Summary
If you're running AI agents in production or building on MCP, this scanner gives you the blast radius view you actually need. It inventories agents, MCP servers, tools, packages, and credential references, then maps vulnerabilities from OSV and GHSA through the dependency graph to show you which agents can reach which exposed attack paths. You get CLI output for CI gates, MCP tools for agent driven security queries, and a self hosted dashboard that visualizes the full mesh. The quickstart command seeds demo data so you can see graph backed findings before pointing it at your own stack. Useful when you need to answer "what breaks if this package is compromised" or enforce pre install guards across a fleet.
Keeps your Mac awake while Claude Code, Codex or Cursor works. Lets it sleep when they are done.
Try free for 7 days →
Block distracting apps from your iPhone permanently without a 3rd party app. Free and open source.
Block now (100% free) →
Notes, actions and memory. Without a meeting bot. First month 100% off.
Download for free →
belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →
Free an open-source skills that make AI coding agents easier to understand, verify, and control.
Download for free →
Connect your Claude agent to live crypto prices and trading routes via 1inch
Get the MCP →Tools
Public tool metadata for what this MCP can expose to an agent.
36 tools
scanRun a full AI supply chain security scan. Discovers local MCP configurations (Claude Desktop, Cursor, Windsurf, VS Code Copilot, OpenClaw, etc.), extracts package dependencies, queries OSV.dev for CVEs, assesses config security (credential exposure, tool access), computes blas...13 params
Run a full AI supply chain security scan. Discovers local MCP configurations (Claude Desktop, Cursor, Windsurf, VS Code Copilot, OpenClaw, etc.), extracts package dependencies, queries OSV.dev for CVEs, assesses config security (credential exposure, tool access), computes blas...
Parameters* required
auto_update_dbbooleanAuto-refresh local vuln DB if stale (>7 days) before scanning.default: true
config_pathvaluePath to MCP client config directory. Auto-discovers all if omitted.
db_sourcesvalueComma-separated DB sources to sync before scanning (e.g. 'nvd,ghsa,osv,epss,kev').
enrichbooleanEnable NVD CVSS, EPSS probability, and CISA KEV enrichment.default: false
fail_severityvalueReturn failure status if vulns at this severity or higher: critical, high, medium, low.
imagevalueDocker image to scan (e.g. 'nginx:1.25', 'ghcr.io/org/app:v1').
output_formatstringOutput format: 'json' (default), 'sarif', 'cyclonedx', 'spdx', 'junit', 'csv', or 'markdown'.default: json
policyvaluePolicy object to evaluate alongside scan results, e.g. {"rules": [{"id": "no-critical", "severity_gte": "critical", "action": "fail"}]}.
sbom_pathvaluePath to existing CycloneDX or SPDX JSON SBOM file to ingest.
scorecardbooleanEnrich packages with OpenSSF Scorecard scores (requires resolvable GitHub repos).default: false
transitivebooleanResolve transitive dependencies for npx/uvx packages.default: false
verify_integritybooleanVerify package SHA-256/SRI hashes and SLSA provenance against registries.default: false
warn_severityvalueReturn warning status (gate_status=warn, exit 0) when vulns at this severity or higher exist. Use with fail_severity for two-tier CI gates, e.g. warn_severity='medium', fail_severity='critical'.
checkCheck a specific package for known CVEs before installing. Queries OSV.dev for vulnerabilities in the given package. Use this before installing an MCP server or dependency to verify it is safe. Args: package: Package name with optional version, e.g. "express@4.18.2", "@modelco...2 params
Check a specific package for known CVEs before installing. Queries OSV.dev for vulnerabilities in the given package. Use this before installing an MCP server or dependency to verify it is safe. Args: package: Package name with optional version, e.g. "express@4.18.2", "@modelco...
Parameters* required
ecosystemstringPackage ecosystem: 'npm', 'pypi', 'go', 'cargo', 'maven', 'nuget', 'rubygems', 'composer', 'swift', 'pub', 'hex', 'conda', 'deb', 'apk', or 'rpm'.default: npm
packagestringPackage name with optional version, e.g. 'express@4.18.2', '@modelcontextprotocol/server-filesystem@2025.1.14', or 'requests' (resolves @latest).
blast_radiusLook up the blast radius of a specific CVE across your AI agent setup. Scans local MCP configurations, finds the specified CVE, and returns the full attack chain: which packages are affected, which MCP servers use those packages, which agents connect to those servers, and what...1 params
Look up the blast radius of a specific CVE across your AI agent setup. Scans local MCP configurations, finds the specified CVE, and returns the full attack chain: which packages are affected, which MCP servers use those packages, which agents connect to those servers, and what...
