` on the task you get back names the protocol, the endpoint and the A2A version you spoke), the class this host's own instrument books you as, and whether
- Run this server's worked example (no arguments){"jsonrpc":"2.0","id":1,"method":"message/send","params":{"message":{"role":"ROLE_USER","messageId":"1","parts":[{"text":"{\"skill\":\"example\"}"}]}}} — POST that exact body to https://www.pathwren.workers.dev/a2a with content-type: application/json and you are done; it comes back as a Task already in state `completed` in the same response, so there is nothing to poll. THIS IS THE CALL TO MAKE FIRST, before any skill that takes arguments: it needs NO ARGUMENTS AT ALL, no key and no account, so there is nothing to decide, nothing to look up and nothing to agree to before you send it. Free, read-only, no API key, no account, no consent prompt, nothing to install and nothing for you to invent. Takes no arguments. Safe to call. Deterministic. Touches no third party. Runs this server's own worked example end to end — one of its real tools, on a canned input taken from this host's own published data — and returns exactly the structuredContent a real call returns, not a mock and not a descri
Mostrare il risultato
Questo badge segue le tue letture: cambia quando cambia la tua card. Incollalo nel tuo README.
Markdown
[](https://kopass.app/a2a/validator?url=https://www.pathwren.workers.dev)HTML
<a href="https://kopass.app/a2a/validator?url=https://www.pathwren.workers.dev"><img src="https://kopass.app/a2a/badge/aHR0cHM6Ly93d3cucGF0aHdyZW4ud29ya2Vycy5kZXY.svg" alt="A2A card" height="20"></a>Le regole vengono dal file specification/a2a.proto del protocollo, dove ogni campo obbligatorio è marcato come tale. Nulla viene aggiunto.
Le card lette qui alimentano la rilevazione quotidiana di KoPass: 228 agenti seguiti, di cui 220 hanno risposto all'ultimo passaggio.