Skip to content
Agentmart
Submit a tool

DEEPBOM

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

Connector by JunHwan-Kwon · GitHub account verified by the MCP Registry

IndexedApache-2.0Local (stdio)Remote (HTTP)★ 2
Write a review

Install

Works with Claude Code, VS Code, Codex, Cursor, Windsurf, Claude Desktop. Read the repository before you give any tool access to your data.

npx agentmarket install connector/junhwan-kwon-deepbom

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Remote endpoint

  • https://deepbom.org/mcp Remote (HTTP)

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

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

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this server can do and what it asks for, from its tool list, install config and code. Checked Oct 25, 2026.

Runs code on install

Its package runs an install script (such as npm postinstall or setup.py code) as soon as you install it, before any tool is called. Read the script first.

Tools
7 read · 0 write · 0 deleteRead-only
Secrets
None asked for
Install scripts
Runs code on install
Runs as
Node.js package

Tools by what they do 7

From the running server's own tool list (tools/list) on Oct 25, 2026.

Read 7 · Look things up without changing anything.

  • deepbom_analyze_file
  • deepbom_capabilities
  • deepbom_publish_analysis
  • deepbom_publish_error
  • deepbom_publish_query
  • deepbom_query_file
  • deepbom_workflow_guide

Network hosts it talks to 38

  • agent-plugins.org · found in code
  • ai.google.dev · found in code
  • blog.tensorflow.org · found in code
  • cyclonedx.org · found in code
  • deepbom-org.web-sandbox.oaiusercontent.com · found in code
  • deepbom.org · found in remote endpoint, install command, code
  • deepbom.test · found in code
  • developer.apple.com · found in code
  • developer.arm.com · found in code
  • developers.google.com · found in code
  • developers.googleblog.com · found in code
  • developers.openai.com · found in code
  • docs.amd.com · found in code
  • docs.nvidia.com · found in code
  • docs.oasis-open.org · found in code
  • doi.org · found in code
  • eur-lex.europa.eu · found in code
  • example.invalid · found in code
  • example.test · found in code
  • fda.gov · found in code
  • files.oaiusercontent.com · found in code
  • github.com · found in code
  • hanlab18.mit.edu · found in code
  • huggingface.co · found in code
  • imdrf.org · found in code
  • in-toto.io · found in code
  • ml-assets.apple.com · found in code
  • onnx.ai · found in code
  • opencompute.org · found in code
  • orcid.org · found in code
Show 8 more hosts
  • raspberrypi.com · found in code
  • raw.githubusercontent.com · found in code
  • s3.amazonaws.com · found in code
  • sitemaps.org · found in code
  • slsa.dev · found in code
  • storage.googleapis.com · found in code
  • tampered.invalid · found in code
  • tensorflow.org · found in code

Files it touches

  • /etc/passwd
  • /proc/cmdline
  • /root/.cache/huggingface/hub/models--nicholasKluge--TeenyTinyLlama-460m/snapshots/3df46126c488f2385f88ecaa26d667da130da8d5
  • /sys/devices/system/cpu/online
  • /sys/fs/cgroup
  • /tmp/not-selected-by-deepbom.h5
  • Your home directory (~)
  • Any path the agent passes to its tools

Tools (7)

As the server listed them on Oct 25, 2026. Descriptions are the server’s own words; hidden characters are shown as [U+…].

  • deepbom_analyze_fileAnalyze an AI model artifactread-only

    Use when the user asks to inspect, summarize, or visualize an attached TFLite, ONNX, GGUF, SafeTensors, Core ML, or ExecuTorch deployment artifact. Opens a browser-local analyzer, returns a hash-bound format-neutral Model IR table and static evidence summary, and provides deterministic document views without executing model code. Do not use for training checkpoints, measured latency, task accuracy, clinical validity, regulatory compliance, or actual runtime placement.

  • deepbom_capabilitiesCheck DEEPBOM capabilitiesread-only

    Use before analysis when format support, privacy boundaries, or the difference between the ChatGPT and local DEEPBOM paths is unclear. Returns capability metadata only and does not inspect a file.

  • deepbom_publish_analysisReturn a DEEPBOM analysis to chatread-only

    Receives one bounded browser-produced DEEPBOM result, validates its structure, and returns it to the conversation. This tool accepts analysis results, never model bytes.

  • deepbom_publish_errorReturn a DEEPBOM analysis error to chatread-only

    Receives one bounded browser-produced DEEPBOM error and returns a recovery action to the conversation. This tool accepts diagnostic text, never model bytes.

  • deepbom_publish_queryReturn requested model evidence to chatread-only

    Component-only: validates and returns a bounded Evidence IR query projection for the same attachment. No model bytes, state persistence, or runtime execution. Result digests establish consistency, not independent server attestation.

  • deepbom_query_fileInspect specific model evidenceread-only

    Use for follow-up questions about an already identified attachment: inspect a layer by subject_ref, search or page through all operations, inspect findings, rank improvement investigations, inspect encoded activation fusion, compare source-pinned static delegate eligibility, or explicitly analyze weight distributions, channels, similarity, singular spectra, sparsity and quantization with section=weights and optional weight_view. Weight analysis reads payloads on demand with explicit decoder/budget coverage (128 MiB widget limit). Reuse the ChatGPT-authorized file and the exact SHA-256 from its…

  • deepbom_workflow_guideChoose a DEEPBOM analysis workflowread-only

    Use to discover how to answer a model-analysis question across ChatGPT, the interactive deepbom.org workspace and the local CLI. Returns real query sections, visualization/export actions, explicit web continuation links, required inputs, CLI argument templates and evidence limits for weights, pruning investigation, comparison, BOM verification, metadata/OMOP, activation evidence, runtime, batch/CI and integrations. No attachment is required. This is guidance, not a completed analysis or local command execution. Prefer answering from existing evidence; inspect supported follow-ups with deepbom_…

Signals

Stars
2
Forks
0
Open issues
1
Last commit
Oct 23, 2026 (6 days ago)
Last release
Oct 20, 2026 (8 days ago)

From GitHub (fetched Oct 24, 2026).

Details

Registry name
io.github.JunHwan-Kwon/deepbom
Version
2.5.0
Auth
Auth not stated
Packages
npm deepbom
License
Apache-2.0
Repository
github.com/JunHwan-Kwon/deepbom
Website
deepbom.org
First seen
Oct 24, 2026
Last checked
Oct 24, 2026
Source
Official MCP Registrygithub-graphql
Cite this page

DEEPBOM MCP server. Agent Mart. https://agentmart.dev/connectors/junhwan-kwon-deepbom (last updated 2026-10-24)