Parameters* required
cve_idstringCVE identifier to look up, e.g. 'CVE-2024-1234' or 'GHSA-xxxx'.
policy_checkEvaluate a security policy against current scan results. Runs a scan, then evaluates the provided policy rules against the findings. Policies can gate on severity thresholds, CISA KEV status, AI risk flags, credential exposure, and denied packages. Args: policy_json: JSON stri...1 params
Evaluate a security policy against current scan results. Runs a scan, then evaluates the provided policy rules against the findings. Policies can gate on severity thresholds, CISA KEV status, AI risk flags, credential exposure, and denied packages. Args: policy_json: JSON stri...
Parameters* required
policy_jsonstringJSON string containing policy rules, e.g. {"rules": [{"id": "no-critical", "severity_gte": "critical", "action": "fail"}]}.
registry_lookupQuery the agent-bom MCP server threat intelligence registry. Look up risk level, known tools, credential requirements, and verification status for known MCP servers. The registry contains 109+ servers with security metadata. Args: server_name: MCP server name to look up (e.g....2 params
Query the agent-bom MCP server threat intelligence registry. Look up risk level, known tools, credential requirements, and verification status for known MCP servers. The registry contains 109+ servers with security metadata. Args: server_name: MCP server name to look up (e.g....
Parameters* required
package_namevaluePackage name to search for, e.g. 'mcp-server-sqlite'. At least one of server_name or package_name is required.
server_namevalueMCP server name to look up, e.g. 'filesystem', '@modelcontextprotocol/server-github'.
generate_sbomGenerate a Software Bill of Materials (SBOM) for your AI agent setup. Discovers AI agents and MCP servers, extracts all package dependencies, and generates a standards-compliant SBOM. Args: format: SBOM format — "cyclonedx" (CycloneDX 1.6) or "spdx" (SPDX 3.0). config_path: Pa...2 params
Generate a Software Bill of Materials (SBOM) for your AI agent setup. Discovers AI agents and MCP servers, extracts all package dependencies, and generates a standards-compliant SBOM. Args: format: SBOM format — "cyclonedx" (CycloneDX 1.6) or "spdx" (SPDX 3.0). config_path: Pa...
Parameters* required
config_pathvaluePath to MCP client config directory. Auto-discovers all if omitted.
formatstringSBOM format: 'cyclonedx' (CycloneDX 1.6) or 'spdx' (SPDX 3.0).default: cyclonedx
complianceGet OWASP LLM Top 10 / OWASP MCP Top 10 / MITRE ATLAS / NIST AI RMF compliance posture. Scans local MCP configurations, maps findings to 47 security controls across four AI security frameworks, and returns per-control pass/warning/fail status with an overall compliance score....2 params
Get OWASP LLM Top 10 / OWASP MCP Top 10 / MITRE ATLAS / NIST AI RMF compliance posture. Scans local MCP configurations, maps findings to 47 security controls across four AI security frameworks, and returns per-control pass/warning/fail status with an overall compliance score....
Parameters* required
config_pathvaluePath to MCP client config directory. Auto-discovers all if omitted.
imagevalueDocker image to scan, e.g. 'nginx:1.25'.
remediateGenerate a remediation plan for vulnerabilities in your AI agent setup. Scans for vulnerabilities, then generates actionable fix commands for each affected package (npm install, pip install), credential scope reduction guidance, and reports on unfixable vulnerabilities. Args:...2 params
Generate a remediation plan for vulnerabilities in your AI agent setup. Scans for vulnerabilities, then generates actionable fix commands for each affected package (npm install, pip install), credential scope reduction guidance, and reports on unfixable vulnerabilities. Args:...
