DEEPBOM

Last 30 days

Uptime

100%

Response time

216 ms typical, 216 ms slowest 5%

Last check

7 h ago

Next check

any minute now

How to call it

Add it to any MCP client that supports remote servers.

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

7 tools

• 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 determi

• 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 e

• 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

Security scan

• No findings. We scan names, descriptions and tool definitions for hidden instructions and other prompt-injection patterns.

Recent checks