English Français العربية

agent-bom

Official registry AI and agents

Scan AI/MCP dependencies, descriptor injection, risky tool inputs and authentication configuration.

Source code Documentation

Install

Add this to your client's MCP configuration (Claude Desktop: claude_desktop_config.json; Cursor: .cursor/mcp.json; VS Code and others use the same "mcpServers" shape).

PYPI package agent-bom
Claude Code 
claude mcp add agent-bom -e 'NVD_API_KEY=<your nvd_api_key>' -- uvx agent-bom==0.110.0 mcp server
JSON configuration (Claude Desktop, Cursor, VS Code) 
{
    "mcpServers": {
        "agent-bom": {
            "command": "uvx",
            "args": [
                "agent-bom==0.110.0",
                "mcp",
                "server"
            ],
            "env": {
                "NVD_API_KEY": "<your nvd_api_key>"
            }
        }
    }
}

Environment variables

  • NVD_API_KEY secret NVD API key for higher rate limits on vulnerability enrichment

Documentation

From the project's README on GitHub, refreshed weekly. Links open on GitHub.

Contents
  1. Quick start
  2. Use it from Claude Code or Codex
  3. Investigate context and exposure
  4. Open the sample graph
  5. Self-host in your environment
  6. Trust and evidence
  7. Contributing and support

Find vulnerable software behind your AI agents—and trace the exposure evidence.

Open security scanner and self-hosted control plane for AI, MCP, and cloud infrastructure. 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 by blast radius and reachability evidence. Local scans need no account.

Quick start · Claude Code and Codex · 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.

Use it from Claude Code or Codex

Ask your coding agent instead of reading a report. In Claude Code:

/plugin marketplace add koda-ai-studio/agent-bom
/plugin install agent-bom@agent-bom

In Codex, run codex plugin marketplace add koda-ai-studio/agent-bom, then install agent-bom-local from the Plugins Directory. Both plugins run the pinned agent-bom release locally and send nothing to an agent-bom service.

AskSkill
"Is this project safe to ship?"checkup: one verdict and the three fixes that matter most
"Am I affected by CVE-2025-29927?"affected: affected or not found in what was scanned, never "safe"
"What have my agents been doing?"activity: MCP usage, unused servers, risky commands from local session history
"Are my agent settings too permissive?"audit-mcp and audit-skills
"Give me an AI-BOM"bom: CycloneDX or SPDX for this machine, a project, an image or a cloud account

Add /plugin install agent-bom-guard@agent-bom to block malicious and typosquatted package installs before Claude runs them. All skills and their permissions · Guard details

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

Explain a finding to your team: create an impact brief with affected assets, source receipts, evidence gaps and the next action to review.

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]==0.110.0'
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 v0.110.0 https://github.com/koda-ai-studio/agent-bom.git && cd agent-bom
AGENT_BOM_IMAGE_TAG=0.110.0 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 other MCP clients, 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.

MITRE technique associations provide investigation context, not proof of an attack. ATLAS mapping receipts retain the weakness association and source catalog hashes; modeled graph paths do not establish observed execution or effective access.

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: v0.110.0 · Latest release: v0.110.0 · Changelog

Frequently asked questions

What is agent-bom?

Scan AI/MCP dependencies, descriptor injection, risky tool inputs and authentication configuration.

How do I install agent-bom?

It runs on your machine. In Claude Code: claude mcp add agent-bom -e 'NVD_API_KEY=<your nvd_api_key>' -- uvx agent-bom==0.110.0 mcp server. For other clients, paste the JSON configuration from this page into their MCP settings.

Does agent-bom need an API key?

Yes. It expects NVD_API_KEY, which you set in its configuration.

Is agent-bom open source?

Yes. Its code is on GitHub under the Apache-2.0 license.

Who maintains agent-bom?

It is published by koda-ai-studio. AI.tn lists it but does not maintain or endorse it.

From the official MCP Registry. Listing is not an endorsement: review a server's code and permissions before giving it access to your data.