Parameters* required
config_pathvaluePath to MCP client config directory. Auto-discovers all if omitted.
imagevalueDocker image to scan, e.g. 'nginx:1.25'.
skill_scanScan skill and instruction files for trust, findings, and provenance. Discovers supported files such as `CLAUDE.md`, `AGENTS.md`, `.cursorrules`, and `skills/*.md`, then parses referenced packages, MCP servers, credential env vars, audit findings, and trust verdicts.1 params
Scan skill and instruction files for trust, findings, and provenance. Discovers supported files such as `CLAUDE.md`, `AGENTS.md`, `.cursorrules`, and `skills/*.md`, then parses referenced packages, MCP servers, credential env vars, audit findings, and trust verdicts.
Parameters* required
pathstringPath to a skill/instruction file or directory to scan.default: .
skill_verifyVerify Sigstore provenance for skill and instruction files.1 params
Verify Sigstore provenance for skill and instruction files.
Parameters* required
pathstringPath to a skill/instruction file or directory to verify.default: .
skill_trustAssess the trust level of a SKILL.md file using ClawHub-style categories. Parses a SKILL.md file, runs security audit checks, then evaluates trust across 5 categories: Purpose & Capability, Instruction Scope, Install Mechanism, Credentials, and Persistence & Privilege. Returns...1 params
Assess the trust level of a SKILL.md file using ClawHub-style categories. Parses a SKILL.md file, runs security audit checks, then evaluates trust across 5 categories: Purpose & Capability, Instruction Scope, Install Mechanism, Credentials, and Persistence & Privilege. Returns...
Parameters* required
skill_pathstringPath to a SKILL.md file (or any skill/instruction file) to assess.
verifyVerify package integrity and SLSA provenance against registries. Checks SHA-256/SRI hashes against npm/PyPI registries and looks up SLSA build provenance attestations to confirm the package was built from its claimed source repository. Returns: JSON with integrity verification...2 params
Verify package integrity and SLSA provenance against registries. Checks SHA-256/SRI hashes against npm/PyPI registries and looks up SLSA build provenance attestations to confirm the package was built from its claimed source repository. Returns: JSON with integrity verification...
Parameters* required
ecosystemstringPackage ecosystem: 'npm' or 'pypi'.default: npm
packagestringPackage name with optional version, e.g. 'express@4.18.2' or 'requests==2.31.0'.
whereShow all MCP discovery paths and which config files exist. Lists every known MCP client config path per platform, indicating which files are present on the current system. Useful for debugging discovery issues or understanding where MCP configs live. Returns: JSON with per-cli...
Show all MCP discovery paths and which config files exist. Lists every known MCP client config path per platform, indicating which files are present on the current system. Useful for debugging discovery issues or understanding where MCP configs live. Returns: JSON with per-cli...
No parameter schema in public metadata yet.
inventoryList all discovered MCP configurations and servers without CVE scanning. Performs fast discovery and package extraction only — no vulnerability scanning. Use this for a quick inventory of configs, servers, and packages. Returns: JSON with discovered agents, their MCP servers,...1 params
List all discovered MCP configurations and servers without CVE scanning. Performs fast discovery and package extraction only — no vulnerability scanning. Use this for a quick inventory of configs, servers, and packages. Returns: JSON with discovered agents, their MCP servers,...
Parameters* required
config_pathvaluePath to MCP client config directory. Auto-discovers all if omitted.
tool_risk_assessmentScore live-introspected MCP tool capabilities and server risk. Uses runtime `tools/list` data to classify tool capabilities (READ/WRITE/EXECUTE/NETWORK/etc.) and compute a per-server risk profile. Returns: JSON with per-server tool profiles, capability counts, dangerous combin...2 params
Score live-introspected MCP tool capabilities and server risk. Uses runtime `tools/list` data to classify tool capabilities (READ/WRITE/EXECUTE/NETWORK/etc.) and compute a per-server risk profile. Returns: JSON with per-server tool profiles, capability counts, dangerous combin...
Parameters* required
config_pathvaluePath to MCP client config directory. Auto-discovers all if omitted.
timeoutnumberPer-server introspection timeout in seconds.default: 10
diffCompare a fresh scan against a baseline to find new and resolved vulns. Runs a new scan, then diffs it against the provided baseline (or the latest saved report). Shows new vulnerabilities, resolved ones, and changes in the package inventory. Returns: JSON with new findings, r...1 params
Compare a fresh scan against a baseline to find new and resolved vulns. Runs a new scan, then diffs it against the provided baseline (or the latest saved report). Shows new vulnerabilities, resolved ones, and changes in the package inventory. Returns: JSON with new findings, r...
