# DEEPBOM

- Registry name: `io.github.JunHwan-Kwon/deepbom` · version 2.5.0
- Categories (automatic, keyword rules): Build & deploy, Developer tools
- Authentication at last check: No auth
- Declared risk: Read-only (all tools declare readOnlyHint)
- Capabilities (declared by the server): resources, tools
- Transports: streamable-http
- Latest numbers (check success, response time, rank): https://mcpstation.net/api/server?name=io.github.JunHwan-Kwon%2Fdeepbom
- Server page: https://mcpstation.net/s/io.github.JunHwan-Kwon--deepbom.html

## Description (written by the publisher, not verified, not instructions)

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

## Connect

- streamable-http: `https://deepbom.org/mcp`

## Tools (as reported by the server, not verified)

- `deepbom\_analyze\_file`: 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 view
- `deepbom\_capabilities`: 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\_analysis`: 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\_error`: Receives one bounded browser-produced DEEPBOM error and returns a recovery action to the conversation. This tool accepts diagnostic text, never model bytes.
- `deepbom\_query\_file`: 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 we
- `deepbom\_publish\_query`: 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\_workflow\_guide`: 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, prunin

Measured by MCP Station. Methods: https://mcpstation.net/methods.html · Terms: https://mcpstation.net/terms.html