InjectScan MCP server

• scan_textFree

  Scans untrusted text for prompt injection before your agent reads or acts on it: web page text, emails, documents, tool results or another agent's message. Flags instruction overrides, jailbreak personas, system-prompt extraction, fake delimiters, exfiltration URLs, tool hijacking, hidden Unicode and encoded payloads (deterministic rules). Use scan_url when you only have a link (it also checks hidden HTML) and scan_tools for MCP tool definitions. Text up to 100000 characters. Free: 30 calls/day per IP shared by scan_text, scan_url and scan_tools, with full results (max 10/min; invalid input is not counted). After that the tool returns an error with the x402 pay URL ($0.003 USDC on Base, Polygon, Arbitrum One or Solana per call at https://api.youraitools.co/injectscan/v1/scan) or prepaid credits. Returns risk_score (0-100), verdict (safe | suspicious | malicious), flagged, categories[] {category, score, description}, findings[] {rule, category, start, end, text} and free_tier usage. Read-only safety signal, not a guarantee.

• scan_toolsFree

  Checks MCP / function-calling tool definitions for tool poisoning (hidden instructions, data-exfiltration requests, hijack attempts in names, descriptions and schemas) before your agent installs or calls them. Use scan_text for ordinary content and scan_url for web pages. Up to 100 tools per call. Free: 30 calls/day per IP shared by scan_text, scan_url and scan_tools, with full results (max 10/min; invalid input is not counted). After that the tool returns an error with the x402 pay URL ($0.003 USDC on Base, Polygon, Arbitrum One or Solana per call at https://api.youraitools.co/injectscan/v1/scan) or prepaid credits. Returns the worst risk_score/verdict, flagged, tools_scanned, tools_flagged and tools[] {index, name, risk_score, verdict, categories, findings[] {field, rule, text}}. Read-only safety signal, not a guarantee.

• scan_urlFree

  Fetches a public web page and scans its visible text plus hidden HTML (comments, hidden elements, alt/aria/meta text) for prompt injection, before your agent browses or summarizes it. Use scan_text if you already have the content and scan_tools for MCP tool definitions. Respects robots.txt and refuses private/internal hosts. Free: 30 calls/day per IP shared by scan_text, scan_url and scan_tools, with full results (max 10/min; invalid input is not counted). After that the tool returns an error with the x402 pay URL ($0.003 USDC on Base, Polygon, Arbitrum One or Solana per call at https://api.youraitools.co/injectscan/v1/scan) or prepaid credits. Returns risk_score (0-100), verdict (safe | suspicious | malicious), flagged, categories[] {category, score, description}, findings[] with location (visible or hidden), url, finalUrl, title, hidden_html {segments_checked, flagged} and page {status, contentType}. Read-only safety signal, not a guarantee.

• –Code scanremote-only server, no package to scann/a
• Live reliabilityremote reachable in 705ms20/20
• Tool poisoning3 tool descriptions checked15/15
• Auth qualityopen endpoint, read-only tools10/15
• Maintenanceno repository listed3/15
• Maintainer identityendpoint served from the registry-verified namespace domain8/10

Safety score

75/100

higher than 50% of 1,761 Finance servers

Tools

3

the typical Finance server has 8

Tools that change things

0%

typical: 0%. Fewer write tools means less an agent can break

Uptime

100%

of our recent checks; the typical remote Finance server answers 100%

Response time

244 ms

faster than 58% of 1,133 Finance servers

InjectScan: common questions

Is InjectScan MCP server safe?

Mostly: it is graded B (75/100). Read the InjectScan safety report

How do I install InjectScan?

It runs remotely at api.youraitools.co. Add it to Claude Code, Cursor, VS Code or Claude Desktop with the snippets above, or call it through the mcp.market gateway without installing anything.

Does InjectScan need an API key?

Not as far as the registry entry and our scan can tell: no credentials are declared or required.

Is InjectScan maintained?

The latest release is v0.1.3.

Is InjectScan up?

100% of our last 28 checks got an answer. We check remote servers about four times a day.

What can I use instead of InjectScan?

Servers from other publishers that do the same job: HPSILab Quant Finance MCP server, Quantum Readiness Scan MCP server and Pulsefeed X402 MCP server.

How does InjectScan compare with other Finance MCP servers?

safety score 75/100 (higher than 50% of 1,761 Finance servers); tools 3 (the typical Finance server has 8); tools that change things 0% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.