Parameters* required
baselinevalueBaseline report JSON object. If omitted, uses the latest saved report from history.
marketplace_checkPre-install trust check for an MCP server package. Queries the package registry (npm or PyPI) for metadata and cross-references against the agent-bom MCP threat intelligence registry. Returns trust signals including download count, CVE status, and registry verification. Args:...2 params
Pre-install trust check for an MCP server package. Queries the package registry (npm or PyPI) for metadata and cross-references against the agent-bom MCP threat intelligence registry. Returns trust signals including download count, CVE status, and registry verification. Args:...
Parameters* required
ecosystemstringPackage ecosystem: 'npm' or 'pypi'.default: npm
packagestringPackage name, e.g. 'express', 'langchain'.
code_scanRun SAST (Static Application Security Testing) on source code via Semgrep. Scans for security flaws: SQL injection, XSS, command injection, hardcoded credentials, insecure deserialization, path traversal, etc. Returns findings with CWE classifications and severity levels. Requ...2 params
Run SAST (Static Application Security Testing) on source code via Semgrep. Scans for security flaws: SQL injection, XSS, command injection, hardcoded credentials, insecure deserialization, path traversal, etc. Returns findings with CWE classifications and severity levels. Requ...
Parameters* required
configstringSemgrep config. 'auto' = Semgrep Registry rules. Can be a path or registry string.default: auto
pathstringPath to source code directory to scan.
context_graphBuild an agent context graph with lateral movement analysis. Models reachability between agents, servers, credentials, tools, and vulnerabilities. Answers: "If agent X is compromised, what else becomes reachable?" Returns: JSON with nodes, edges, lateral_paths, interaction_ris...3 params
Build an agent context graph with lateral movement analysis. Models reachability between agents, servers, credentials, tools, and vulnerabilities. Answers: "If agent X is compromised, what else becomes reachable?" Returns: JSON with nodes, edges, lateral_paths, interaction_ris...
Parameters* required
config_pathvaluePath to MCP config directory. Omit to auto-discover.
max_depthintegerMax BFS depth for lateral path discovery (1-6, default 4).default: 4
source_agentvalueAgent name to compute lateral paths from. Omit for all agents.
graph_exportExport the agent dependency graph in graph-native formats. Formats: - **graphml** — yEd, Gephi, NetworkX compatible with AIBOM-typed attributes - **cypher** — Neo4j import script with AIBOM node labels (AIAgent, MCPServer, Package, Vulnerability) - **dot** — Graphviz (pipe thr...2 params
Export the agent dependency graph in graph-native formats. Formats: - **graphml** — yEd, Gephi, NetworkX compatible with AIBOM-typed attributes - **cypher** — Neo4j import script with AIBOM node labels (AIAgent, MCPServer, Package, Vulnerability) - **dot** — Graphviz (pipe thr...
Parameters* required
config_pathvaluePath to MCP config directory. Omit to auto-discover.
formatstringExport format: graphml, cypher, dot, mermaid, or json (default).default: json
analytics_queryQuery vulnerability trends, posture history, and runtime event summaries from ClickHouse. Requires AGENT_BOM_CLICKHOUSE_URL to be set. Returns empty results if ClickHouse is not configured.5 params
Query vulnerability trends, posture history, and runtime event summaries from ClickHouse. Requires AGENT_BOM_CLICKHOUSE_URL to be set. Returns empty results if ClickHouse is not configured.
Parameters* required
agentvalueFilter by agent name. Used by vuln_trends and posture_history.
daysintegerLookback window in days (default 30). Used by vuln_trends and posture_history.default: 30
hoursintegerLookback window in hours (default 24). Used by event_summary.default: 24
limitintegerMax results for top_cves (default 20).default: 20
query_typestringQuery type: vuln_trends, top_cves, posture_history, or event_summary
cis_benchmarkRun CIS benchmark checks against a cloud account. Evaluates security posture against CIS Foundations Benchmarks: - AWS Foundations v3.0: 18 checks (IAM, Storage, Logging, Networking) - Snowflake v1.0: 12 checks (Auth, Network, Data Protection, Monitoring, Access Control) - Azu...6 params
Run CIS benchmark checks against a cloud account. Evaluates security posture against CIS Foundations Benchmarks: - AWS Foundations v3.0: 18 checks (IAM, Storage, Logging, Networking) - Snowflake v1.0: 12 checks (Auth, Network, Data Protection, Monitoring, Access Control) - Azu...
