# agent-bom (pypi · agent-bom)

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

- Trust score: 82/100 (high trust)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-10-25

## Components

- pypi · `agent-bom`: 82/100 (this document), [markdown](https://verifymcp.io/servers/koda-ai-studio-agent-bom/agent-bom.md), [page](https://verifymcp.io/servers/koda-ai-studio-agent-bom/agent-bom)

## Channel facts

- Registry: `pypi`
- Package: `agent-bom`
- Version: `0.110.0`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-10-25.

- **Supply Chain Security**: 100/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - Runs setuptools.build_meta at install time, a recognised build step with no custom scripting around it.
  - 6 of 67 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 100/100
  - Source repository is publicly reachable at the declared URL.
  - Cryptographically verified build provenance (signed, bound to koda-ai-studio/agent-bom).
  - Clear OSI-approved license (Apache-2.0).
  - Actively maintained (last published 2 days ago).
  - Publishes a security disclosure policy (SECURITY.md).
- **Schema Quality & AI Usability**: 76/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 3093 tokens (~257/item across 12 items; 8 tools + 4 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 0/100
  - Stability not yet verified: not enough scan history yet (needs a 30-day window).
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 8 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 10 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a current MCP spec version (2026-07-28).

**Unverified: 1 category.** A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.

## Install

### How do I install the agent-bom MCP server?

agent-bom runs locally as a PyPI package, launched with uvx agent-bom. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add koda-ai-studio-agent-bom -- uvx agent-bom
```

### Cursor

```json
{
  "mcpServers": {
    "koda-ai-studio-agent-bom": {
      "command": "uvx",
      "args": [
        "agent-bom"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "koda-ai-studio-agent-bom": {
      "command": "uvx",
      "args": [
        "agent-bom"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add koda-ai-studio-agent-bom -- uvx agent-bom
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "koda-ai-studio-agent-bom": {
      "type": "local",
      "command": [
        "uvx",
        "agent-bom"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add koda-ai-studio-agent-bom --command uvx --arg agent-bom
```

### Hermes

```yaml
mcp_servers:
  koda-ai-studio-agent-bom:
    command: "uvx"
    args: ["agent-bom"]
```

### Netclaw

```json
{
  "McpServers": {
    "koda-ai-studio-agent-bom": {
      "Transport": "stdio",
      "Command": "uvx",
      "Arguments": [
        "agent-bom"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add koda-ai-studio-agent-bom -t stdio -c uvx -a agent-bom
```

### Other

```json
{
  "mcpServers": {
    "koda-ai-studio-agent-bom": {
      "command": "uvx",
      "args": [
        "agent-bom"
      ]
    }
  }
}
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-10-23 (score 82, +15)

- [security improvement] Malware scan: unverified → pass

### 2026-10-22 (score 67)

First indexed and scored.

## MCP tools (8)

### `scan` (~1263 tokens)

Security Scan

Run a full AI supply chain security scan and return an AI-BOM.

Point it at a target with one of:
  • repo_url     — a public git repo URL (cloned + scanned, no checkout)
  • config_path  — a local project / MCP-config directory
  • image        — a Docker image
  • sbom_path    — an existing CycloneDX/SPDX SBOM
  • package      — a single package or MCP launch command (pair it with
                   ``ecosystem`` when the spec names no launcher)
With none of these, it auto-discovers local MCP clients (Claude Desktop,
Cursor, Windsurf, VS Code Copilot, OpenClaw, etc.).

It extracts package dependencies, looks up CVEs (online via OSV.dev and
advisory sources unless offline mode is requested or configured),
assesses config security (credential exposure, tool access), computes
blast radius, and returns structured results. Scanning is fully static
and read-only — repository and image contents are parsed, never executed.

Returns:
    JSON. By default a bounded summary: counts (packages, agents,
    findings by severity/category), top findings, affected paths, and a
    result_id. Page any full-fidelity section with
    scan(result_id=..., section='findings', offset=0, limit=25).
    An incomplete scan (e.g. vulnerability source unavailable) is
    returned as an error result whose body is still JSON.

Input parameters:

- `auto_update_db` (boolean): Explicitly refresh the local vuln DB when older than the daily freshness target before scanning.
- `config_path`: Local directory to scan — a project root or an MCP client config directory. Auto-discovers installed MCP clients if omitted unless no_discover=true. Mutually exclusive with repo_url.
- `db_sources`: Comma-separated DB sources to sync before scanning (e.g. 'nvd,ghsa,osv,epss,kev').
- `detail` (string): JSON output only. 'summary' (default): counts, top findings, affected paths, and a result_id for paged follow-ups. 'full': the whole AI-BOM document, shortened structurally (still valid JSON, with _t…
- `ecosystem`: Ecosystem of ``package`` when the spec does not name a launcher: 'npm', 'pypi', 'go', 'cargo', 'maven', 'nuget', 'rubygems', 'composer', 'swift', 'pub', 'hex', 'conda', 'deb', 'apk', or 'rpm'. Omitte…
- `enrich` (boolean): Enable NVD CVSS, EPSS probability, and CISA KEV enrichment.
- `fail_severity`: Return failure status if vulns at this severity or higher: critical, high, medium, low.
- `image`: Docker image to scan (e.g. 'nginx:1.25', 'ghcr.io/org/app:v1').
- `limit` (integer): Maximum items per page of `section` (1-200).
- `no_discover` (boolean): Disable ambient host MCP-client discovery. Explicit repo/config, image, SBOM, and package targets are still scanned; use this for deterministic CI.
- `offline`: true: use the local vulnerability DB only and skip registry, OSV, GHSA, and NVIDIA network lookups (requires a populated DB from `agent-bom db update`). false: query those sources online. Omitted: on…
- `offset` (integer): Zero-based item offset into `section`.
- `output_format` (string): Output format: 'json' (default), 'sarif', 'cyclonedx', 'spdx', 'junit', 'csv', or 'markdown'.
- `package`: Direct package or MCP launch command to scan, e.g. 'npx @modelcontextprotocol/server-filesystem@2025.1.14' or '@modelcontextprotocol/server-filesystem'. A bare 'name@version' spec is assumed to be np…
- `policy`: Policy object to evaluate alongside scan results, e.g. {"rules": [{"id": "no-critical", "severity_gte": "critical", "action": "fail"}]}.
- `repo_url`: Public git repository URL to clone and scan, e.g. 'https://github.com/org/repo'. Maps the repo's dependencies, project structure, secrets, IaC, and AI/MCP usage into an AI-BOM. Static and read-only:…
- `result_id`: result_id from a previous scan response. With it, no new scan runs: returns that result's summary, or one page of `section`.
- `sbom_path`: Path to existing CycloneDX or SPDX JSON SBOM file to ingest.
- `scorecard` (boolean): Enrich packages with OpenSSF Scorecard scores (requires resolvable GitHub repos).
- `section`: Section of a stored result to page, e.g. 'findings', 'blast_radius', 'packages', 'exposure_paths'.
- `transitive` (boolean): Resolve transitive dependencies for npx/uvx packages.
- `verify_integrity` (boolean): Verify package SHA-256/SRI hashes and SLSA provenance against registries.
- `warn_severity`: Return 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'.

Output parameters:

- `result` (string)

### `check` (~393 tokens)

Package CVE Check

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",
             "@modelcontextprotocol/server-filesystem@2025.1.14",
             or just "requests" (resolves @latest).
    ecosystem: Package ecosystem — "npm", "pypi", "go", "cargo",
               "maven", "nuget", "rubygems", "composer", "swift",
               "pub", "hex", "conda", "deb", "apk", or "rpm".
               Defaults to "npm".

Returns:
    JSON with package, version, ecosystem, vulnerability count,
    and vulnerability details (id, severity, cvss, fix version, summary).

Input parameters:

- `ecosystem` (string): Package ecosystem: 'npm', 'pypi', 'go', 'cargo', 'maven', 'nuget', 'rubygems', 'composer', 'swift', 'pub', 'hex', 'conda', 'deb', 'apk', or 'rpm'.
- `offline` (boolean): Use only the local advisory database. An explicit version is required; registry resolution and publication checks are disabled.
- `package` (string, required): Package name with optional version, e.g. 'express@4.18.2', '@modelcontextprotocol/server-filesystem@2025.1.14', or 'requests' (resolves @latest).
- `version`: Optional package version when omitted from ``package`` (e.g. package='flask', version='0.12.2'). Prefer embedding in ``package`` as 'flask@0.12.2' or 'flask==0.12.2' when possible.

Output parameters:

- `result` (string)

### `intel_lookup` (~61 tokens)

Threat Intel Advisory Lookup

Look up one advisory from the local threat-intel database.

Input parameters:

- `advisory_id` (string, required): CVE, GHSA, or OSV advisory ID, e.g. CVE-2024-1234 or GHSA-abcd-1234-wxyz.

Output parameters:

- `result` (string)

### `policy_check` (~181 tokens)

Policy Evaluation

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 string containing policy rules. Example:
        {"rules": [{"id": "no-critical", "severity_gte": "critical",
        "action": "fail"}, {"id": "no-kev", "kev": true, "action": "fail"}]}

Returns:
    JSON with passed (bool), violations list, failure_count, and
    warning_count.

Input parameters:

- `policy_json` (string, required): JSON string containing policy rules, e.g. {"rules": [{"id": "no-critical", "severity_gte": "critical", "action": "fail"}]}.

Output parameters:

- `result` (string)

### `generate_sbom` (~178 tokens)

Generate SBOM

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 1.7) or "spdx" (SPDX 3.0).
    config_path: Path to a specific MCP config directory.
                 If not provided, auto-discovers all local agent configs.

Returns:
    JSON string containing the SBOM in the requested format.

Input parameters:

- `config_path`: Path to MCP client config directory. Auto-discovers all if omitted.
- `format` (string): SBOM format: 'cyclonedx' (CycloneDX 1.7) or 'spdx' (SPDX 3.0).

