Connection check
local install
agent-security-scanner-mcp
Security layer for AI agents: blocks prompt injection, detects fake packages, scans vulnerabilities.
Tools
26
GitHub stars
121
Installs / wk
1.9k
Licence
MIT
Transport
stdio
Last checked
never
Tools & capabilities
26 toolsRead from the published package source — this server runs locally, so there is no endpoint to query. Names are taken from the code, not observed at runtime, and descriptions are often absent.
check_package
from source
Check if a package name is legitimate or potentially hallucinated (AI-invented) Check if a package name is legitimate or potentially hallucinated (AI-invented)
clawproof_health
from source
Alias for scanner_health (deprecated, use scanner_health instead) Alias for scanner_health (deprecated, use scanner_health instead)
evaluate_compliance
from source
Evaluate a project against compliance frameworks (SOC2-technical, GDPR-technical, AIUC-1). Collects evidence from code scans, SBOM, vulnerability checks, and hallucination detectio… Evaluate 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.
fix_security
from source
Scan a file and return fixes. Use verbosity= Scan a file and return fixes. Use verbosity=
get_compliance_controls
from source
Look up compliance controls with evaluation criteria. Supports multiple frameworks: aiuc-1 (default), soc2-technical, gdpr-technical. Filter by domain, control IDs, or OWASP LLM ta… Look 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.
list_package_stats
from source
List statistics about loaded package lists for hallucination detection List statistics about loaded package lists for hallucination detection
list_security_rules
from source
List all available security fix templates and their descriptions List all available security fix templates and their descriptions
record_security_outcome
from source
Record aggregate remediation outcomes after reviewing scanner findings. Sends counts only; never sends code, findings, paths, or rule IDs. Record aggregate remediation outcomes after reviewing scanner findings. Sends counts only; never sends code, findings, paths, or rule IDs.
remediation_available
from source
remediation_outcome_recorded
from source
remediation_requested
from source
sbom_check_hallucinations
from source
Check 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… Check 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_diff
from source
Compare current project SBOM against a stored baseline. Reports added, removed, and version-changed packages. Use save_baseline=true to create initial baseline. Compare current project SBOM against a stored baseline. Reports added, removed, and version-changed packages. Use save_baseline=true to create initial baseline.
sbom_export_report
from source
Generate an HTML or JSON audit report from SBOM data, optionally enriched with vulnerability scan results. Suitable for PCI-DSS and compliance audits. Generate an HTML or JSON audit report from SBOM data, optionally enriched with vulnerability scan results. Suitable for PCI-DSS and compliance audits.
sbom_generate
from source
Generate 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 verbo… Generate 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=
sbom_scan_vulnerabilities
from source
Cross-reference SBOM components against OSV.dev vulnerability database. Returns CVE IDs, CVSS scores, severity, and fix recommendations. Accepts directory_path (generates fresh) or… Cross-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).
scan_agent_action
from source
Pre-execution security check for agent actions (bash, file_write, file_read, http_request, file_delete, cron, process_spawn, git, docker). Returns ALLOW/WARN/BLOCK. Pre-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_agent_prompt
from source
Scan a prompt for malicious intent. Returns BLOCK/WARN/LOG/ALLOW. Use verbosity= Scan a prompt for malicious intent. Returns BLOCK/WARN/LOG/ALLOW. Use verbosity=
scan_git_diff
from source
Scan git diff for new security vulnerabilities. Only reports issues on changed lines. Use for PR reviews. Scan git diff for new security vulnerabilities. Only reports issues on changed lines. Use for PR reviews.
scan_mcp_server
from source
Scan an MCP server Scan an MCP server
scanner_health
from source
Check plugin health: engine status, daemon status, package data availability Check plugin health: engine status, daemon status, package data availability
scan_packages
from source
Scan code for package imports and check for hallucinated (AI-invented) packages. Use verbosity= Scan code for package imports and check for hallucinated (AI-invented) packages. Use verbosity=
scan_project
from source
Scan an entire directory for security vulnerabilities with .gitignore support and security grading. Use verbosity= Scan an entire directory for security vulnerabilities with .gitignore support and security grading. Use verbosity=
scan_security
from source
Scan a file for security vulnerabilities. Use verbosity= Scan a file for security vulnerabilities. Use verbosity=
scan_skill
from source
Deep security scan of an OpenClaw skill. Multi-layer analysis: prompt injection detection, code analysis (AST+taint), ClawHavoc malware signatures, package supply chain verificatio… Deep 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.
score_aivss
from source