Parameters* required
checksvalueComma-separated check IDs to run (e.g. '1.1,2.1'). Omit to run all.
profilevalueAWS CLI profile (only for provider=aws).
project_idvalueGCP project ID (only for provider=gcp). Falls back to GOOGLE_CLOUD_PROJECT env var.
providerstringCloud provider: 'aws', 'snowflake', 'azure', or 'gcp'.
regionvalueAWS region (only for provider=aws). Defaults to us-east-1.
subscription_idvalueAzure subscription ID (only for provider=azure). Falls back to AZURE_SUBSCRIPTION_ID env var.
fleet_scanBatch-scan a list of MCP server names against the security metadata registry. Designed for fleet inventory data (CrowdStrike, SIEM, CSV exports) where you have server names but not versions. Returns per-server risk assessment with registry match status, risk category, tools, c...1 params
Batch-scan a list of MCP server names against the security metadata registry. Designed for fleet inventory data (CrowdStrike, SIEM, CSV exports) where you have server names but not versions. Returns per-server risk assessment with registry match status, risk category, tools, c...
Parameters* required
serversstringComma-separated or newline-separated list of MCP server names to scan. E.g. '@modelcontextprotocol/server-filesystem, brave-search, glean, 50 sleep'.
runtime_correlateCross-reference vulnerability scan results with proxy runtime audit logs. Identifies which vulnerable tools were ACTUALLY CALLED in production, distinguishing confirmed attack surface from theoretical risk. Produces risk-amplified findings: a vulnerable tool that was called 10...3 params
Cross-reference vulnerability scan results with proxy runtime audit logs. Identifies which vulnerable tools were ACTUALLY CALLED in production, distinguishing confirmed attack surface from theoretical risk. Produces risk-amplified findings: a vulnerable tool that was called 10...
Parameters* required
audit_logstringPath to proxy audit JSONL log file (generated by 'agent-bom proxy --log audit.jsonl').default:
config_pathstringPath to MCP config directory (e.g. ~/.config/claude) or 'auto' for default discovery.default: auto
otel_tracestringPath to OTel OTLP JSON trace file for ML API provenance (detects deprecated/vulnerable model versions).default:
vector_db_scanScan for running vector databases and assess their security posture. Probes well-known ports for Qdrant (6333), Weaviate (8080), Chroma (8000), and Milvus (9091). For each discovered instance checks: - Authentication required (no_auth flag if collections accessible without cre...1 params
Scan for running vector databases and assess their security posture. Probes well-known ports for Qdrant (6333), Weaviate (8080), Chroma (8000), and Milvus (9091). For each discovered instance checks: - Authentication required (no_auth flag if collections accessible without cre...
Parameters* required
hostsvalueComma-separated hosts to probe (default: 127.0.0.1). Example: '127.0.0.1,10.0.0.5'.
aisvs_benchmarkRun AISVS v1.0 (AI Security Verification Standard) compliance checks. Evaluates the local AI system stack against OWASP AISVS v1.0 controls: - AI-4.1 Model files use safe serialization (not pickle/pt/bin) - AI-4.2 Model files have cryptographic integrity digest - AI-4.3 Ollama...1 params
Run AISVS v1.0 (AI Security Verification Standard) compliance checks. Evaluates the local AI system stack against OWASP AISVS v1.0 controls: - AI-4.1 Model files use safe serialization (not pickle/pt/bin) - AI-4.2 Model files have cryptographic integrity digest - AI-4.3 Ollama...
Parameters* required
checksvalueComma-separated AISVS check IDs to run (e.g. 'AI-4.1,AI-6.1'). Omit to run all 9 checks.
gpu_infra_scanDiscover GPU/AI compute infrastructure: containers, K8s nodes, and DCGM endpoints. Scans for GPU-enabled workloads from the local Docker daemon and Kubernetes clusters. Identifies NVIDIA base images, CUDA/cuDNN versions, explicit GPU device assignments, and unauthenticated DCG...2 params
Discover GPU/AI compute infrastructure: containers, K8s nodes, and DCGM endpoints. Scans for GPU-enabled workloads from the local Docker daemon and Kubernetes clusters. Identifies NVIDIA base images, CUDA/cuDNN versions, explicit GPU device assignments, and unauthenticated DCG...
