Prompt-injection check, safe web fetch, and skill-pack audit for agents. Free trial, then x402.
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.
Check untrusted texts or URLs for prompt injection before your agent reads them. Per item: verdict (safe, suspicious, injection), score, intents, a one-sentence human_summary and evidence spans with code point, UTF-8 byte and UTF-16 offsets. Hidden HTML and invisible characters are weighed. Deterministic rules for EN, with override and agent-addressed phrases also in NL and DE; a clean verdict is not a guarantee. Try it free first with try_check_prompt_injection (3 calls a day). Costs $0.005 USDC per item on Base via x402: the first call without payment returns the payment requirements; pay with an x402-capable MCP client (_meta['x402/payment']) or call POST https://prompt-injection-check.onrender.com/check over HTTP x402.
fast = deterministic rules (EN, NL, DE). full runs as fast on this instance.
public http(s) URLs to fetch and check (max 3 MB each)
texts your agent is about to read
Tool list last changed Oct 25, 2026.
Check untrusted texts or URLs for prompt injection before your agent reads them. Per item: verdict (safe, suspicious, injection), score, intents, a one-sentence human_summary and evidence spans with code point, UTF-8 byte and UTF-16 offsets. Hidden HTML and invisible characters are weighed. Deterministic rules for EN, with override and agent-addressed phrases also in NL and DE; a clean verdict is not a guarantee. Try it free first with try_check_prompt_injection (3 calls a day). Costs $0.005 USDC per item on Base via x402: the first call without payment returns the payment requirements; pay with an x402-capable MCP client (_meta['x402/payment']) or call POST https://prompt-injection-check.onrender.com/check over HTTP x402.
| Argument | Type | Description |
|---|---|---|
| mode | string | fast = deterministic rules (EN, NL, DE). full runs as fast on this instance. |
| urls | array | public http(s) URLs to fetch and check (max 3 MB each) |
| texts | array | texts your agent is about to read |
| threshold | number | |
| includeSanitizedText | boolean |
{
"type": "object",
"properties": {
"mode": {
"enum": [
"fast",
"full"
],
"type": "string",
"default": "fast",
"description": "fast = deterministic rules (EN, NL, DE). full runs as fast on this instance."
},
"urls": {
"type": "array",
"items": {
"type": "string",
"format": "uri"
},
"description": "public http(s) URLs to fetch and check (max 3 MB each)"
},
"texts": {
"type": "array",
"items": {
"type": "string"
},
"description": "texts your agent is about to read"
},
"threshold": {
"type": "number",
"default": 0.5,
"maximum": 1,
"minimum": 0.05
},
"includeSanitizedText": {
"type": "boolean",
"default": true
}
},
"description": "1 to 20 items (texts plus urls). Price: $0.005 per item, paid with x402 (USDC on Base)."
}Static permission report for an agent skill pack. Send files (a list of {path, content}, up to 30) or one public https url to a raw file. Per finding, with file and line: network destinations, files and paths read/written/deleted (~/.ssh, ~/.aws, .env, browser profiles, wallets), secrets and env vars read, shell commands and installs (curl|sh, sudo, rm -rf), and instructions aimed at the agent the buyer did not ask for (plus hidden and base64 text). Returns a risk level and a plain summary of what the pack can do with the human's accounts. Deterministic, no code run; not a guarantee. Try free first with try_check_skill_pack. $0.01 USDC per pack on Base via x402: the first call without payment returns the requirements; pay with an x402 MCP client (_meta['x402/payment']) or POST https://prompt-injection-check.onrender.com/skill-check.
| Argument | Type | Description |
|---|---|---|
| url | string | alternatively, one public https URL to a single raw text file (SKILL.md or a script); archives are not unpacked |
| files | array | the pack's files (up to 30 files, 200000 bytes total) |
{
"type": "object",
"properties": {
"url": {
"type": "string",
"format": "uri",
"pattern": "^https://",
"description": "alternatively, one public https URL to a single raw text file (SKILL.md or a script); archives are not unpacked"
},
"files": {
"type": "array",
"items": {
"type": "object",
"required": [
"path",
"content"
],
"properties": {
"path": {
"type": "string",
"maxLength": 300,
"description": "the file's path in the pack, e.g. SKILL.md or scripts/run.sh"
},
"content": {
"type": "string",
"description": "the file's text content"
}
}
},
"maxItems": 30,
"minItems": 1,
"description": "the pack's files (up to 30 files, 200000 bytes total)"
}
},
"description": "give files (a list of {path, content}) OR url (one public https file); price $0.01 per pack"
}Fetch 1 to 10 public https pages in one call. Per URL: status, final_url, title, clean markdown, verdict (safe, suspicious, injection), intents, evidence spans (offsets into the markdown or the raw HTML for hidden content) and safe_markdown with flagged sentences removed. robots.txt is respected. Fetch plus check in one call. Free trial with your own URL: try_fetch_and_check. Costs $0.005 USDC per URL fetched successfully on Base via x402; failed URLs are free. The first call without payment returns the payment requirements for the URLs that were fetched; pay with an x402-capable MCP client (_meta['x402/payment']) or POST https://prompt-injection-check.onrender.com/fetch-check.
