- Conduid
- Marketplace
- #code-scanning
MCP servers tagged code-scanning
22 live MCP servers tagged "code-scanning", ranked by trust score. Tags come from package metadata and repository topics, so this list covers servers across every category that work with code-scanning.
Vibescan
Security scanner for AI-generated ("vibe-coded") code. Runs SAST, DAST, and sandboxed exploit simulation across 15+ languages using 30+ tools. Catches what LLMs introduce bef…
Agentshield
🛡️ The security firewall for AI agent tools & MCP servers (Claude 5, GPT-5.6, Gemini 3.8, Antigravity, Cursor, Codex, Hermes). Catch command injection, secret theft & toxic flows…
Agentfile
Find what is wrong with the AI agent configuration your repository already has.
Sentinel AI
Real-time AI safety guardrails for LLM apps. 10 scanners: prompt injection, PII, harmful content, code vulnerabilities, obfuscation detection. Sub-ms latency. Python + TypeScript…
Agenticqa Scan Action
Analyze AI codebases to identify integration points, security risks, and test coverage gaps in one step with comprehensive reports.
Guard Scanner
🛡️ Agent Security Scanner — 364 patterns, 35 threat categories, 27 runtime checks. Zero-Trust policy layer for MCP/A2A agents.
Agentic Workflow Guard
Static analysis for AI automation workflows. Find prompt-injection paths, overpowered tools, and write-capable agent jobs before they run.
Guardskill
Read-only scanner for what lets a repository run code in a coding agent (Claude Code, Codex, Cursor, Copilot): git settings, hooks, and committed MCP server definitions and agent…
Assay Agent Gate Demo
Runnable demo: a CI gate that denies an agent's undeclared privileged tool action before it runs, with evidence in the Security tab. Built on assay.
Scan Action
The first GitHub Action that scans MCP servers, AI agents & LLM pipelines for security vulnerabilities. 24 checks: tool poisoning, SSRF, prompt injection, DataFlow taint. Results…
Codetrellis Matrix
Open-source project awareness engine for AI coding tools via compressed codebase context, MCP, and editor integrations.
Plimsoll Action
Review what an AI agent release changed at runtime (files, network, MCP tools), gate the PR, and report findings in code scanning. For AI platform and security teams.
Agent Rules Audit
Offline scanner for AI agent instruction files (AGENTS.md, CLAUDE.md, .cursorrules, skills, MCP configs) — flags prompt-injection payloads, hidden Unicode, encoded blobs, exfiltra…
Riskmap
Local-first static auditor for risky MCP and agent-tool repository patterns.
Security Scanner WorkFlows
mcp-scan is a free, open-source security scanner for MCP (Model Context Protocol) servers. It scans your MCP server's source code for critical security issues: hardcoded API keys,…
Drift Check
Zero-execution MCP security preflight + GitHub Action. Detect mutable package references before AI agents run them. Try any public repo in the browser.
Agenstral
Local preflight and audit tool for AI coding agents: scan repo risk, enforce tool-call policy, and record tamper-evident audit logs. Local-first, zero telemetry.
Aicaudit
aicaudit — AI-powered code audit for Python: taint-path static analysis + evidence-grounded AI verdicts. Every result ships with a machine-checkable source-to-sink path.
Agentic Semgrep Rules
Semgrep rules for AI agent code: static analysis for LLM applications in Python, TypeScript and JavaScript. Finds model output reaching exec, shells, SQL, URLs, files and HTML, us…
Skill Scan Gate
CI gate for Claude Code skills and plugins: scans a skills or plugin repository for instruction-override text, exfiltration patterns, dangerous hook commands, unpinned MCP servers…
Agenticqa Scan Action
Analyze AI codebases to identify integration points, security risks, and test coverage gaps in one step with comprehensive reports.
Guard
Validates MCP manifests and built artifacts for provenance, security, and supply-chain compliance.