- Conduid
- Marketplace
- #audit
MCP servers tagged audit
225 live MCP servers tagged "audit", ranked by trust score. Tags come from package metadata and repository topics, so this list covers servers across every category that work with audit.
KYA
Know Your Agent — An open standard for AI agent identity, compliance, and auditability
Zazaki MCP Repo Audit
可复用的本地 MCP plugin 仓库 — Git 仓库提交前审计 MCP server
Klaviyo Audit Agent Skill
Read-only Klaviyo MCP audit skill for Codex, Claude, GitHub Copilot, and other AI agents.
Agent Owl
Cryptographic file integrity monitoring with OWL/RDF ontology and EU AI Act compliance for Claude Code
Audit Reports
MCP server security & EU AI Act compliance audit reports. Demo: Anthropic filesystem server scored 7/100.
Fluxmirror
Multi-agent activity audit for Claude Code, Gemini CLI, Qwen Code, and Claude Desktop MCP.
K8s Sec Agent
Kubernetes security audit agent - declarative kagent agent with MCP tools and privacy-preserving pseudonymization via LLM proxy
Iso Evidence MCP
MCP server to automate audit evidence: read a task from Notion, capture authenticated GitHub screenshots with Playwright, and upload them back to the page. Built for ISO 27001.
Agent Action Shield
Human-in-the-loop approval UI for AI agent tool calls. Risk-tiered confirmation, drop-in React and Vue components, and a tamper-evident audit trail of every decision. Zero runtime…
Patchwork Harness
The verifying harness for AI coding agents: test gates, independent cross-vendor review and grounded answers, with every action on the Patchwork audit trail.
ANNPACK
Verifiable knowledge artifacts for AI agents — package, search, and prove exactly which source revision produced each retrieval.
Ssha Broker
SSH broker for AI agents: it holds the credentials, enforces per-host policy and records a tamper-evident audit log. MCP server, CLI and Agent Skill in one static Go binary.
Aragami
Read-only static posture audit for Tor Browser and Firefox: reports configuration posture and static residue without launching or changing anything. A clean audit is not proof of…
Invguard
Self-hosted vulnerability watchdog for the hardware and software you actually own. Manual inventory only — no network scanning, by design. Tracks NVD, CVE List V5, OSV, KEV, EPSS,…
Bh MCP Attribution
Attribution-enforcing audit emission for MCP servers and gateways. Reference implementation of the enforced emission tier from bh-audit-schema v2.*
Witness
🔐 Cryptographic audit trails for AI decisions — hash chains, Merkle trees, RFC 3161 timestamps, compliance presets for HIPAA/GDPR/SOC2
Twira
Coding power tools for AI agents. 18 deterministic MCP tools: code-graph search, SAST, blast radius, wire-level PII redaction, signed audit chain. Works with Claude Code, Codex, G…
Trust
The missing trust layer for the MCP ecosystem. Audit the servers on your machine. npx mcp-trust
Gateway
Security gateway for Model Context Protocol (MCP) traffic - logging, auditing, and scanning
Governance Gateway
Governance and multi-tenancy gateway fronting agentmemory, issue trackers, a docs corpus and CI behind the Model Context Protocol — per-tenant isolation, confirmation-gated writes…
Agentguard
Safety and audit framework for autonomous AI agents — policy enforcement, append-only audit logs, MCP integration
Security Audit
Security audit tooling for avatar-factory style artifacts.
Audit
Security audit checklist for third-party MCP servers before you install them
Guardian
A local security firewall, scanner, and audit layer for Model Context Protocol servers.
Aragami SilentCrystal
Read-only static posture audit for Tor Browser and Firefox: reports configuration posture and static residue without launching or changing anything. A clean audit is not proof of…
Doctor
Scan, Score, Install MCP Servers with confidence. The missing toolkit for the MCP ecosystem.
Audit
Security scanner for MCP server configs — finds dangerous permissions, hardcoded secrets, and supply-chain risks. Zero deps.
Golf Scanner
Discover and audit MCP servers for security vulnerabilities across Claude Code, Cursor, VS Code, and more
Map1
Deterministic identity for structured data
ScopeBlind/verify-mcp
2.0.
Acgs Lite
Constitutional governance infrastructure for AI agents — the missing safety layer between your LLM and production
enmanuelmag/heimdall-mcp
mcp`
Enji Guard CLI
CLI/MCP agent surface for Enji Guard
Farofino MCP
Faro Fino Smart Contract Auditor MCP Server
Sonic Boom
🔍 Sonic-Boom: A CLI and MCP server that visualizes project logic, architectural debt, and code anomalies as frequency patterns. Surgical code auditing via the "Sonic Code" paradig…
Librecrawl MCP
Audit websites with this self-hosted SEO crawler. Connect LibreCrawl to Claude and perform unlimited technical audits without per-crawl fees.
Agent Audit Trail MCP
Immutable audit logging for AI agents — hash-chained event log, integrity verification, EU AI Act compliance
WebAuditMCP
Local-first MCP server for web auditing — axe-core, Playwright, security headers
Grantguard
Prove a Postgres role cannot perform the writes it is not allowed to perform. Catalog-based least-privilege audit + CI gate + MCP server.
Wa Audit
Verified commercial audit of a WhatsApp business number: WAHA export, clean corpus, LLM analysis with a mandatory two-layer verifier (34/60 findings refuted in the original run),…
Doorman
Secure-by-default FastAPI->MCP bridge: deny-by-default exposure, scope->tool auth that fails closed (even on STDIO), rate limiting, PII redaction, and audit. In-process, no gatewa…
Readproof
Readproof — the lockfile and replay primitive for what AI agents read: stable identity, freshness policy, content-addressed snapshots, per-run manifests, diff, byte-exact replay,…
Barndoor
Barndoor — independent third-party profile of a public API surface, by API Evangelist. Barndoor AI is the control plane for agentic AI, providing secure access and governance for…
Agentstate
The open, governed state layer for AI agents — trustworthy, not smarter. The model proposes; a deterministic engine decides; every change is an event. Sits under any agent framewo…
Open Agent Context
Open Agent Context Standard: portable, governed memory and context for AI agents. Python reference implementation with CLI, SQLite, evidence, audit, and MCP adapters.
Inspectra
Hybrid code audit system powered by deterministic MCP tools and conditional hotspot exploration. Audits 12 domains: security, tests, architecture, conventions, performance, docume…
Novoriq Chargeback Operations
AI-native chargeback operations MCP for dispute monitoring, evidence workflows, and revenue recovery infrastructure.
Abra Flexi MCP
Model Context Protocol server pro ABRA FlexiBee API - AI asistent pro automatizaci účetnictví s GDPR anonymizací a audit módy
Appwrite Security MCP
MCP server for Appwrite security audits inside Claude Code, Cursor, Cline.
Agent Receipt
MCP middleware that creates cryptographic receipts for every real tool call — ghost actions leave no receipt