| Argument | Type | Description |
|---|---|---|
| urls* | array | 1 to 10 public https URLs |
| threshold | number | |
| includeMarkdown | boolean | false leaves out the raw markdown and keeps only safe_markdown |
{
"type": "object",
"required": [
"urls"
],
"properties": {
"urls": {
"type": "array",
"items": {
"type": "string",
"format": "uri",
"pattern": "^https://"
},
"maxItems": 10,
"minItems": 1,
"description": "1 to 10 public https URLs"
},
"threshold": {
"type": "number",
"default": 0.5,
"maximum": 1,
"minimum": 0.05
},
"includeMarkdown": {
"type": "boolean",
"default": true,
"description": "false leaves out the raw markdown and keeps only safe_markdown"
}
},
"description": "price = number of URLs fetched successfully x $0.005; failed URLs are free"
}Free. Replays the published known-answer set v1.2 (24 cases) and returns score and sha256, so you can verify the detector before paying.
| Argument | Type | Description |
|---|---|---|
| details | boolean |
{
"type": "object",
"properties": {
"details": {
"type": "boolean",
"default": false
}
}
}Free, no payment. Same check and same output as check_prompt_injection for 1 text of at most 4000 characters, plus a trial object with remaining_today and how to upgrade. 3 free calls per source per UTC day, shared with try_fetch_and_check and POST https://prompt-injection-check.onrender.com/try/check; after that the tool returns an error with the paid route.
| Argument | Type | Description |
|---|---|---|
| text* | string | your own text, max 4000 characters (or texts with exactly 1 item) |
| threshold | number | |
| includeSanitizedText | boolean |
{
"type": "object",
"required": [
"text"
],
"properties": {
"text": {
"type": "string",
"maxLength": 4000,
"minLength": 1,
"description": "your own text, max 4000 characters (or texts with exactly 1 item)"
},
"threshold": {
"type": "number",
"default": 0.5,
"maximum": 1,
"minimum": 0.05
},
"includeSanitizedText": {
"type": "boolean",
"default": true
}
}
}Free, no payment. Same report and output as check_skill_pack for 1 pack (files or url), plus a trial object. 3 free calls per source per UTC day, shared with the other try_ tools; after that the tool returns an error with the paid route.
| Argument | Type | Description |
|---|---|---|
| url | string | alternatively, one public https URL to a single raw text file (SKILL.md or a script); archives are not unpacked |
| files | array | the pack's files (up to 30 files, 200000 bytes total) |
{
"type": "object",
"properties": {
"url": {
"type": "string",
"format": "uri",
"pattern": "^https://",
"description": "alternatively, one public https URL to a single raw text file (SKILL.md or a script); archives are not unpacked"
},
"files": {
"type": "array",
"items": {
"type": "object",
"required": [
"path",
"content"
],
"properties": {
"path": {
"type": "string",
"maxLength": 300,
"description": "the file's path in the pack, e.g. SKILL.md or scripts/run.sh"
},
"content": {
"type": "string",
"description": "the file's text content"
}
}
},
"maxItems": 30,
"minItems": 1,
"description": "the pack's files (up to 30 files, 200000 bytes total)"
}
},
"description": "give files (a list of {path, content}) OR url (one public https file); price $0.01 per pack"
}Free, no payment. Same fetcher, safety rules and output as fetch_and_check for 1 public https URL, plus a trial object. 3 free calls per source per UTC day, shared with try_check_prompt_injection; failed fetches also use a call.
| Argument | Type | Description |
|---|---|---|
| url* | string | 1 public https URL (or urls with exactly 1 item) |
| threshold | number | |
| includeMarkdown | boolean |
{
"type": "object",
"required": [
"url"
],
"properties": {
"url": {
"type": "string",
"format": "uri",
"pattern": "^https://",
"description": "1 public https URL (or urls with exactly 1 item)"
},
"threshold": {
"type": "number",
"default": 0.5,
"maximum": 1,
"minimum": 0.05
},
"includeMarkdown": {
"type": "boolean",
"default": true
}
}
}