# DEEPBOM (npm · deepbom)

Browser-local and CLI static evidence for deployed AI model artifacts.

- Trust score: 86/100 (high trust)
- Change this week: +18
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-09-21

## Components

- remote · `deepbom.org`: 74/100, [markdown](https://verifymcp.io/servers/junhwan-kwon-deepbom/deepbom-2.md), [page](https://verifymcp.io/servers/junhwan-kwon-deepbom/deepbom-2)
- npm · `deepbom`: 86/100 (this document), [markdown](https://verifymcp.io/servers/junhwan-kwon-deepbom/deepbom.md), [page](https://verifymcp.io/servers/junhwan-kwon-deepbom/deepbom)

## Channel facts

- Registry: `npm`
- Package: `deepbom`
- Version: `1.103.0`
- 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 2026-09-21.

- **Supply Chain Security**: 100/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - No install/post-install scripts declared.
  - No production dependencies, so there is no dependency health to assess.
- **Provenance & Transparency**: 100/100
  - Source repository is publicly reachable at the declared URL.
  - Cryptographically verified build provenance (signed, bound to JunHwan-Kwon/deepbom).
  - Clear OSI-approved license (Apache-2.0).
  - Actively maintained (last published 3 days ago).
  - Publishes a security disclosure policy (SECURITY.md).
- **Schema Quality & AI Usability**: 65/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 1045 tokens (~261/item across 4 items; 4 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 43/100
  - Stability observed for 13 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 99/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 96% of tool parameters carry a description.
  - Structured output schemas are declared (75% 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 4 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 5 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### How do I install the DEEPBOM MCP server?

DEEPBOM runs locally as an npm package, launched with npx -y deepbom. 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 junhwan-kwon-deepbom -- npx -y deepbom
```

### Cursor

```json
{
  "mcpServers": {
    "junhwan-kwon-deepbom": {
      "command": "npx",
      "args": [
        "-y",
        "deepbom"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "junhwan-kwon-deepbom": {
      "command": "npx",
      "args": [
        "-y",
        "deepbom"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add junhwan-kwon-deepbom -- npx -y deepbom
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "junhwan-kwon-deepbom": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "deepbom"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add junhwan-kwon-deepbom --command npx --arg -y --arg deepbom
```

### Hermes

```yaml
mcp_servers:
  junhwan-kwon-deepbom:
    command: "npx"
    args: ["-y", "deepbom"]
```

### Netclaw

```json
{
  "McpServers": {
    "junhwan-kwon-deepbom": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "deepbom"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add junhwan-kwon-deepbom -t stdio -c npx -a -y deepbom
```

### Other

