Skip to content

AI tools, MCP servers and agent skills for audit

119 MCP servers, 4 agent skills and 2 AI tools for audit in security, including agent-governance-toolkit, archestra and MCP security audit, most popular first. 64 of the 125 are listed as free or open source. Each one is written up from its own site or README, with pricing, platforms and alternatives.

Showing 61–90 of 125

  1. MCPVetter

    MCP server

    Scan MCP configs for leaked secrets and poisoned tools, and review AI-written code

    Not checked yet
    • 7 tools
    • Remote
    • Freemium
    • Security
  2. Scovant Core

    MCP server

    Passive scan of a website's AI-agent readiness: robots, llms.txt, JSON-LD, MCP, security

    Runs locally
    • Open source
    • Marketing and SEO
  3. Conarium

    MCP server

    Self-hosted gateway that masks PII and signs receipts for AI access to your databases

    Runs locally
    • Open source
    • Security
  4. Slipmark

    MCP server

    Record AI agent verdicts bound to file hashes and refuse stale ones before shipping

    Runs locally
    • Open source
    • Security
  5. mcpprobe

    MCP server

    Read-only MCP security data: the check catalogue, public scan status and your own reports

    Not checked yet
    • Remote
    • Freemium
    • Security
  6. QuietProof

    MCP server

    29 deterministic audits for APIs, CI, containers and web files, paid per call

    Not checked yet
    • Remote
    • Paid
    • Developer tools
  7. mcp-toolbelt

    MCP server

    29 DNS, SEO, SSL and security check tools for agents, paid per call

    Not checked yet
    • 9 tools
    • Remote
    • Paid
    • Security
  8. Bannerproof

    MCP server

    Scan a site for trackers firing before cookie consent, with evidence and fixes

    Not checked yet
    • 16 tools
    • Remote
    • Freemium
    • Security
  9. 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
  10. Read-only scanner that checks remote MCP servers for tool poisoning and silent changes

    Not checked yet
    • Remote
    • Paid
    • Security
  11. Seven-tool proof loop that authorizes agent actions and records tamper-evident evidence

    Runs locally
    • 7 tools
    • Freemium
    • AI models and LLM tooling
  12. Grades a site's security headers and explains each one, over stdio

    Runs locally
    • 3 tools
    • Open source
    • Security
  13. Deedglass

    MCP server

    Rules for each agent tool call, then a check of what a database really changed

    Runs locally
    • Open source
    • Security
  14. Stackduke Radar

    MCP server

    Read-only MCP lookup of which tools public MCP servers expose and how they change

    Not checked yet
    • Remote
    • Free
    • Developer tools
  15. Golem Intel

    MCP server

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

    Not checked yet
    • Remote
    • Free
    • Security
  16. Read-only checks that a NEAR protocol holds the tokens it owes, at a single block

    Not checked yet
    • Remote
    • Free
    • Finance and payments
  17. Nacre

    MCP server

    Self-hosted knowledge index where each search returns only what the caller may read

    Runs locally
    • Open source
    • Knowledge and memory
  18. Policyseed

    MCP server

    Draft SOC 2 policies from your assistant, with 22 open-source templates

    Runs locally
    • 5 tools
    • Open source
    • Security
  19. Pay-per-call MCP service that audits zero knowledge claims and returns a deterministic

    Not checked yet
    • Remote
    • Security
  20. Deterministic API/MCP check that returns DEFINED or NOT_DEFINED for zero-trust evidence

    Not checked yet
    • Remote
    • Security
  21. Small Print

    MCP server

    Look up changes in MCP server, skill and plugin descriptions before an agent uses them

    Runs locally
    • 4 tools
    • Freemium
    • Security
  22. Wayreceipt

    MCP server

    Countersigned proof-of-delivery receipts for work sold between AI agents

    Not checked yet
    • 4 tools
    • Remote
    • Open source
    • Security
  23. Enterprise MCP gateway that authorizes each agent tool call per person, tool and argument

    Not checked yet
    • Remote
    • Contact sales
    • Security
  24. Manage and secure MCP servers on Speakeasy's AI control plane from an agent

    Not checked yet
    • Remote
    • Paid
    • Security
  25. Data Prism

    MCP server

    Fail-closed privacy layer that pseudonymises enterprise API data for LLM agents

    Not checked yet
    • 2 tools
    • Remote
    • Open source
    • Security