Three fast safety checks for agents, each with a signed hash-chained receipt: (1) prompt-injection c
Maintain this server? Claim it
Call this server's tools from your browser. Nothing to install.
Requests go through mcptry because browsers can't call most MCP servers directly. Header values are sent to the server for that request only and are never stored or logged.
Tool list from our last check. Connect live to refresh it.
Machine-readable catalog with prices and 402 terms
This tool takes no arguments.
This tool isn't marked read-only, so it may change something on the server or in an account you connected.
Pick your client. Values in capitals, like YOUR_TOKEN, are yours to fill in.
claude mcp add --transport http agent-safety https://sml-agent-products.onrender.com/agent-safety/mcp
Machine-readable catalog with prices and 402 terms
No arguments.
{
"type": "object",
"properties": {}
}Prompt-injection check ($0.004 via x402 at POST https://sml-agent-products.onrender.com/agent-safety/v1/prompt-injection). POST {text}. Verdict safe/suspicious/malicious + score + categories + matched spans + obfuscation tricks found + recommendation.
| Argument | Type | Description |
|---|---|---|
| text* | string | Agent-bound text to classify |
{
"type": "object",
"required": [
"text"
],
"properties": {
"text": {
"type": "string",
"maxLength": 100000,
"description": "Agent-bound text to classify"
}
}
}URL safety check ($0.004 via x402 at GET https://sml-agent-products.onrender.com/agent-safety/v1/url-safety). GET ?url=. Verdict safe/suspicious/dangerous + score + reasons (lookalike, brand impersonation, domain age, redirects, seed-phrase/drainer content, agent-targeted injection).
| Argument | Type | Description |
|---|---|---|
| url* | string |
{
"type": "object",
"required": [
"url"
],
"properties": {
"url": {
"type": "string",
"format": "uri"
}
}
}x402 endpoint health / pay-readiness ($0.002 via x402 at GET https://sml-agent-products.onrender.com/agent-safety/v1/x402-health). GET ?url=&method=GET|POST&maxUsd=. Live probe (never pays): go/caution/no_go, recommended payment option, every accepts problem, discovery + bazaar metadata, latency.
| Argument | Type | Description |
|---|---|---|
| url* | string | |
| maxUsd | number | |
| method | string |
{
"type": "object",
"required": [
"url"
],
"properties": {
"url": {
"type": "string"
},
"maxUsd": {
"type": "number"
},
"method": {
"enum": [
"GET",
"POST"
],
"type": "string"
}
}
}We read every tool's name, description and inputs the way the model will, looking for instructions hidden from you. A clean result means no warning signs, not a guarantee. Scanned Nov 3, 2026.
No readOnlyHint / destructiveHint annotations, so clients can't tell a read from a write without asking.
Fix: Add annotations to each tool, e.g. { readOnlyHint: true } for tools that only read.
What changed in this server's tools since we started watching, newest first. Each change is scanned again.
x402 endpoint health / pay-readiness ($0.002 via x402 at GET https://sml-agent-safety.onrender.com/v1/x402-health).https://sml-agent-products.onrender.com/agent-safety/v1/x402-health). GET ?url=&method=GET|POST&maxUsd=. Live probe (never pays): go/caution/no_go, recommended payment option, every accepts problem, discovery + bazaar metadata, latency.
URL safety check ($0.004 via x402 at GET https://sml-agent-safety.onrender.com/v1/url-safety).https://sml-agent-products.onrender.com/agent-safety/v1/url-safety). GET ?url=. Verdict safe/suspicious/dangerous + score + reasons (lookalike, brand impersonation, domain age, redirects, seed-phrase/drainer content, agent-targeted injection).
Prompt-injection check ($0.004 via x402 at POST https://sml-agent-safety.onrender.com/v1/prompt-injection).https://sml-agent-products.onrender.com/agent-safety/v1/prompt-injection). POST {text}. Verdict safe/suspicious/malicious + score + categories + matched spans + obfuscation tricks found + recommendation.