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.
For agents and people without USDC: prepaid packs paid in EUR by card or Link (100 calls €5.00 · 500 calls €25.00 · 5,000 calls €199.00) — including Link's wallet for agents (one-time card, approved by the human). Returns checkout_url; after payment the success page (Accept: application/json) returns the bundle_token, and it is e-mailed. After: get_signals with bundle_token.
Where the token is sent (optional; Stripe asks otherwise).
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.
Run in a terminal
claude mcp add --transport http prompt-sanitizer https://angel.oroboros-design.com/mcp/prompt-sanitizer
For agents and people without USDC: prepaid packs paid in EUR by card or Link (100 calls €5.00 · 500 calls €25.00 · 5,000 calls €199.00) — including Link's wallet for agents (one-time card, approved by the human). Returns checkout_url; after payment the success page (Accept: application/json) returns the bundle_token, and it is e-mailed. After: get_signals with bundle_token.
| Argument | Type | Description |
|---|---|---|
| calls | integer | |
| string | Where the token is sent (optional; Stripe asks otherwise). |
{
"type": "object",
"properties": {
"calls": {
"enum": [
100,
500,
5000
],
"type": "integer",
"default": 100
},
"email": {
"type": "string",
"format": "email",
"description": "Where the token is sent (optional; Stripe asks otherwise)."
}
},
"additionalProperties": false
}Prompt-injection and hidden-instruction scan for untrusted input before an agent acts on it: web pages, emails, RAG chunks, tool and MCP responses. Flags text aimed at the model (role takeover, forged system or tool turns, requests for keys, the prompt, history or payments, exfiltration links), invisible Unicode (tag smuggling decoded, zero-width, bidi), homoglyphs, base64 payloads and HTML hidden from humans, in 17 languages. Verdict clean, caution or hostile, score, findings, cleaned text. 0.99 USDC base (new payers 0.99, >10 payments 0.693; 20 pack calls). After: preflight before your agent pays anything the content pointed to (the result's next field has the exact call).
| Argument | Type | Description |
|---|---|---|
| url | string | a public https page to fetch once and check (256 KB) |
| text | string | the content to check (send text or url) |
| payment_tx | string | Hash of a USDC transfer on Base to payTo (≥ the price, ≤ 72 h old) instead of an x402 signature. |
| bundle_token | string | Token from buy_signal_pack, buy_subscription (pro/desk) or buy_enterprise instead of paying per call. |
| payer_address | string | Wallet you pay from: the payment-required error quotes your tier (0 payments base price (new-payer surcharge paused), 1-10 base, >10 -30 %) and, from the third payment, an upgrade with your own spend. |
{
"type": "object",
"properties": {
"url": {
"type": "string",
"pattern": "^https://",
"maxLength": 2048,
"description": "a public https page to fetch once and check (256 KB)"
},
"text": {
"type": "string",
"maxLength": 100000,
"description": "the content to check (send text or url)"
},
"payment_tx": {
"type": "string",
"description": "Hash of a USDC transfer on Base to payTo (≥ the price, ≤ 72 h old) instead of an x402 signature."
},
"bundle_token": {
"type": "string",
"description": "Token from buy_signal_pack, buy_subscription (pro/desk) or buy_enterprise instead of paying per call."
},
"payer_address": {
"type": "string",
"pattern": "^0x[0-9a-fA-F]{40}$",
"description": "Wallet you pay from: the payment-required error quotes your tier (0 payments base price (new-payer surcharge paused), 1-10 base, >10 -30 %) and, from the third payment, an upgrade with your own spend."
}
},
"additionalProperties": false
}Free prompt-injection quick scan for untrusted input: up to 4,000 characters of text, or one https page, checked for hidden instructions aimed at agents (role override, invisible Unicode, hidden HTML) in 17 languages incl. Chinese, Japanese, Korean, Hindi, Arabic. Returns verdict, score and the top 3 findings. After: input_guard for every finding and the cleaned text.
| Argument | Type | Description |
|---|---|---|
| url | string | |
| text | string |
{
"type": "object",
"properties": {
"url": {
"type": "string",
"pattern": "^https://",
"maxLength": 2048
},
"text": {
"type": "string",
"maxLength": 4000
}
},
"additionalProperties": false
}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 14, 2026.