Skip to content

AI tools, MCP servers and agent skills for prompt injection

83 MCP servers, 2 agent skills and 1 AI tool for prompt injection in security, including SkillSpector, Agent governance and Agentic actions auditor, most popular first. 37 of the 86 are listed as free or open source. Each one is written up from its own site or README, with pricing, platforms and alternatives.

Showing 1–30 of 33

  1. Flockward

    MCP server

    Free link and site safety checks that warn agents about prompt-injection traps

    • 10 tools
    • Remote
    • Free
    • Security
  2. Check user prompts for injection and jailbreaks with a guard that learns from your labels

    • 3 tools
    • Remote
    • Freemium
    • AI models and LLM tooling
  3. CORDON

    MCP server

    Reads web pages for agents as clean markdown with hidden instructions stripped

    Not checked yet
    • 2 tools
    • Remote
    • Freemium
    • Security
  4. Verified email for AI agents: checked inbound mail, held sends and disposable inboxes

    Not checked yet
    • 5 tools
    • Remote
    • Free
    • Communication
  5. Boardcheck

    MCP server

    Flags fake engagement and prompt injection in AI-agent job board listings

    Runs locally
    • Open source
    • Security
  6. TAR Engine

    MCP server

    Audit AI agent skills for safety with static, semantic, adversarial and supply-chain scans

    Runs locally
    • 1 tool
    • Freemium
    • Security
  7. Toolproof

    MCP server

    Safety grades for MCP servers and APIs, with wrap and lockfile modes to catch tool changes

    Runs locally
    • 1 tool
    • Free
    • Security
  8. Xray

    MCP server

    Scan text or files for hidden Unicode, decoded ASCII smuggling and look-alike letters

    Not checked yet
    • 1 tool
    • Remote
    • Free
    • Security
  9. SkillTotal

    MCP server

    Static security scanner for MCP servers, agent skills and npm or PyPI packages

    Runs locally
    • Open source
    • Security
  10. Exepal

    MCP server

    Safety checks for AI agents: page reading, prompt injection, secrets and PII scans

    Not checked yet
    • 1 tool
    • Remote
    • Freemium
    • Security
  11. The Agent Forge

    MCP server

    Check MCP servers, skills and packages for advisories before your agent installs them

    Not checked yet
    • 6 tools
    • Remote
    • Free
    • Security
  12. SafeToClone

    MCP server

    Grades any public GitHub repo A to F for safety, in plain English, before you install it

    Not checked yet
    • Remote
    • Free
    • Security
  13. Scan prompts, tool definitions and model output for injection, and guard tool calls

    Runs locally
    • Open source
    • AI models and LLM tooling
  14. MachineMail

    MCP server

    Real email inboxes for AI agents, with a trust report on every message

    Not checked yet
    • 2 tools
    • Remote
    • Freemium
    • Communication
  15. Repo Run Check

    MCP server

    Scans GitHub repos and shell commands for malware tricks before an agent runs them

    Not checked yet
    • 4 tools
    • Remote
    • Freemium
    • Developer tools
  16. Preflight

    MCP server

    Scans an MCP server for open access and overreaching tools before an agent connects

    Not checked yet
    • 2 tools
    • Remote
    • Freemium
    • Security
  17. Read-only scanner that checks remote MCP servers for tool poisoning and silent changes

    Not checked yet
    • Remote
    • Paid
    • Security
  18. Turns web pages and PDFs into clean Markdown and strips hidden prompt-injection text

    Not checked yet
    • Remote
    • Paid
    • Web search and scraping
  19. Checks whether a page may be used, then reads it as Markdown or JSON for agents

    Not checked yet
    • 7 tools
    • Remote
    • Freemium
    • Web search and scraping
  20. GlyphGuard

    MCP server

    Find hidden Unicode, homoglyphs and lookalike names in text before an agent acts on it

    Not checked yet
    • 3 tools
    • Remote
    • Free
    • Security
  21. InjectScan

    MCP server

    Prompt-injection scanner for text, web pages and MCP tool definitions, paid per call

    Not checked yet
    • 3 tools
    • Remote
    • Freemium
    • AI models and LLM tooling
  22. Verdict L402

    MCP server

    Ask an action firewall for an allow, review or block verdict before an agent acts

    Not checked yet
    • 4 tools
    • Remote
    • Paid
    • Security
  23. SmuggleCheck

    MCP server

    Scan untrusted text for hidden prompt injection: Unicode tags, zero-width, homoglyphs

    Not checked yet
    • 2 tools
    • Remote
    • Free
    • Security
  24. Golem Security

    MCP server

    Threat-intelligence verdicts on a URL, domain or IP before a coding agent connects

    Not checked yet
    • Remote
    • Free
    • Security