Output parameters:

- `result` (string)

### `compliance` (~261 tokens)

Compliance Posture

Return compliance posture with its source: the tenant's persisted evidence, or a labelled local scan.

With completed scans in the control plane, ``summary`` is exactly
\``/v1/compliance/summary``; ``framework`` adds ``/v1/compliance/{framework}``
and ``control`` pages the driving finding ids from
\``/v1/findings?framework=&control=``. Otherwise (or with
source='local_scan') it scans local MCP configurations and labels that scope.

Input parameters:

- `config_path`: Local scan only: MCP client config directory. Auto-discovers if omitted.
- `control`: Persisted only: page the finding ids driving this control.
- `cursor`: driving_findings.next_cursor from the previous page.
- `framework`: Persisted only: add one framework's controls, e.g. 'soc2'.
- `image`: Local scan only: Docker image to scan, e.g. 'nginx:1.25'.
- `limit` (integer): Driving finding ids per page.
- `source` (string): auto: persisted tenant evidence when it exists, else a labelled local scan. persisted / local_scan force one.
- `tenant_id` (string): Tenant scope for persisted compliance. Defaults to 'default'.

Output parameters:

- `result` (string)

### `remediate` (~172 tokens)

Remediation Plan

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:
    config_path: Path to a specific MCP config directory.
                 If not provided, auto-discovers all local agent configs.
    image: Docker image reference to scan (e.g. "nginx:1.25").

Returns:
    JSON with package_fixes (upgrade commands by ecosystem),
    credential_fixes (scope reduction steps), and unfixable items.

Input parameters:

- `config_path`: Path to MCP client config directory. Auto-discovers all if omitted.
- `image`: Docker image to scan, e.g. 'nginx:1.25'.

Output parameters:

- `result` (string)

### `exposure_paths` (~354 tokens)

Exposure Paths

Return the attack-path queue in the dashboard's order, with why each path ranks where it does.

Ranking is ``ranking.order`` (evidence tier, KEV, severity, evidence confidence,
composite risk, credential count); every path carries ``rank``, ``evidenceTier``,
\``isKev``, ``severity``, ``evidenceConfidence`` and ``rankingFactors``. Totals,
filters and cursor pages match ``/v1/graph/attack-paths``.

Input parameters:

- `credential_id`: Credential name or node id exposed on the path.
- `cursor`: pagination.next_cursor; keep the filters unchanged.
- `finding_id`: CVE, advisory or finding node id on the path.
- `has_credential`: Only paths that do (true) or do not (false) expose a credential.
- `kev`: Only paths through a known-exploited finding (true) or none (false).
- `limit` (integer): Maximum ranked exposure paths to return.
- `min_risk` (number): Minimum composite path risk (0-100).
- `min_severity`: Worst on-path finding at least this severe.
- `node_id`: Any graph node the path passes through.
- `scan_id`: Optional historical scan ID. Omit for the current tenant estate.
- `source_type`: Entrypoint entity type, e.g. 'agent'.
- `target_id`: Only paths ending at this graph node id.
- `tenant_id` (string): Tenant scope. Defaults to 'default'.
- `view` (string): summary (default): rank, risk, KEV, evidence tier, endpoints, finding/credential ids. full adds hops, relationships, nodes and edges.

Output parameters:

- `result` (string)

## Diagnostics

Captured diagnostic sections: Provenance, Install scripts, Dependencies. The full working is on the page: https://verifymcp.io/servers/koda-ai-studio-agent-bom/agent-bom#diagnostics

## Score history

- 2026-10-25: 82
- 2026-10-24: 82
- 2026-10-23: 82
- 2026-10-22: 67

## Common questions

### What is the agent-bom MCP server?

agent-bom is an MCP server listed in the public MCP registry as io.github.koda-ai-studio/agent-bom. Scan AI/MCP dependencies, descriptor injection, risky tool inputs and authentication configuration. This page covers its PyPI package (agent-bom).

### Is the agent-bom MCP server safe to use?

agent-bom scores 82 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 25 October 2026. Its build provenance is signed and verified. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the agent-bom MCP server expose?

agent-bom exposes 8 tools: scan, check, intel_lookup, policy_check, generate_sbom, and 3 more. Their descriptions and schemas cost roughly 2,863 tokens of context every time the server is loaded.

### Is the agent-bom MCP server still maintained?

agent-bom is still listed as active in the MCP registry. We last reached this channel on 25 October 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What licence is the agent-bom MCP server under?

agent-bom declares the Apache-2.0 licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

## Links

- PyPI project: https://pypi.org/project/agent-bom/
- Socket report: https://socket.dev/pypi/package/agent-bom
- Repository: https://github.com/koda-ai-studio/agent-bom
- Changelog RSS feed: https://verifymcp.io/servers/koda-ai-studio-agent-bom/agent-bom.xml
- Changelog JSON feed: https://verifymcp.io/servers/koda-ai-studio-agent-bom/agent-bom.json
- HTML version of this page: https://verifymcp.io/servers/koda-ai-studio-agent-bom/agent-bom