Skip to content

MCP servers for security

562 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. Map which functions reach network, files, database or subprocess, then gate risky edits

    Runs locally
    • Open source
    • Developer tools
  2. Read-only MCP server that shows which git name, email and SSH key a repo will use

    Runs locally
    • 6 tools
    • Open source
    • Developer tools
  3. Hosted sign-in, OIDC and API keys so agents and apps can confirm who a user is

    Not checked yet
    • Remote
    • Paid
    • Security
  4. Find end-of-life runtimes, packages and Actions in a repo, with file, line and source

    Runs locally
    • Open source
    • Developer tools
  5. Approval gateway that keeps AI assistants from reading or changing your data unchecked

    Runs locally
    • Open source
    • Security
  6. Saves web pages as signed, timestamped evidence and checks or compares them later

    Not checked yet
    • 17 tools
    • Remote
    • Paid
    • Legal and government
  7. Free MCP server that checks lockfiles, Node.js and PHP versions and Dockerfiles for flaws

    Not checked yet
    • Remote
    • Open source
    • Security
  8. Pay-per-call data tools for agents: web to Markdown, DNS checks, trials, CVEs and filings

    Not checked yet
    • Remote
    • Paid
    • Web search and scraping
  9. Self-hosted fleet of persistent, logged-in stealth Chrome sessions for AI agents

    Runs locally
    • Open source
    • Browser automation
  10. Find risky ERC-20 approvals on a Base wallet and get unsigned revoke calldata

    Not checked yet
    • Remote
    • Paid
    • Security
  11. Mac key vault where agents get scoped, expiring tokens and never the API keys

    Runs locally
    • 2 tools
    • Open source
    • Security
  12. Registry, scoped permissions and one-step recall for AI agents in health systems

    Not checked yet
    • Remote
    • Contact sales
    • Security
  13. Reputation checks, pre-hire reports and escrow for agent-to-agent trades paid in USDC

    Not checked yet
    • 4 tools
    • Remote
    • Paid
    • Finance and payments
  14. Pay-per-call rug-checks and a pump.fun launch feed for Solana trading bots

    Not checked yet
    • 1 tool
    • Remote
    • Paid
    • Finance and payments
  15. Pay-per-call website safety, domain, email and Base on-chain checks for agents

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

    Runs locally
    • Open source
    • AI models and LLM tooling
  17. Pay-per-call read-only crypto data and security checks, settled in USDC on Base via x402

    Not checked yet
    • Remote
    • Paid
    • Finance and payments
  18. Passive-by-default OSINT lookups for AI agents: DNS, WHOIS, IP, breaches, Shodan and more

    Runs locally
    • 16 tools
    • Open source
    • Security
  19. Ask Copilot or Claude to audit and operate client Microsoft 365 tenants as an MSP

    Not checked yet
    • Remote
    • Paid
    • Cloud and infrastructure
  20. Local security scanner that checks AI-written code and drives a scan, fix, rescan loop

    Runs locally
    • Open source
    • Security
  21. Persistent sandbox for coding agents: run commands, edit files, manage Git and sessions

    Not checked yet
    • 1 tool
    • Remote
    • Open source
    • Developer tools

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