Agent security pre-checks: prompt-injection scan, MCP tool-poisoning scan, x402 endpoint check.
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.
Free. What Prescan does, prices of the paid tools and HTTP endpoints, and links to docs.
This tool takes no arguments.
Pick your client. Values in capitals, like YOUR_TOKEN, are yours to fill in.
claude mcp add --transport http prescan https://prescan.canisell.xyz/mcp
Free. What Prescan does, prices of the paid tools and HTTP endpoints, and links to docs.
No arguments.
{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {}
}Is this x402 endpoint safe to pay? Fetches its 402 terms with one GET (never pays) and checks: payTo validity and EIP-55 checksum, zero/token-contract/OFAC-sanctioned payTo, asset is canonical USDC for the network, amount vs your budget, price vs the price advertised in its OpenAPI and on x402scan, payTo vs the one x402scan recorded, HTTPS, redirects, resource host, domain age (RDAP), tunnels/shared hosts. Returns go/caution/no_go, the recommended payment option and findings. Costs $0.003 USDC per call via x402 (charged only on success). Without an x402 wallet you get the payment terms and the paid HTTP URL instead.
| Argument | Type | Description |
|---|---|---|
| url* | string | The x402 endpoint you are about to pay (full URL incl. query). Only GET is sent; nothing is paid. |
| max_usd | number | Your budget per call in USD; above it the verdict is no_go. |
| network | string | Preferred network, CAIP-2 (eip155:8453) or v1 name (base). |
{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"url"
],
"properties": {
"url": {
"type": "string",
"maxLength": 2000,
"minLength": 8,
"description": "The x402 endpoint you are about to pay (full URL incl. query). Only GET is sent; nothing is paid."
},
"max_usd": {
"type": "number",
"maximum": 1000000,
"description": "Your budget per call in USD; above it the verdict is no_go.",
"exclusiveMinimum": 0
},
"network": {
"type": "string",
"maxLength": 80,
"description": "Preferred network, CAIP-2 (eip155:8453) or v1 name (base)."
}
}
}Free. The detection categories, rule counts and thresholds used by scan_text and scan_tools.
No arguments.
{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {}
}Free. Prompt-injection pre-check for up to 1000 characters: verdict (safe/suspicious/malicious), score, categories and rule ids. For spans, a sanitized copy, long texts or batches use scan_text (paid).
| Argument | Type | Description |
|---|---|---|
| text* | string | Text to check, up to 1000 characters |
| source | string | Where the text comes from; tunes a few rules (token_metadata flags any URL in a token name). |
{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"text"
],
"properties": {
"text": {
"type": "string",
"maxLength": 1000,
"description": "Text to check, up to 1000 characters"
},
"source": {
"enum": [
"web_page",
"email",
"tool_output",
"document",
"chat_message",
"token_metadata",
"code",
"other"
],
"type": "string",
"description": "Where the text comes from; tunes a few rules (token_metadata flags any URL in a token name)."
}
}
}Prompt-injection pre-check for text your agent is about to read (tool output, web page, email, document, token names/metadata). Deterministic rules, no LLM: instruction override (EN/DE/FR/ES/IT/PT/PL/RU), role hijack, jailbreaks, system-prompt extraction, fake chat delimiters, text addressed to the AI, concealment, data exfiltration (markdown-image beacons, secrets to URLs), tool/fund hijack (shell pipes, transfers, unlimited approvals, skip-confirmation), crypto lures (seed-phrase requests, claim/airdrop links), hidden text (zero-width, Unicode tag and variation-selector smuggling, bidi, homoglyphs, CSS-hidden HTML, ANSI) and encoded payloads (base64/hex/percent decoded and re-scanned). Returns verdict safe/suspicious/malicious, action allow/treat_as_untrusted_data/block, 0-100 score, findings with character spans, risky links, decoded payloads and a sanitized copy. Batch up to 100 texts per call. Costs $0.002 USDC per call via x402 (charged only on success). Without an x402 wallet you get the payment terms and the paid HTTP URL instead.
| Argument | Type | Description |
|---|---|---|
| text | string | Text to scan, up to 100000 characters. Use either text or items. |
| items | array | Batch: up to 100 texts (e.g. token names, search results, emails), 200000 characters in total, one price. |
| source | string | Where the text comes from; tunes a few rules (token_metadata flags any URL in a token name). |
| sanitize | boolean | Return `sanitized`: the text with invisible characters removed and injected instructions replaced by a marker. Default true. |
Tool-poisoning scan of MCP tool definitions (a tools/list result) or function schemas before your agent connects or calls them: hidden <IMPORTANT> instructions, cross-tool shadowing, side-channel parameters that ask for file/conversation contents, recipient/payee overrides, instructions hidden in parameter names, defaults or enums, Unicode/ANSI smuggling, duplicate or lookalike tool names. Per-tool verdict and findings with location, plus capability flags (shell, files, network, payments, messaging). Costs $0.002 USDC per call via x402 (charged only on success). Without an x402 wallet you get the payment terms and the paid HTTP URL instead.
| Argument | Type | Description |
|---|---|---|
| tools* | array | Tool definitions as returned by MCP tools/list (or OpenAI/Anthropic function schemas), up to 200. |
| server | object | Optional label echoed back. |
{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"tools"
],
"properties": {
"tools": {
"type": "array",
"items": {
"type": "object",
"required": [
"name"
],
"properties": {
"name": {
"type": "string",
"maxLength": 200,
"minLength": 1
},
"title": {
"type": "string",
"maxLength": 1000
},
"parameters": {},
"description": {
"type": "string",
"maxLength": 100000
},
"inputSchema": {},
"input_schema": {}
},
"additionalProperties": {}
},
"maxItems": 200,
"minItems": 1,
"description": "Tool definitions as returned by MCP tools/list (or OpenAI/Anthropic function schemas), up to 200."
},
"server": {
"type": "object",
"properties": {
"url": {
"type": "string",
"maxLength": 2000
},
"name": {
"type": "string",
"maxLength": 200
}
},
"description": "Optional label echoed back."
}
}
}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 2, 2026.
{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {
"text": {
"type": "string",
"maxLength": 100000,
"description": "Text to scan, up to 100000 characters. Use either text or items."
},
"items": {
"type": "array",
"items": {
"type": "object",
"required": [
"text"
],
"properties": {
"id": {
"type": "string",
"maxLength": 200
},
"text": {
"type": "string",
"maxLength": 100000
},
"source": {
"enum": [
"web_page",
"email",
"tool_output",
"document",
"chat_message",
"token_metadata",
"code",
"other"
],
"type": "string",
"description": "Where the text comes from; tunes a few rules (token_metadata flags any URL in a token name)."
}
}
},
"maxItems": 100,
"description": "Batch: up to 100 texts (e.g. token names, search results, emails), 200000 characters in total, one price."
},
"source": {
"enum": [
"web_page",
"email",
"tool_output",
"document",
"chat_message",
"token_metadata",
"code",
"other"
],
"type": "string",
"description": "Where the text comes from; tunes a few rules (token_metadata flags any URL in a token name)."
},
"sanitize": {
"type": "boolean",
"description": "Return `sanitized`: the text with invisible characters removed and injected instructions replaced by a marker. Default true."
}
}
}