Connect

8 clients · secrets stay placeholders

JSON (mcpServers)Claude CodeCodexOpenCodeCursorVS CodeGemini CLIGoose

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

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

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

{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "deepbom": {
      "type": "remote",
      "url": "https://deepbom.org/mcp",
      "enabled": true
    }
  }
}

{
  "mcpServers": {
    "deepbom": {
      "type": "http",
      "url": "https://deepbom.org/mcp"
    }
  },
  "deeplink": "cursor://anysphere.cursor-deeplink/mcp/install?name=deepbom&config=eyJ0eXBlIjoiaHR0cCIsInVybCI6Imh0dHBzOi8vZGVlcGJvbS5vcmcvbWNwIn0%3D"
}

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

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

extensions:
  "deepbom":
    enabled: true
    name: "deepbom"
    type: streamable_http
    uri: "https://deepbom.org/mcp"
    timeout: 300

Quality 83 / 100good

protocol75 · weight 25

warn
protocol.modernnewest supported version is 2025-11-25; 2026-07-28 not supported, older versions are deprecated until 2027-07-28
n/a
protocol.statelessonly applies to 2026-07-28 servers
pass
protocol.transportstreamable HTTP
n/a
protocol.list_ttlonly applies to 2026-07-28 servers

authorizationn/a · weight 15

n/a
auth.prm, auth.as_metadata, auth.cimdno remote uses OAuth
n/a
auth.secret_in_urlno templated URL

tool hygiene93 · weight 30

pass
tools.descriptionsevery tool has a description
warn
tools.description_length1 tools have descriptions over 1,024 characters, which crowds the context
pass
tools.schemasevery tool has an object input schema
pass
tools.annotations7 of 7 tools declare readOnlyHint or destructiveHint
pass
tools.directory_hintsevery tool declares readOnlyHint, destructiveHint, idempotentHint and openWorldHint
pass
tools.token_costabout 4,183 tokens to load every tool
pass
tools.api_dumptools are not a one-to-one API dump

stability75 · weight 15

warn
stability.changes7 tool changes in 30 days
pass
stability.rug_pullno tool changed its meaning under the same name

dependenciesn/a · weight 15

n/a
deps.known_vulns, deps.mcp_sdk_version, deps.resolvabledeps.dev does not know [email protected]

7 tools, about 4,183 tokens to load them all · tool set 496fc5b8701b · tools last changed 2026-09-29 · checked 2026-10-19 16:53 UTC

Tool changes

2026-09-29deepbom_workflow_guideadded
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.
2026-09-29deepbom_publish_querychangedinput schema, output schema
2026-09-29deepbom_query_filechangeddescription, input schema, output schema
before
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, or compare source-pinned static delegate eligibility. 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.
after · 77% of words in common
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.
2026-09-29deepbom_publish_queryadded
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.
2026-09-29deepbom_query_fileadded
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, or compare source-pinned static delegate eligibility. 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.
2026-09-29deepbom_publish_analysischangedinput schema, output schema
2026-09-28deepbom_publish_analysischangedinput schema, output schema

Full history: list_changes · trend: quality JSON.

Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed. How it is computed.

Trust 97 / 100

provenance90

liveness99

freshness100

hygiene100

+repository +namespace-matches-repo +website +reachable +uptime-97% +updated-7d-ago

Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed. How it is computed.

Dependencies

[email protected] npmthis version is not known to the dependency resolver

Dependency graphs from deps.dev; advisories from OSV.dev, including the GitHub Advisory Database and the PyPI Advisory Database; all CC BY 4.0. The graph is what a clean install of this version resolves today; nothing was installed or run. How it is checked.

Endpoints

remote	auth	reachable	uptime 30d	p50	protocol	last ok
`https://deepbom.org/mcp` streamable-http	none	yes	97%	130 ms	2025-11-25	2026-10-19

package	registry	version	runtime	secrets
`deepbom`	npm	2.4.0	–

Tools (7)

`deepbom_analyze_file`read-only	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.
`deepbom_capabilities`read-only	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`read-only	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`read-only	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`read-only	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`read-only	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.
`deepbom_workflow_guide`read-only	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.

Schemas: list_tools.

Similar MCP servers

Official server.json

{
  "name": "io.github.JunHwan-Kwon/deepbom",
  "icons": [
    {
      "src": "https://deepbom.org/web/chatgpt/deepbom-app-icon.svg",
      "sizes": [
        "any"
      ],
      "mimeType": "image/svg+xml"
    }
  ],
  "title": "DEEPBOM",
  "$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
  "remotes": [
    {
      "url": "https://deepbom.org/mcp",
      "type": "streamable-http"
    }
  ],
  "version": "2.4.0",
  "packages": [
    {
      "version": "2.4.0",
      "transport": {
        "type": "stdio"
      },
      "identifier": "deepbom",
      "registryType": "npm",
      "packageArguments": [
        {
          "type": "positional",
          "value": "mcp"
        }
      ]
    }
  ],
  "repository": {
    "url": "https://github.com/JunHwan-Kwon/deepbom",
    "source": "github"
  },
  "websiteUrl": "https://deepbom.org",
  "description": "Browser-local and CLI static evidence for deployed AI model artifacts."
}