← BrowseAI/LLM

Prompt-Injection Check ✓ Verified Official

by FiatDock · $0.0045 / call

About this service

A pay-per-call MCP tool that scans text an agent is about to read — a web page, an email, a tool description, another agent's message — for the shapes that hijack agents: instruction-override phrasing, a redefined system role, requests to move credentials, hidden directive tags and invisible Unicode. Returns a verdict and every pattern found; the same ruleset scans every FiatDock marketplace listing. Pattern-based, not a guarantee. Tool: prompt_injection_check — $0.0045 USDC/call via x402 (paid automatically by the fiatdock-mcp package). Nothing is stored.

securityprompt-injectionai-safetyagentstextx402

Tools included — 39

Reported by this server's own tools/list, refreshed automatically.

get_quoteget_order_statustoken_pricesearch_servicesget_servicesearch_x402create_offramp_sessioncreate_onramp_sessiontoken_safetystablecoin_intelgas_priceblock_numbereth_balanceusdc_balancetoken_metadatatx_statusaddress_inteltoken_reportweb_reademail_checkperp_marketprediction_marketsdefi_yieldsfx_rateswallet_portfoliotoken_holdersdomain_intelsite_contactscrypto_newssec_filingsprompt_injection_checktoken_screenerpaper_searchsatellite_scenesseo_auditx402_top_servicesens_resolvecall_servicecall_x402

Add to your agent

Paste this into your MCP client config (e.g. Claude Desktop, Cursor). Click the block to select all, then copy.

{
  "mcpServers": {
    "prompt-injection-check": {
      "url": "https://fiatdock.com/mcp"
    }
  }
}

Endpoint: https://fiatdock.com/mcp · networks: base · PAID — $0.0045/call via x402 at this endpoint (unpaid calls answer HTTP 402 with the exact requirements)

Reviews — none yet

Only buyers who completed a paid call can review — verified purchases only.