Parameters* required
k8s_contextvaluekubectl context to use for K8s GPU node discovery. Omit for current context.
probe_dcgmbooleanWhether to probe DCGM exporter endpoints on port 9400 (unauthenticated metrics leak detection).default: true
dataset_card_scanScan a directory for ML dataset card metadata and provenance. Discovers and parses: - HuggingFace dataset_info.json (auto-generated metadata) - HuggingFace README.md YAML frontmatter (dataset cards) - DVC .dvc tracking files (data versioning provenance) Flags: UNLICENSED_DATAS...1 params
Scan a directory for ML dataset card metadata and provenance. Discovers and parses: - HuggingFace dataset_info.json (auto-generated metadata) - HuggingFace README.md YAML frontmatter (dataset cards) - DVC .dvc tracking files (data versioning provenance) Flags: UNLICENSED_DATAS...
Parameters* required
directorystringDirectory path to scan for dataset cards (dataset_info.json, README.md frontmatter, .dvc files).
training_pipeline_scanScan a directory for ML training pipeline lineage and provenance. Discovers and parses: - MLflow: meta.yaml, MLmodel, requirements.txt, conda.yaml - Kubeflow: Argo workflow YAML, KFP v2 pipelineSpec YAML - W&B: wandb-metadata.json, config.yaml, wandb-summary.json Flags: UNSAFE...1 params
Scan a directory for ML training pipeline lineage and provenance. Discovers and parses: - MLflow: meta.yaml, MLmodel, requirements.txt, conda.yaml - Kubeflow: Argo workflow YAML, KFP v2 pipelineSpec YAML - W&B: wandb-metadata.json, config.yaml, wandb-summary.json Flags: UNSAFE...
Parameters* required
directorystringDirectory path to scan for training pipeline artifacts (MLflow, Kubeflow, W&B).
browser_extension_scanScan installed browser extensions for dangerous permissions. Scans Chrome, Chromium, Brave, Edge, and Firefox for extensions with: - nativeMessaging (can execute arbitrary commands) - debugger (can intercept all browser traffic) - cookies/clipboardRead on AI domains - Broad ho...1 params
Scan installed browser extensions for dangerous permissions. Scans Chrome, Chromium, Brave, Edge, and Firefox for extensions with: - nativeMessaging (can execute arbitrary commands) - debugger (can intercept all browser traffic) - cookies/clipboardRead on AI domains - Broad ho...
Parameters* required
include_low_riskbooleanInclude low-risk extensions in results (default: only medium+ risk).default: false
model_provenance_scanCheck ML model provenance and supply chain metadata. Queries HuggingFace Hub or Ollama for: - Serialization format (safetensors=safe, pickle/pt=unsafe) - SHA256 digest verification - Gated/private status - Model card presence - Risk assessment (critical/high/medium/safe) Retur...2 params
Check ML model provenance and supply chain metadata. Queries HuggingFace Hub or Ollama for: - Serialization format (safetensors=safe, pickle/pt=unsafe) - SHA256 digest verification - Gated/private status - Model card presence - Risk assessment (critical/high/medium/safe) Retur...
Parameters* required
model_idstringHuggingFace model ID (e.g. 'meta-llama/Llama-3-8B') or Ollama model name (e.g. 'llama3').
sourcestringModel source: 'huggingface' or 'ollama' (default: huggingface).default: huggingface
prompt_scanScan prompt template files for injection risks and security issues. Discovers and analyzes: - .prompt files - system_prompt.* files - Files in prompts/ directories Checks for injection patterns, unsafe variable interpolation, and missing guardrails in prompt templates.1 params
Scan prompt template files for injection risks and security issues. Discovers and analyzes: - .prompt files - system_prompt.* files - Files in prompts/ directories Checks for injection patterns, unsafe variable interpolation, and missing guardrails in prompt templates.
Parameters* required
directorystringDirectory path to scan for prompt template files (.prompt, system_prompt.*, prompts/ directories).
model_file_scanScan a directory for ML model files and assess serialization risks. Discovers model files and checks: - Serialization format (safetensors=safe, pickle/joblib=unsafe) - File size and format metadata - GGUF/GGML quantization details - Known unsafe patterns in pickle-based format...1 params
Scan a directory for ML model files and assess serialization risks. Discovers model files and checks: - Serialization format (safetensors=safe, pickle/joblib=unsafe) - File size and format metadata - GGUF/GGML quantization details - Known unsafe patterns in pickle-based format...