```json
{
  "mcpServers": {
    "junhwan-kwon-deepbom": {
      "command": "npx",
      "args": [
        "-y",
        "deepbom"
      ]
    }
  }
}
```

## 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.

### 2026-09-21 (score 86, +1)

No change was recorded against any check on this day. Stability & Change Management went from 40 to 43. That category is still filling its 30-day observation window: 12 days of observed history at the previous scan, 13 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-19 (score 85, +1)

No change was recorded against any check on this day. Stability & Change Management went from 33 to 37. That category is still filling its 30-day observation window: 10 days of observed history at the previous scan, 11 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-18 (score 84, +11)

- [security improvement] Known CVEs: unverified → pass
- [functional improvement] Dependency health: unverified → pass

### 2026-09-17 (score 73, +16)

- [security improvement] Malware scan: unverified → pass
- [security improvement] Known CVEs: unverified → pass
- [functional improvement] Dependency health: unverified → pass
- [functional] Package version: 1.101.0 → 1.103.0
- [functional] Package version: 1.101.0 → 1.102.0

### 2026-09-16 (score 57, −26)

- [security regression] Malware scan: pass → unverified
- [security regression] Known CVEs: pass → unverified
- [functional regression] Dependency health: pass → unverified
- [functional] Package version: 1.99.1 → 1.101.0

### 2026-09-15 (score 83, +15)

- [security improvement] Malware scan: unverified → pass

### 2026-09-14 (score 68, +12)

- [security improvement] Malware scan: unverified → pass
- [security improvement] Known CVEs: unverified → pass
- [functional improvement] Dependency health: unverified → pass
- [functional] Package version: 1.97.4 → 1.99.1

### 2026-09-13 (score 56, −25)

- [security regression] Malware scan: pass → unverified
- [security regression] Known CVEs: pass → unverified
- [functional regression] Schema quality: 225 → 252
- [functional regression] Dependency health: pass → unverified
- [functional] Package version: 1.96.15 → 1.97.4
- [functional] Package version: 1.96.15 → 1.97.3
- [functional] Package version: 1.96.15 → 1.97.0

## MCP tools (4)

### `deepbom_capabilities` (~44 tokens)

Inspect DEEPBOM capabilities

Return deepbom.cli_capabilities.v1: supported artifact formats, output contracts, scan policies, target profiles, and exit codes. Call this before assuming an option exists.

Output parameters:

- `schema`

### `deepbom_audit` (~583 tokens)

Audit a deployed model artifact

Audit one local or immutable remote model artifact and return local static evidence. Request section=model_summary for the common operation/storage table derived from Model IR; it does not infer framework trainability or runtime order. Supported remote identities are hf:// with a full commit, gs:// with an object generation, and HTTPS with SHA-256. Remote bytes may be downloaded into a content-addressed local cache but are never uploaded by DEEPBOM. Findings distinguish artifact_defect, caution, and evidence_gap; an evidence_gap is not a defect. The result never establishes executed accelerator assignment, latency, energy, accuracy, or device fit.

Input parameters:

- `cache_dir` (string): Content-addressed cache directory under the allowed roots.
- `expected_sha256` (string): Independent expected digest for a local or remote artifact.
- `external_data_dir` (string): Local ONNX external_data or ExecuTorch .ptd sidecar directory under the allowed roots.
- `gate` (string): Return a policy-blocked status when an artifact_defect is present. Nothing is gated by default.
- `list_sections` (boolean): List selectable analysis sections instead of auditing.
- `max_download_gib` (integer): Upper bound for one remote download in GiB.
- `offline` (boolean): Refuse network access and require a verified cache receipt.
- `output_format` (string): summary is the bounded human-readable default. Request envelope for the canonical cross-format contract, json/json-compact for format-specific evidence, CycloneDX 1.7, or SARIF explicitly.
- `path` (string, required): Local artifact/package path under DEEPBOM_MCP_ALLOWED_ROOTS, or an immutable hf://, gs://, or hash-pinned HTTPS source.
- `pointer` (string): Emit one RFC 6901 JSON Pointer result, such as /operator_count.
- `policy` (string): Built-in gate profile. Engineering blocks artifact defects; regulatory also requires evidence gaps to be resolved but does not determine legal compliance.
- `scan` (string): Bounded scan policy. structure avoids payload integrity work; integrity streams supported payload checks; full requests all supported static analysis.
- `section` (string): Emit only these analysis sections, comma-separated. Use list_sections first. model_summary returns deepbom.model_summary.v1. Applies to json formats.
- `target` (string): TFLite target profile id for cost-model binding; it is not host detection.
- `tensor_limit` (integer): Maximum tensor rows to return; requires tensors=true. The result includes next_offset when more rows exist.
- `tensor_offset` (integer): Zero-based tensor row offset for a bounded tensor page; requires tensors=true.
- `tensors` (boolean): For a GGUF artifact, return the bounded structure-only deepbom.tensor_table.v1 projection instead of the full tensor/numerical ledgers.

### `deepbom_diff` (~238 tokens)

Compare two model artifacts

Compare two artifacts of the same supported format and return deepbom.semantic_artifact_diff.v1. TFLite results also retain the target-bound deployment delta. The comparison does not prove lineage, runtime behaviour, task quality, or regulatory significance.

Input parameters:

- `baseline` (string, required): Local or immutable remote baseline artifact or package.
- `cache_dir` (string): Content-addressed cache directory under the allowed roots.
- `candidate` (string, required): Local or immutable remote candidate artifact or package of the same format.
- `expected_sha256` (string): Expected digest for the baseline source. Use independently pinned remote URLs for both artifacts when possible.
- `max_download_gib` (integer)
- `offline` (boolean): Refuse network access and require verified cache receipts.
- `target` (string): Optional TFLite target profile id for the embedded pinned cost model.
- `tensor_limit` (integer): Maximum changed-tensor rows to return; requires tensors=true.
- `tensor_offset` (integer): Zero-based changed-tensor row offset; requires tensors=true.
- `tensors` (boolean): Return the tensor-encoding transition projection instead of the full semantic diff.

Output parameters:

- `schema`

### `deepbom_explain_rule` (~74 tokens)

Explain a DEEPBOM rule

Return the machine-readable meaning, evidence boundary, source binding, and verification status of one DEEPBOM rule or analysis term. Use deepbom_capabilities or the CLI rule index to discover identifiers instead of guessing their meaning.

Input parameters:

- `rule` (string, required): Rule or analysis-term identifier accepted by deepbom explain-rule.

Output parameters:

- `schema`

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/junhwan-kwon-deepbom/deepbom#diagnostics

## Score history

- 2026-09-21: 86
- 2026-09-20: 85
- 2026-09-19: 85
- 2026-09-18: 84
- 2026-09-17: 73
- 2026-09-16: 57
- 2026-09-15: 83
- 2026-09-14: 68
- 2026-09-13: 56
- 2026-09-12: 81
- 2026-09-11: 66
- 2026-09-10: 66
- 2026-09-09: 80
- 2026-09-08: 65

## Common questions

### What is the DEEPBOM MCP server?

DEEPBOM is an MCP server listed in the public MCP registry as io.github.JunHwan-Kwon/deepbom. Browser-local and CLI static evidence for deployed AI model artifacts. This page covers its npm package (deepbom).

### Is the DEEPBOM MCP server safe to use?

DEEPBOM scores 86 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 21 September 2026. It declares no install or post-install scripts. 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 DEEPBOM MCP server expose?

DEEPBOM exposes 4 tools: deepbom_capabilities, deepbom_audit, deepbom_diff, deepbom_explain_rule. Their descriptions and schemas cost roughly 939 tokens of context every time the server is loaded.

### Is the DEEPBOM MCP server still maintained?

DEEPBOM is still listed as active in the MCP registry. We last reached this channel on 21 September 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 DEEPBOM MCP server under?

DEEPBOM 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

- npm package: https://www.npmjs.com/package/deepbom
- Socket report: https://socket.dev/npm/package/deepbom
- Repository: https://github.com/JunHwan-Kwon/deepbom
- Website: https://deepbom.org/
- Changelog RSS feed: https://verifymcp.io/servers/junhwan-kwon-deepbom/deepbom.xml
- Changelog JSON feed: https://verifymcp.io/servers/junhwan-kwon-deepbom/deepbom.json
- HTML version of this page: https://verifymcp.io/servers/junhwan-kwon-deepbom/deepbom