Prompt-injection check (x402)

com.onrender.prompt-injection-checkPublished by prompt-injection-check.onrender.comOfficial publisherv0.7.0Updated Oct 25, 2026

Prompt-injection check and safe web fetch for agents, span offsets. Free trial, then $0.005 x402.

VerifiedStreamable HTTPWeb executableWeb Search & ScrapingSecurity & Monitoring

Overview

AI-generated overview

Remote MCP server that checks untrusted text or web pages for prompt injection and returns verdicts, scores and evidence spans.

What you can do
Check untrusted texts or URLs for prompt injection before an agent acts on them, with verdict, score, intents, a summary and evidence spans with character offsets, weighing hidden HTML and invisible characters. Fetch 1 to 10 public https pages and get status, title, clean markdown, a verdict, evidence spans and a safe_markdown version with flagged sentences removed, respecting robots.txt. Run free trial checks on one text or one URL, limited to 3 calls per source per UTC day. Replay a published known-answer set of 24 cases to verify the detector before paying.
When to use it
Useful when an assistant ingests untrusted content such as scraped pages, user-supplied text or fetched URLs and you want a pre-screen for injection attempts before acting on it. The free trial and selftest let you evaluate the detector before committing to paid calls.
Requirements
A remote streamable HTTP endpoint; no local runtime, account or API key is declared. Paid tools require payment in USDC on Base via x402 at $0.005 per item or per fetched URL. Network access to the endpoint and to the pages being fetched is needed.
Before you install
Paid tools spend money: $0.005 USDC per checked item or fetched URL, settled on Base via x402, so costs scale with volume. The server fetches public web pages on your behalf and sends the text you submit to a third-party service for analysis. Free trial calls are capped at 3 per source per UTC day, and failed fetches still count.

Installation

In SourceWeft

  1. Open Prompt-injection check (x402) in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/com.onrender.prompt-injection-check%2Fprompt-injection-check/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config.

{
  "mcpServers": {
    "prompt-injection-check-x402": {
      "type": "http",
      "url": "https://prompt-injection-check.onrender.com/mcp"
    }
  }
}

Tools

5

check_prompt_injection

Prompt-injection check (paid, x402)

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.

ParametersmodeurlstextsthresholdincludeSanitizedText

fetch_and_check

Fetch web pages as markdown with a prompt-injection check (paid, x402)

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.

ParametersurlsrequiredthresholdincludeMarkdown

try_check_prompt_injection

Free trial: prompt-injection check on your own text

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.

ParameterstextrequiredthresholdincludeSanitizedText

try_fetch_and_check

Free trial: fetch one web page with a prompt-injection check

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.

ParametersurlrequiredthresholdincludeMarkdown

selftest

Free self-test

Free. Replays the published known-answer set v1.2 (24 cases) and returns score and sha256, so you can verify the detector before paying.

Parametersdetails

Version history

2
  1. v0.7.0LatestOct 25, 2026
  2. v0.6.0Oct 25, 2026

Score

72% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listedRequired15 pts
  • DescriptionRequired15 pts
  • Logo10 pts

    Publish an icon in the registry entry.

  • Documentation15 pts

    Declare a GitHub repository with a README, or serve resource_documentation in the OAuth protected-resource metadata.

  • LicenseNot applicable

    A hosted service is used under its provider's terms, so no license is expected here. This check is left out of the percentage.