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 1–20 of 20

  1. Scanner that checks agent skills for prompt injection, exfiltration and other risks

    • Open source
    • Open-source agent
    • 26.7K GitHub stars
    • Security
  2. Adds policy checks, intent screening, trust scores and audit logs to AI agents

    • Open source
    • 41.3K GitHub stars
    • AI models and LLM tooling
  3. Audits GitHub Actions workflows that run AI coding agents for prompt injection risks

    • Open source
    • 8.2K GitHub stars
    • AI models and LLM tooling
  4. SUNGLASSES

    MCP server

    Local input firewall that scans text, files and MCP metadata for prompt injection

    Runs locally
    • Open source
    • Security
  5. Boardcheck

    MCP server

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

    Runs locally
    • Open source
    • Security
  6. YUSA

    MCP server

    Prompt-injection scanner and tool-call gate for AI agents, run locally over stdio

    Runs locally
    • 3 tools
    • Open source
    • Security
  7. SkillTotal

    MCP server

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

    Runs locally
    • Open source
    • Security
  8. AgentGuard

    MCP server

    Let an agent pay on NEAR through a vault whose rules a smart contract enforces

    Runs locally
    • 7 tools
    • Open source
    • Finance and payments
  9. vibatchium

    MCP server

    Self-hosted fleet of persistent, logged-in stealth Chrome sessions for AI agents

    Runs locally
    • Open source
    • Browser automation
  10. Scan prompts, tool definitions and model output for injection, and guard tool calls

    Runs locally
    • Open source
    • AI models and LLM tooling
  11. Gage

    MCP server

    Signed, sealed handoffs between AI agents, with trust decided by the receiver

    Runs locally
    • Open source
    • Security
  12. pylos-mcp

    MCP server

    Email MCP server for Gmail, Outlook and IMAP that fences messages against prompt injection

    Runs locally
    • 12 tools
    • Open source
    • Communication
  13. keygrant

    MCP server

    Secrets manager MCP server that runs commands with API keys the model never sees

    Runs locally
    • 2 tools
    • Open source
    • Security
  14. Two-Key

    MCP server

    Authorization proxy that needs a rule check and AI judges to approve each tool call

    Runs locally
    • Open source
    • Security
  15. Iris

    MCP server

    Score AI agent runs for quality, PII leaks, prompt injection and cost, on your own machine

    Runs locally
    • 3 tools
    • Open source
    • AI models and LLM tooling
  16. opsgate

    MCP server

    Typed, policy-checked server operations for AI agents, with approvals and an audit log

    Runs locally
    • 11 tools
    • Open source
    • Developer tools
  17. MCPSense

    MCP server

    Offline security inspection for MCP configs, metadata and dependencies, run from the CLI

    Runs locally
    • Open source
    • Security
  18. Pins MCP tool definitions in a lockfile and flags rug-pulls, poisoning and leaked secrets

    Runs locally
    • 2 tools
    • Open source
    • Security
  19. AsItIs

    MCP server

    Read-only MCP server that lints and budgets CLAUDE.md, AGENTS.md and other steering files

    Runs locally
    • Open source
    • Files and documents
  20. Ghostchars

    MCP server

    Find and strip zero-width, bidi and tag characters hidden in text, offline

    Runs locally
    • 5 tools
    • Open source
    • Security