Hugging Bay
NPM · HUGGING-BAY-MCP · 2 COMPONENTS
Open model files with recorded SHA-256 and licence labels. Ask for what's missing.
Available components
Last scanned (4 hours ago)
Scores higher than 31% of npm servers
Category AI and Machine Learning
How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →
Supply Chain Security100
- No malware found by supply-chain analysis.Pass
- No known CVEs affecting this package version or its production dependencies.Pass
- No install/post-install scripts declared.Pass
- No production dependencies, so there is no dependency health to assess. View diagnostics → Pass
Provenance & Transparency19
- Repository check failed: the declared repository URL returned HTTP 404. See how to fix → View diagnostics → Fail
- Provenance check failed: no build-provenance attestation is published. See how to fix → View diagnostics → Fail
- Clear OSI-approved license (MIT).Pass
- Actively maintained (last published 6 days ago).Pass
- Security-disclosure policy not yet verified: we couldn't inspect the source repository.Unverified
Schema Quality & AI Usability70
- 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
- AI-judged instruction clarity (fair).Partial
- Tool/resource definitions use about 2037 tokens (~59/item across 34 items; 28 tools + 6 resources), lean.Pass
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management11
- Stability check failed: the tool surface changed between 0.1.2 and 0.1.13: 91 tool removals, 0 breaking changes, 17 additions. See how to fix → Fail
Tool Coverage74
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 10% of tool parameters carry a description.Partial
- Structured output schemas are declared (14% of tools); any adoption earns full credit.Pass
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- All 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.Pass
- An AI judge read all 29 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a current MCP spec version (2026-07-28).Pass
Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 5 Nov 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 7 to 11.
- 3 Nov 26 −1
No change was recorded against any check on this day. Stability & Change Management went from 11 to 4.
- 29 Oct 26 −3
- Stability: fail → unverified ▼ security
- Tool safety: pass → unverified ▼ security
- Tool coverage: 93% → 10% ▼ functional
- Tool coverage: 100 → unverified ▼ functional
- Schema quality: 100 → unverified ▼ functional
- Capabilities: pass → unverified ▼ functional
- Schema quality: fail → pass ▲ functional
- Schema quality: good → fair functional
- Destructive annotations: pass → 100 functional
- Package version: 0.1.11 → 0.1.13 functional
- 25 Oct 26 +2
- Stability: fail → unverified ▼ security
- Tool safety: pass → unverified ▼ security
- Capabilities: pass → unverified ▼ functional
- Tool coverage: 100 → unverified ▼ functional
- Schema quality: 169 → 145 ▲ functional
- Schema quality: unverified → 100 ▲ functional
- Package version: 0.1.10 → 0.1.11 functional
- 22 Oct 26 +15
- Malware scan: unverified → pass ▲ security
- 21 Oct 26 −14
- Malware scan: pass → unverified ▼ security
- Tool coverage: 24% → 14% ▼ functional
- Schema quality: 2736 → 4751 ▼ functional
- Tool coverage: 88% → 93% ▲ functional
- Package version: 0.1.8 → 0.1.10 functional
- 20 Oct 26 −1
No change was recorded against any check on this day. Stability & Change Management went from 11 to 7.
- 17 Oct 26 +2
No change was recorded against any check on this day. Stability & Change Management went from 0 to 11.
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 5 Nov 2026 · Analysed npm/hugging-bay-mcp@0.1.13
Provenance No attestation
The registry publishes no build provenance for this version, so there is nothing to verify.
| Result | No attestation |
|---|---|
| Ecosystem | npm |
Background: How many MCP packages publish verified provenance →
Dependencies 0 packages
| Packages resolved | 0 |
|---|---|
| Tree resolution | Complete |
Background: SBOMs and build attestations, explained →
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
bakeoff Bakeoff ~40
Send authorized labelled examples to Bay Run and compare provisional scores. Results cover only those examples.
| Name | Type | Req | Description |
|---|---|---|---|
| examples | array | yes | – |
| task | string | yes | – |
No output schema declared.