Parameters* required
directorystringDirectory path to scan for ML model files (.gguf, .safetensors, .onnx, .pt, .pkl, .h5, etc.).
ai_inventory_scanScan source code for AI component usage patterns. Detects: - AI SDK imports (openai, anthropic, langchain, etc.) across 7 languages - Model string references (gpt-4o, claude-3-5-sonnet, llama-3, etc.) - Hardcoded API keys (sk-proj-*, sk-ant-*, hf_*, etc.) - Deprecated model us...1 params
Scan source code for AI component usage patterns. Detects: - AI SDK imports (openai, anthropic, langchain, etc.) across 7 languages - Model string references (gpt-4o, claude-3-5-sonnet, llama-3, etc.) - Hardcoded API keys (sk-proj-*, sk-ant-*, hf_*, etc.) - Deprecated model us...
Parameters* required
directorystringDirectory to scan for AI SDK imports, model refs, API keys, shadow AI (Python/JS/TS/Java/Go/Rust/Ruby).
license_compliance_scanEvaluate package licenses against compliance policy. Categorizes each package license using the full SPDX catalog (2,500+ licenses) with proper expression parsing (OR/AND/WITH), deprecated ID normalization, and network-copyleft detection (AGPL, EUPL, OSL). Risk tiers: permissi...2 params
Evaluate package licenses against compliance policy. Categorizes each package license using the full SPDX catalog (2,500+ licenses) with proper expression parsing (OR/AND/WITH), deprecated ID normalization, and network-copyleft detection (AGPL, EUPL, OSL). Risk tiers: permissi...
Parameters* required
policy_jsonstringOptional JSON policy: {"license_block": ["GPL-*"], "license_warn": ["LGPL-*"]}. Uses default policy (block GPL/AGPL/SSPL/BUSL/EUPL/OSL, warn LGPL/MPL/EPL/CDDL) if empty.default:
scan_jsonstringJSON string of a previous scan result (from the 'scan' tool) containing agents with packages. Or a JSON array of {"name": "pkg", "version": "1.0", "ecosystem": "npm", "license": "MIT"} objects.
ingest_external_scanIngest Trivy, Grype, or Syft JSON scan output and return packages with blast radius analysis. Auto-detects the scanner format from the JSON structure: - Trivy (``trivy fs --format json``): Results + Vulnerabilities - Grype (``grype --output json``): matches array - Syft (``syf...1 params
Ingest Trivy, Grype, or Syft JSON scan output and return packages with blast radius analysis. Auto-detects the scanner format from the JSON structure: - Trivy (``trivy fs --format json``): Results + Vulnerabilities - Grype (``grype --output json``): matches array - Syft (``syf...
Parameters* required
scan_jsonstringJSON string from Trivy, Grype, or Syft scan output
Find vulnerable software behind your AI agents—and trace the exposure evidence.
For AppSec and platform engineers responsible for AI agents and MCP servers: scan a repository, correlate its findings with agent and infrastructure context, and prioritize fixes using blast radius and reachability evidence. Open security scanner and self-hosted control plane for AI, MCP, and cloud infrastructure. Local scans need no account.
Quick start · Sample graph · Self-host · Product tour · Docs
Quick start
From the repository you want to inspect:
pip install agent-bom
agent-bom scan .
Read the inventory, findings, coverage gaps, and remediation guidance in the terminal.
Save a report with agent-bom scan . -f sarif -o findings.sarif, then
upload it and gate CI.
Run agent-bom doctor if setup fails. See the first-run guide.
No project handy? Run agent-bom scan --demo --offline for a bundled sample.
Exit 1 is expected: the sample trips the security gate. A non-zero exit
can mean a security gate or incomplete assessment; inspect the report and coverage.
See the exit codes.
The recording uses labeled sample data and bundled advisories. Credential references are names, not secret values. Recorded relationships do not prove exploitation or successful data access.
