Skip to content

MCP servers for security

231 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. Self-hosted AI memory on Postgres and pgvector, with hybrid search and a knowledge graph

    Runs locally
    • 4 tools
    • Open source
    • Knowledge and memory
  2. Permission-aware MCP server that lets Claude read your Odoo 18 or 19 data as one user

    Not checked yet
    • Remote
    • Paid
    • AI models and LLM tooling
  3. MCP server that checks whether an x402 seller actually delivered before an agent pays

    Runs locally
    • Open source
    • Finance and payments
  4. Anchor a file's SHA-256 hash on Base as proof of existence, and look up proofs

    Not checked yet
    • 2 tools
    • Remote
    • Paid
    • Files and documents
  5. Plain-language checks of wallet approvals and signature requests, rated SAFE to RISK

    Not checked yet
    • Remote
    • Paid
    • Finance and payments
  6. Exact-action approval and signed receipts for consequential AI agent actions

    Runs locally
    • Open source
    • Security
  7. Hosted MCP checks that npm and PyPI packages, versions and functions actually exist

    Not checked yet
    • 3 tools
    • Remote
    • Open source
    • Security
  8. Pay-per-call MCP tools to read web pages, audit SEO and check domain, email and SSO setup

    Not checked yet
    • 24 tools
    • Remote
    • Paid
    • Web search and scraping
  9. One hosted endpoint for 16 MSP platforms such as ConnectWise, NinjaOne and Microsoft 365

    Not checked yet
    • Remote
    • Paid
    • Cloud and infrastructure
  10. Find vendor trust centers, analyze SOC 2 reports and request access from an AI client

    Not checked yet
    • 15 tools
    • Remote
    • Open source
    • Security
  11. Checks agent work against the destination system's own records, not the agent's word

    Runs locally
    • 5 tools
    • Paid
    • Security
  12. Pay-per-call DNS, WHOIS/RDAP and IP lookups plus a one-call domain report

    Not checked yet
    • Remote
    • Paid
    • Developer tools
  13. Paid point-in-time EVM address reports with EIP-7702 delegation flags across four networks

    Not checked yet
    • 2 tools
    • Remote
    • Paid
    • Finance and payments
  14. Guard agents' PostgreSQL and MySQL access with SQL audit, masking and write approval

    Not checked yet
    • Remote
    • Open source
    • Databases
  15. Role-aware onboarding answers about a codebase, filtered to what the caller may see

    Not checked yet
    • 9 tools
    • Remote
    • Open source
    • Developer tools
  16. Verify x402 delivery receipts and payments on Solana before trusting a settlement

    Not checked yet
    • 4 tools
    • Remote
    • Paid
    • Finance and payments
  17. Base L2 token safety scans, swap simulation and approval risk, paid per call in USDC

    Not checked yet
    • 12 tools
    • Remote
    • Paid
    • Security

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