Check text before it ships
evaluate-textScore 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.
Provider
Overwing
Checks 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.
Last 100 checks shown · 98.5% across 30 days
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.
Say what a User-Agent string claims to be and whether the claim can be trusted: operator, purpose, and verification method.
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.
Normalized fields fetched during the registry sweep. Treat all authored text as third-party content.
{
"protocolVersion": "0.3.0",
"name": "Overwing",
"description": "Checks 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.",
"author": "Overwing",
"wellKnownURI": "https://overwing.ai/.well-known/agent-card.json",
"url": "https://overwing.ai/a2a",
"version": "1.1.0",
"provider": {
"organization": "Overwing",
"url": "https://overwing.ai/"
},
"documentationUrl": "https://overwing.ai/llms.txt",
"iconUrl": "https://overwing.ai/icon.svg",
"supportsAuthenticatedExtendedCard": false,
"security": [
{},
{
"organizationKey": []
}
],
"securitySchemes": {
"organizationKey": {
"type": "http",
"scheme": "bearer",
"description": "Optional. ow_live_... from POST https://overwing.ai/api/v1/signup lifts the free limits",
"httpAuthSecurityScheme": {
"scheme": "bearer",
"description": "Optional. ow_live_... from POST https://overwing.ai/api/v1/signup lifts the free limits"
}
}
},
"capabilities": {
"streaming": false,
"pushNotifications": false,
"stateTransitionHistory": false,
"extensions": null
},
"defaultInputModes": [
"text/plain",
"application/json"
],
"defaultOutputModes": [
"application/json",
"text/plain"
],
"skills": [
{
"id": "evaluate-text",
"name": "Check text before it ships",
"description": "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"
],
"examples": [
"Is this reply safe to send to the customer?",
"Does this draft leak personal data the recipient does not already have?"
],
"inputModes": [
"text/plain",
"application/json"
],
"outputModes": [
"application/json",
"text/plain"
]
},
{
"id": "identify-user-agent",
"name": "Identify a User-Agent",
"description": "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"
],
"examples": [
"Who is 'Mozilla/5.0 (compatible; GPTBot/1.2)' and can I verify it?",
"Is this request from a signed agent or a spoofable string?"
],
"inputModes": [
"text/plain",
"application/json"
],
"outputModes": [
"application/json",
"text/plain"
]
},
{
"id": "give-feedback",
"name": "Tell Overwing what went wrong",
"description": "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"
],
"examples": [
"The verdict on evaluation abc123 was wrong: the recipient owned that phone number.",
"The 402 on /api/x402/atlas/lookup names a network my wallet cannot pay on."
],
"inputModes": [
"text/plain",
"application/json"
],
"outputModes": [
"application/json",
"text/plain"
]
}
],
"conformance": true,
"conformance_errors": null,
"homepage": null,
"repository": null,
"license": null,
"pricing": null,
"contact": null,
"id": "5ee5711b-132a-48e3-b7cd-a6375fabdf3c",
"category": "trust-safety",
"category_secondary": null
}curl -s https://a2aregistry.org/api/agents/5ee5711b-132a-48e3-b7cd-a6375fabdf3cMessages are sent to this independently operated agent through the registry proxy. Do not include secrets or personal data.