DEEPBOM MCP server
io.github.JunHwan-Kwon/deepbomJunHwan-Kwonstreamable-httpv2.5.0Scanned
Browser-local and CLI static evidence for deployed AI model artifacts.
7 tools: 3 do something that can't be undone, 2 change things and 2 only read.
- Reads private data · 2
- Reads text others write · 0
- Can send data out · 3
- 3 findings
Tools listed without sign-in. Remote posture
With Anlyon
3 tools here do something that can't be undone. Govern them.
- Anlyon lists the tools and adopts none.
- Each tool you adopt gets approvals and receipts.
- Your agent never holds the key.
A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.
What the DEEPBOM MCP server can do
The DEEPBOM MCP server is published by the GitHub account JunHwan-Kwon. It has 7 tools. It can do things that cannot be undone, such as sending, paying or publishing (deepbom_publish_analysis, deepbom_publish_error and deepbom_publish_query) and create or change data (2 tools: deepbom_capabilities and deepbom_workflow_guide), but cannot delete data. 2 tools only read.
2 tools read private data (deepbom_analyze_file and deepbom_query_file); 3 tools can send data out of your system (deepbom_publish_analysis, deepbom_publish_error and deepbom_publish_query).
The fixed checks matched 3 findings (annotation-conflict). Each one comes with the text it matched.
Its remote endpoint lists its tools without sign-in.
Last scanned Nov 15, 2026, version 2.5.0.
Tools
Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.
7 tools
Can't be undone 3Claude Code: ask
deepbom_publish_analysisReceives one bounded browser-produced DEEPBOM result, validates its structure, and returns it to the conversation.Can send data out1 finding
Why it is in this group
- The name "deepbom_publish_analysis" says "publish": a word for a change that another call does not undo.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- outboundThe name "deepbom_publish_analysis" says "publish": it sends or publishes something to other people.
Findings
- Warn
The server marks "deepbom_publish_analysis" read-only (readOnlyHint: true), and its own name, description or input give the class "irreversible".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "deepbom_publish_analysis" says "publish": a word for a change that another call does not undo.
Description, as the server wrote it Receives one bounded browser-produced DEEPBOM result, validates its structure, and returns it to the conversation. This tool accepts analysis results, never model bytes.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
- idempotentHint: true
deepbom_publish_errorReceives one bounded browser-produced DEEPBOM error and returns a recovery action to the conversation.Can send data out1 finding
Why it is in this group
- The name "deepbom_publish_error" says "publish": a word for a change that another call does not undo.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- outboundThe name "deepbom_publish_error" says "publish": it sends or publishes something to other people.
Findings
- Warn
The server marks "deepbom_publish_error" read-only (readOnlyHint: true), and its own name, description or input give the class "irreversible".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "deepbom_publish_error" says "publish": a word for a change that another call does not undo.
Description, as the server wrote it Receives one bounded browser-produced DEEPBOM error and returns a recovery action to the conversation. This tool accepts diagnostic text, never model bytes.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
- idempotentHint: true
deepbom_publish_queryComponent-only: validates and returns a bounded Evidence IR query projection for the same attachment.Can send data out1 finding
Why it is in this group
- The name "deepbom_publish_query" says "publish": a word for a change that another call does not undo.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- outboundThe name "deepbom_publish_query" says "publish": it sends or publishes something to other people.
Findings
- Warn
The server marks "deepbom_publish_query" read-only (readOnlyHint: true), and its own name, description or input give the class "irreversible".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "deepbom_publish_query" says "publish": a word for a change that another call does not undo.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
- idempotentHint: true
Changes things 2Claude Code: ask
deepbom_capabilitiesUse before analysis when format support, privacy boundaries, or the difference between the ChatGPT and local DEEPBOM paths is unclear.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
- idempotentHint: true
deepbom_workflow_guideUse to discover how to answer a model-analysis question across ChatGPT, the interactive deepbom.org workspace and the local CLI.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it 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_query_file before offering web continuation for richer interaction. Website links transfer only a workflow ID, never model data.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
- idempotentHint: true
Only reads 2Show 2 read-only tools
deepbom_analyze_fileUse when the user asks to inspect, summarize, or visualize an attached TFLite, ONNX, GGUF, SafeTensors, Core ML, or ExecuTorch deployment artifact.Reads private dataNo findings
Why it is in this group
- The name "deepbom_analyze_file" says "analyze": a word for reading.
What it can reach
- private-dataThe name "deepbom_analyze_file" says "analyze" and "file": it reads files.
- private-dataThe input names a file (input.file), and the tool reads: it reads files.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
- idempotentHint: true
deepbom_query_fileUse 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 invest…Reads private dataNo findings
Why it is in this group
- The name "deepbom_query_file" says "query": a word for reading.
What it can reach
- private-dataThe name "deepbom_query_file" says "query" and "file": it reads files.
- private-dataThe input names a file (input.file), and the tool reads: it reads files.
