Skip to content

MCP servers for security

67 MCP servers that scan for vulnerabilities, manage secrets and investigate threats. Each one shows how to install it in Claude, Cursor and VS Code, whether it runs locally or remotely, and the tools it provides.
  1. Experimental agent wallet that seals agreements in a public register anchored in Bitcoin

    Runs locally
    • 13 tools
    • Open source
    • Finance and payments
  2. Passive audit that checks whether an MCP endpoint exposes its tools without authentication

    Runs locally
    • Open source
    • Security
  3. Read-only checks of an AI agent's Sigvara standing, score, stake and slashes

    Runs locally
    • Open source
    • Security
  4. MCP wrapper that holds database writes until a second person approves them on their phone

    Runs locally
    • Open source
    • Databases
  5. Check a store or product page for scam and dark-pattern signals before buying

    Runs locally
    • 2 tools
    • Paid
    • E-commerce
  6. Read-only payment preflight for AI agents: pay, review or do-not-pay before signing

    • 9 tools
    • Remote
    • Open source
    • Security
  7. Run an 88-test MCP spec compliance suite and get an A-F grade from CLI or agent

    Runs locally
    • 2 tools
    • Open source
    • Security
  8. Local input firewall that scans text, files and MCP metadata for prompt injection

    Runs locally
    • Open source
    • Security
  9. npm registry intelligence, security audits and publish-side writes without the 2FA prompt

    Runs locally
    • 9 tools
    • Open source
    • Developer tools
  10. Screen an x402 payment counterparty with allow, review or block before an agent pays

    Runs locally
    • 1 tool
    • Open source
    • Security
  11. Test whether a crypto token is a honeypot by trading it on a forked chain

    Not checked yet
    • 15 tools
    • Remote
    • Paid
    • Security
  12. Phone, email and IP checks plus a 0-100 identity risk score, from your AI assistant

    Runs locally
    • 5 tools
    • Paid
    • Security
  13. Checks one inbound email and returns structured findings on scams, paid links and pitches

    Runs locally
    • 3 tools
    • Paid
    • Security
  14. Hash and sign evidence of what AI agents did, mapped to AI governance frameworks

    Runs locally
    • Open source
    • Security
  15. Sign media with C2PA Content Credentials and check a file's declared origin

    Not checked yet
    • 15 tools
    • Remote
    • Paid
    • Design and media
  16. Sign each agent action, log it publicly and verify the proofs offline

    Not checked yet
    • 6 tools
    • Remote
    • Paid
    • Security
  17. Pay-per-call scam, wallet and payment pre-flight checks for agents, in USDC

    Runs locally
    • 7 tools
    • Paid
    • Security
  18. Signed receipts that bind a data fingerprint to a witnessed time, for agents

    Not checked yet
    • 4 tools
    • Remote
    • Paid
    • Security
  19. Static security scanner for MCP servers, agent skills and npm or PyPI packages

    Runs locally
    • Open source
    • Security
  20. Look up safety scores, incidents and verified results for AI trading bots and tools

    Not checked yet
    • 11 tools
    • Remote
    • Open source
    • Finance and payments
  21. MCP server giving agents a signed identity and hash-anchored settlements on Midnight

    Runs locally
    • 4 tools
    • Paid
    • Security
  22. Run ad scans, write detection rules and manage alerts across 108 tools

    Not checked yet
    • Remote
    • Paid
    • Security
  23. Live CVE, advisory and framework-release lookups for coding agents, billed per call

    Runs locally
    • 5 tools
    • Paid
    • Security
  24. Free MCP server that checks lockfiles, Node.js and PHP versions and Dockerfiles for flaws

    Not checked yet
    • Remote
    • Open source
    • Security
  25. Give an AI agent its own DID: prove identity offline, verify bundles, pay and message

    Not checked yet
    • 1 tool
    • Remote
    • Open source
    • Security
  26. Scan Node.js projects for unprotected API routes and get an explained health score

    Runs locally
    • Open source
    • Developer tools
  27. Preflight trust check for x402 payment endpoints, with an ok, caution or avoid verdict

    Not checked yet
    • 4 tools
    • Remote
    • Paid
    • Finance and payments
  28. Signed, chain-anchored receipts that prove which model said what and when

    Runs locally
    • 6 tools
    • Paid
    • Security

See every kind of AI for security: tools, agents, MCP servers and skills.Ranked: the best AI for security.