Investigate context and exposure
Which agent uses the vulnerable component? What could it reach? What evidence supports that path? Correlate retained scans by exact, tenant-scoped identities; trace the recorded blast radius from each agent through its MCP servers to packages, findings, credentials and data stores. Inspect each relationship's source and evidence kind, then rescan the same scope to check what changed.
Fictional sample estate. Dashed use, credential and access links are configured or modeled, not observed at runtime; path analysis covers the collected snapshot only.
From agent to verified fix: select Document Intake Agent → inspect CVE-2023-4863 (high, KEV-listed) and the evidence on each arrow → take the proposed remediation → rescan the changed pin and compare snapshots. The comparison verifies the changed input, not a running deployment.
Supporting evidence: one package, three parsed inputs. A repository pin, an
image SBOM and a modeled Kubernetes workload resolve to one pillow@9.0.0. The
image inventory and the deployment occurrence stay separate nodes; the advisory
receipt is open.
Real parsers, modeled infrastructure; a graph path does not prove exploitation.
Explore context, correlation and reachability · Run the reference lab · Reproduce these screenshots
Repository and cloud investigations
Trace source imports, deployment configuration and CI to a published container and its vulnerable packages:
Follow a public API gateway into a vulnerable workload, its role and a PII bucket:
Open the sample graph
pip install 'agent-bom[ui]==0.108.4'
agent-bom quickstart --run --offline
Run the server command it prints, then open its graph URL. Offline quickstart skips package-CVE lookup, so zero CVEs is not a clean verdict; use the bundled demo for advisory-backed findings or populate the advisory database.
Self-host in your environment
Your infrastructure, identity, database, and audit boundary. Start a local pilot from a published release checkout:
git clone --depth 1 --branch v0.109.0 https://github.com/koda-ai-studio/agent-bom.git && cd agent-bom
AGENT_BOM_IMAGE_TAG=0.109.0 docker compose up -d
Open http://localhost:3000, then Connections or New Scan. The pilot binds to loopback and retains state in a Docker volume. For cloud accounts, add a scoped read-only connection, verify access, then start a scan. Use the authenticated deployment.
- Scan with CLI or CI; export findings, SBOMs and reports.
- Centralize inventory, graph evidence, remediation and compliance in your own control plane.
- Enforce policy on selected live MCP tool calls through the proxy or gateway.
Docker pilot guide · Compose with PostgreSQL · Choose a deployment · Enterprise controls · Connect cloud accounts
Work with your existing tools
Use CLI or GitHub Action, REST API, or MCP; export SARIF, CycloneDX, SPDX, JSON and HTML. Cloud connectors and fleet sync collect inventory; proxy and gateway deployments add runtime evidence.
For coding assistants, run agent-bom mcp server.
Start with eight focused tools in the default profile.
Choose an MCP profile for graph, cloud, runtime or audit work.
Try three investigations: affected agents, exposure receipts and a before/after scan comparison.
Import existing scanner reports without replacing their source evidence.
Prefer an isolated invocation? Use uvx agent-bom scan . or check a dependency
with uvx agent-bom check requests@2.33.0 --ecosystem pypi. Add
pre-commit and CI setup for repeated checks.
Proxy, gateway and fleet · Integration capability matrix · MCP client setup · Smithery setup and manifest
Trust and evidence
Discovery uses read-only access by default. Explicit disk side-scans create temporary cloud resources. Missing evidence stays unavailable or partial; control mappings are not audit certification.
Measured matcher proof · Product boundaries · Permissions · Threat model · Release verification · Graph data model
Contributing and support
Contributing · Capabilities and roadmap · Support · Report an inaccurate finding · Apache-2.0
Source version: v0.109.0 · Latest release: v0.109.0 · Changelog
Featured
Keeps your Mac awake while Claude Code, Codex or Cursor works. Lets it sleep when they are done.
Try free for 7 days →Block distracting apps from your iPhone permanently without a 3rd party app. Free and open source.
Block now (100% free) →Notes, actions and memory. Without a meeting bot. First month 100% off.
Download for free →belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →Free an open-source skills that make AI coding agents easier to understand, verify, and control.
Download for free →Connect your Claude agent to live crypto prices and trading routes via 1inch
Get the MCP →Configuration
NVD_API_KEYsecretNVD API key for higher rate limits on vulnerability enrichment
Registryactive
Packageagent-bom
TransportSTDIO
AuthRequired
UpdatedApr 28, 2026
