Local static analysis and evidence generation for deployed AI model artifacts
Local static analysis and evidence generation for deployed AI model artifacts
active Production-safe Score 95/100 http no auth
At a glance
| Endpoint | https://deepbom.org/mcp |
|---|---|
| Source | https://github.com/JunHwan-Kwon/deepbom |
| Transport | http |
| Tools | 7 |
| Auth | none |
| First seen | 2026-09-14 00:28:22 |
| Last checked | 2026-11-17 21:53:09 |
Observed reliability
| 7-day uptime | 100% |
|---|---|
| 24-hour uptime | 100% |
| Handshake success | 100% |
| Latency p50 / p95 | 305 / 578 ms |
| Last successful check | 2026-11-17 21:53:09 |
Measured by Arclan's validator via repeated live MCP handshakes. How this is computed →
Tools (7)
deepbom_analyze_file— Use when the user asks to inspect, summarize, or visualize an attached TFLite, ONNX, GGUF, SafeTensors, Core ML, or ExecuTorch deployment ardeepbom_capabilities— Use before analysis when format support, privacy boundaries, or the difference between the ChatGPT and local DEEPBOM paths is unclear. Returdeepbom_publish_analysis— Receives one bounded browser-produced DEEPBOM result, validates its structure, and returns it to the conversation. This tool accepts analysideepbom_publish_error— Receives one bounded browser-produced DEEPBOM error and returns a recovery action to the conversation. This tool accepts diagnostic text, nedeepbom_query_file— Use for follow-up questions about an already identified attachment: inspect a layer by subject_ref, search or page through all operations, ideepbom_publish_query— Component-only: validates and returns a bounded Evidence IR query projection for the same attachment. No model bytes, state persistence, ordeepbom_workflow_guide— Use to discover how to answer a model-analysis question across ChatGPT, the interactive deepbom.org workspace and the local CLI. Returns rea
Validation history
| Checked | Reachable | Handshake | Latency | Score | State |
|---|---|---|---|---|---|
| 2026-11-17 21:53:09 | ✓ | ✓ | 365 ms | 91 | active |
| 2026-11-17 21:38:03 | ✓ | ✓ | 423 ms | 91 | active |
| 2026-11-17 21:22:38 | ✓ | ✓ | 367 ms | 91 | active |
| 2026-11-17 21:07:25 | ✓ | ✓ | 189 ms | 94 | active |
| 2026-11-17 20:52:21 | ✓ | ✓ | 499 ms | 91 | active |
| 2026-11-17 20:37:21 | ✓ | ✓ | 182 ms | 94 | active |
| 2026-11-17 20:22:15 | ✓ | ✓ | 201 ms | 94 | active |
| 2026-11-17 20:07:10 | ✓ | ✓ | 415 ms | 91 | active |
| 2026-11-17 19:51:25 | ✓ | ✓ | 331 ms | 91 | active |
| 2026-11-17 19:36:18 | ✓ | ✓ | 599 ms | 91 | active |
| 2026-11-17 19:21:05 | ✓ | ✓ | 377 ms | 91 | active |
| 2026-11-17 19:05:52 | ✓ | ✓ | 335 ms | 91 | active |
| 2026-11-17 18:50:39 | ✓ | ✓ | 346 ms | 91 | active |
| 2026-11-17 18:35:29 | ✓ | ✓ | 540 ms | 91 | active |
| 2026-11-17 18:20:27 | ✓ | ✓ | 427 ms | 91 | active |
Query this programmatically
Agents can pull this record live over the MCP protocol or REST:
get_server("https://deepbom.org/mcp") # via the Arclan MCP endpoint https://arclan.ai/mcp
GET https://arclan.ai/api/registry/deepbom-org-mcp # JSON