Description, as the server wrote it 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 previous DEEPBOM result. section=profiles lists available backend profiles; query.target selects only a TFLite CPU planning profile from capabilities. The browser computes the query from the shared Evidence IR and returns a bounded result; model bytes are not sent to DEEPBOM. Static candidate eligibility is not observed placement, speed, accuracy, or runtime fusion. Do not invent findings while browser_query_started is pending.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
- idempotentHint: true
This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.
Exfil surface
Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.
No private-data, untrusted-input, outbound path in this server alone: no tool is tagged untrusted-input.
- Reads private data2
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write0
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out3
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.
Remote posture
What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.
Looked at Nov 20, 2026, 18:58 UTC, unchanged since Oct 22, 2026. No credentials were sent and no tool was called. What is looked at.
- Reachable
- yes
- HTTP status of an anonymous initialize
- 200
- tools/list served without credentials
- yes
- Tools that change things, listed without credentials
- 5
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- not observed
- Authorization servers
- not observed
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- not observed
- Client ID metadata documents
- not observed
- HighThe whole server
The endpoint served tools/list without credentials, and the list has 5 tools that change things (3 irreversible, 2 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://deepbom.org/mcp: tools/list returned 7 tools to an anonymous client, including deepbom_publish_analysis (irreversible), deepbom_publish_error (irreversible), deepbom_publish_query (irreversible), deepbom_capabilities (write), deepbom_workflow_guide (write)
Findings
Matches of fixed checks, with the text they matched.
The server marks "deepbom_publish_analysis" read-only (readOnlyHint: true), and its own name, description or input give the class "irreversible".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "deepbom_publish_analysis" says "publish": a word for a change that another call does not undo.
The server marks "deepbom_publish_error" read-only (readOnlyHint: true), and its own name, description or input give the class "irreversible".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "deepbom_publish_error" says "publish": a word for a change that another call does not undo.
The server marks "deepbom_publish_query" read-only (readOnlyHint: true), and its own name, description or input give the class "irreversible".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "deepbom_publish_query" says "publish": a word for a change that another call does not undo.
History
Changes to its tool definitions and to its remote endpoint, newest first.
No change seen yet. Its tools are rescanned every day, and a remote endpoint is looked at once a week.
Install
Pinned to version 2.5.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http deepbom https://deepbom.org/mcpclaude mcp add --transport http deepbom https://deepbom.org/mcpRun in a terminal.
Claude Code permissions
Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.
{
"permissions": {
"allow": [
"mcp__deepbom__deepbom_analyze_file",
"mcp__deepbom__deepbom_query_file"
],
"ask": [
"mcp__deepbom__deepbom_capabilities",
"mcp__deepbom__deepbom_publish_analysis",
"mcp__deepbom__deepbom_publish_error",
"mcp__deepbom__deepbom_publish_query",
"mcp__deepbom__deepbom_workflow_guide"
],
"deny": []
}
}Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as deepbom. Review it before you use it.
Capability tags behind 5 rules
- mcp__deepbom__deepbom_analyze_file private-data
- mcp__deepbom__deepbom_publish_analysis outbound
- mcp__deepbom__deepbom_publish_error outbound
- mcp__deepbom__deepbom_query_file private-data
- mcp__deepbom__deepbom_publish_query outbound
Pin
Keep the decision: fail CI when the tools change, follow every change, or show a badge.
Pin in CI
Fail a build when the tools you reviewed are not the tools the server serves today.
curl -s "https://radar.anlyon.com/api/v1/servers/io.github.JunHwan-Kwon/deepbom/verify?hash=93f590501451cbb7540d485ad58afb4935cac35102b60dfcea403a3cdcab2842" | jq -e '.changed == false'Pinned hash 93f590501451, from Nov 15, 2026, 23:17 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/io.github.JunHwan-Kwon/deepbom/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/io.github.JunHwan-Kwon/deepbom)Source: MCP Registry · repository. Synced Oct 21, 2026, 18:17 UTC.
DEEPBOM MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the DEEPBOM MCP server safe?
- No scan can promise that. What its definitions show: 7 tools, 5 of which can change, send or delete something, and 3 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the DEEPBOM MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the DEEPBOM MCP server do things that cannot be undone?
- Yes. 3 tools can send, pay, publish or merge: deepbom_publish_analysis, deepbom_publish_error and deepbom_publish_query.
What tools does the DEEPBOM MCP server have?
- 7 tools: 3 irreversible, 2 write, 2 read. deepbom_publish_analysis, deepbom_publish_error, deepbom_publish_query, deepbom_capabilities, deepbom_workflow_guide, deepbom_analyze_file and deepbom_query_file.
Does the DEEPBOM MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the DEEPBOM MCP server send data to outside services?
- 3 tools can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): deepbom_publish_analysis, deepbom_publish_error and deepbom_publish_query.
Has the DEEPBOM MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 15, 2026.