MCP server

DEEPBOM

io.github.JunHwan-Kwon/deepbom

Checked 26 Oct 2026, 08:29 UTC · Connected to it and listed its tools

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

Website Source

At a glance

Type

MCP server

Publisher

Not verified

Status

Working at last check

Tools

7

Token cost

About 4,693 tokens per request

Sets up in

Claude Code, Claude Desktop, Codex, Gemini CLI, Cursor, VS Code, Antigravity, ChatGPT, OpenAI API, Grok

Last checked

26 Oct 2026, 08:29 UTC

Connect it to your agent

Add to CursorAdd to VS CodeVS Code Insiders

Opens the app, which shows the server and asks you to confirm. For other apps, copy the setup below.

Claude Code

claude mcp add --transport http deepbom https://deepbom.org/mcp

Claude Desktop

Settings → Connectors → Add custom connector, and paste the URL.

Codex (config.toml)

[mcp_servers.deepbom]
url = "https://deepbom.org/mcp"

Gemini CLI

{"mcpServers":{"deepbom":{"httpUrl":"https://deepbom.org/mcp"}}}

Cursor

{"mcpServers":{"deepbom":{"url":"https://deepbom.org/mcp"}}}

VS Code

{"servers":{"deepbom":{"type":"http","url":"https://deepbom.org/mcp"}}}

Antigravity

agy mcp add deepbom https://deepbom.org/mcp

ChatGPT

Settings → Apps & Connectors → Advanced settings: turn on Developer mode, then Create a connector and paste the URL. Which plans can do this varies.

OpenAI API (Responses tools)

{"type":"mcp","server_label":"deepbom","server_url":"https://deepbom.org/mcp","require_approval":"always"}

Grok (xAI API tools)

{"type":"mcp","server_label":"deepbom","server_url":"https://deepbom.org/mcp"}

Tools

• deepbom_analyze_file ~334 tokens
  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 ~92 tokens
  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 Sends messages · ~1611 tokens
  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 Sends messages · ~255 tokens
  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_query Sends messages · ~1081 tokens
  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_file ~943 tokens
  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_workflow_guide ~377 tokens
  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

Browse

• GitHub tools
• Hiring and jobs
• GitHub and code hosting

Related MCP servers

• AIfra — temporary static previews
  48-hour HTTPS previews of prebuilt static sites and HTML slides. No server builds or backends.
• Novence
  Hosted MCP for creating, checking, deploying, and hosting static sites for AI agents.
• CourseProfiler
  Race course profiling, catalog search, course submission, and personalized race plans.
• aft.page
  Deploy a folder, build output, or public GitHub repo to a live URL. Update, roll back.
• Pact0
  Agents hire other agents for part of a task and get it back, or do trials and paid escrow jobs.
• RQM Studio Jobs
  Delegate 20 fail-closed RQM Studio quantum work products with fixed-request x402.
• Api Governance
  Signed, offline-verifiable contract-change authorization. Only a granted change can proceed.
• Hesper Atlas Evidence
  Verify stock signals, replay evidence, provenance, freshness, and caveats.

Badge for your README

[![AptLynx](https://aptlynx.net/badge/io.github.JunHwan-Kwon/deepbom.svg)](https://aptlynx.net/servers/io.github.JunHwan-Kwon/deepbom)

Listing text is written by the maker; AptLynx lists tools and does not vouch for them. Find another tool · Browse by topic · For agents