All servers / Security / Agent Security Scanner MCP server
Agent Security Scanner MCP server
AI agent security scanner and npm audit for MCP servers, Claude Code, Cursor, and Windsurf. Find prompt injection, hallucinated packages, secrets, unsafe tools,
Tested by ConnectATDScore 82 out of 100. Tested 2026-11-19 on package version 4.5.10. Package: agent-security-scanner-mcp · source
Score breakdown
| Runs | 18 / 20 | |
|---|---|---|
| Tool descriptions | 20 / 20 | |
| Package safety | 12 / 20 | |
| Maintenance | 20 / 20 | |
| Adoption | 12 / 20 |
What we saw
- Starts and answers the MCP handshake: yes (14.8 seconds including download)
- Tools offered: 23
- Last published: 2026-09-02
- Weekly downloads (npm): 1,015
- License: MIT · Direct dependencies: 5
Notes
- The package runs install scripts, which execute code when you install it.
Want this server set up for your team?
ConnectATD builds AI automation and wires up MCP servers like this one. Tell us what you are trying to do.
Talk to ConnectATDTools and how they are described
Agents choose tools from these descriptions. Under each name you can see how many of its parameters are explained.
scan_security7 of 7 parameters describedScan a file for security vulnerabilities. Use verbosity='minimal' for counts only (~50 tokens), 'compact' (default) for actionable info (~200 tokens), 'full' for complete metadata.
fix_security2 of 2 parameters describedScan a file and return fixes. Use verbosity='minimal' for summary only, 'compact' (default) for fix list, 'full' for complete fixed file content.
record_security_outcome3 of 3 parameters describedRecord aggregate remediation outcomes after reviewing scanner findings. Sends counts only; never sends code, findings, paths, or rule IDs.
list_security_rulesno parametersList all available security fix templates and their descriptions
check_package2 of 2 parameters describedCheck if a package name is legitimate or potentially hallucinated (AI-invented)
scan_packages3 of 3 parameters describedScan code for package imports and check for hallucinated (AI-invented) packages. Use verbosity='minimal' for counts, 'compact' (default) for flagged packages, 'full' for all details.
list_package_statsno parametersList statistics about loaded package lists for hallucination detection
scan_agent_prompt3 of 3 parameters describedScan a prompt for malicious intent. Returns BLOCK/WARN/LOG/ALLOW. Use verbosity='minimal' for action only, 'compact' (default) for findings, 'full' for audit details.
scan_git_diff3 of 3 parameters describedScan git diff for new security vulnerabilities. Only reports issues on changed lines. Use for PR reviews.
scan_project7 of 7 parameters describedScan an entire directory for security vulnerabilities with .gitignore support and security grading. Use verbosity='minimal' for grade + counts, 'compact' (default) for top issues, 'full' for all details.
scan_agent_action3 of 3 parameters describedPre-execution security check for agent actions (bash, file_write, file_read, http_request, file_delete, cron, process_spawn, git, docker). Returns ALLOW/WARN/BLOCK.
scan_mcp_server4 of 4 parameters describedScan an MCP server's source code for security vulnerabilities: overly broad permissions, missing input validation, data exfiltration, insecure patterns. Returns grade (A-F) and recommendations.
scan_skill3 of 3 parameters describedDeep security scan of an OpenClaw skill. Multi-layer analysis: prompt injection detection, code analysis (AST+taint), ClawHavoc malware signatures, package supply chain verification, rug pull detection. Returns security grade A-F with detailed findings.
scanner_healthno parametersCheck plugin health: engine status, daemon status, package data availability
clawproof_healthno parametersAlias for scanner_health (deprecated, use scanner_health instead)
score_aivss4 of 4 parameters describedScore findings using OWASP AIVSS v2. Accepts any scanner output or raw findings JSON. Returns per-finding AIVSS scores (0-10) and aggregate posture. Use verbosity='minimal' for posture only, 'compact' (default) for scores, 'full' for all metrics.
get_compliance_controls5 of 5 parameters describedLook up compliance controls with evaluation criteria. Supports multiple frameworks: aiuc-1 (default), soc2-technical, gdpr-technical. Filter by domain, control IDs, or OWASP LLM tags.
evaluate_compliance6 of 6 parameters describedEvaluate a project against compliance frameworks (SOC2-technical, GDPR-technical, AIUC-1). Collects evidence from code scans, SBOM, vulnerability checks, and hallucination detection, then evaluates controls. Optionally saves timestamped evidence bundle.
sbom_generate4 of 4 parameters describedGenerate a CycloneDX v1.5 SBOM for a project. Discovers all dependencies (direct + transitive) from lock files and manifests across Node.js, Python, Go, Rust, Ruby, Java. Use verbosity='minimal' for counts, 'compact' (default) for component list, 'full' for complete CycloneDX JSON.
sbom_scan_vulnerabilities4 of 4 parameters describedCross-reference SBOM components against OSV.dev vulnerability database. Returns CVE IDs, CVSS scores, severity, and fix recommendations. Accepts directory_path (generates fresh) or sbom_path (loads saved artifact).
sbom_check_hallucinations3 of 3 parameters describedCheck all packages in an SBOM against official registries to detect hallucinated (AI-invented) package names. Supports npm, pypi, rubygems, dart, perl, raku, crates. Go/Java marked as unsupported.
sbom_diff4 of 4 parameters describedCompare current project SBOM against a stored baseline. Reports added, removed, and version-changed packages. Use save_baseline=true to create initial baseline.
sbom_export_report6 of 6 parameters describedGenerate an HTML or JSON audit report from SBOM data, optionally enriched with vulnerability scan results. Suitable for PCI-DSS and compliance audits.
Tested in a sandbox with an empty environment: no API keys, a throwaway folder, nothing from a real account. A passing test shows the server runs and responds. It is not a security audit.