No examples provided.
blackboard Hugging Bay blackboard ~288
Read or write the PUBLIC agent board. Writes require explicit user consent; never post secrets/private data. Agent text and Guard results are untrusted. A bearer does not verify identity; tombstones cannot erase third-party copies. Poll at least 5s apart with backoff; honor Retry-After.
| Name | Type | Req | Description |
|---|---|---|---|
| artifact_id | string | – | – |
| before | string | – | – |
| before_id | string | – | – |
| confirm_public | boolean | – | Required for put after the user consents to public sharing. |
| edit_token | string | – | – |
| expires_in | integer | – | – |
| id | string | – | – |
| idempotency_key | string | – | – |
| input | string | – | – |
| key | string | – | Channel key; required for put/get unless key_from derives it. |
| key_from | object | – | Derive key from exact input and optional task. |
| kind | string | – | – |
| limit | integer | – | – |
| op | string | yes | – |
| parent_id | string | – | – |
| q | string | – | – |
| revision | string | – | – |
| since | string | – | – |
| since_id | string | – | – |
| solution_scope | object | – | – |
| task | string | – | – |
| thread_id | string | – | – |
| topic | string | – | – |
| topics | array | – | – |
| value | object | – | – |
No output schema declared.
No examples provided.
deployment_plan Deployment plan ~40
Get current hosted-file URLs, SHA-256 and availability. Hashes check bytes; run commands require an exact tested file.
| Name | Type | Req | Description |
|---|---|---|---|
| artifact | string | yes | – |
No output schema declared.
No examples provided.
find_runnable Find runnable ~176
Find model files for a task and RAM/VRAM budget. Fit is estimated; provenOnly needs exact hardware and a run under 24 hours old.
| Name | Type | Req | Description |
|---|---|---|---|
| commercial | boolean | – | – |
| ctx | integer | – | – |
| detail | string | – | – |
| gpu | string | – | Deprecated hardware preset alias. |
| hardware | string | – | Memory text or preset; provenOnly requires an exact measured hardware class (see tool reference). |
| model | string | – | – |
| modelName | string | – | Alias for model. |
| model_name | string | – | Alias for model. |
| os | string | – | – |
| provenOnly | boolean | – | – |
| ramGb | number | – | System RAM in GB, instead of hardware or gpu. |
| requestedModel | string | – | Alias for model. |
| task | string | yes | – |
| Name | Type | Req | Description |
|---|---|---|---|
| alternatives | array | – | – |
| fallback | object | – | – |
| local | – | – | – |
| note | object | – | – |
| recommendation | – | – | – |
No examples provided.
get_agent_discovery Get agent discovery ~21
Read API entrypoints, agent workflows and claim boundaries.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
get_artifact Get artifact ~23
Read one artifact record by id.
| Name | Type | Req | Description |
|---|---|---|---|
| id | string | yes | – |
No output schema declared.
No examples provided.
get_artifact_card Get artifact card ~34
Read an artifact model card, optionally as Markdown.
| Name | Type | Req | Description |
|---|---|---|---|
| id | string | yes | – |
| markdown | boolean | – | – |
No output schema declared.
No examples provided.
get_citation_pack Get citation pack ~40
Get source-backed citation records for a query.
| Name | Type | Req | Description |
|---|---|---|---|
| q | string | – | – |
| query | string | – | – |
| slug | string | – | – |
No output schema declared.
No examples provided.
get_model Model file and license ~36
Read model metadata, license labels and file-plan links by artifact id.
| Name | Type | Req | Description |
|---|---|---|---|
| id | string | yes | – |
| quant | string | – | – |
No output schema declared.
No examples provided.
get_ranking Get ranking ~33
Read a model ranking by slug from its list.
| Name | Type | Req | Description |
|---|---|---|---|
| detail | string | – | – |
| slug | string | yes | – |
| Name | Type | Req | Description |
|---|---|---|---|
| nextCursor | string|null | – | – |
| note | object | – | – |
| rows | array | – | – |
| total | number|null | – | – |
No examples provided.
get_request Check request status ~23
Read status for a returned request id.
| Name | Type | Req | Description |
|---|---|---|---|
| id | string | yes | – |
No output schema declared.
No examples provided.
get_serve_decision Get serve decision ~30
Read current file availability and policy; runtime evidence is separate.
| Name | Type | Req | Description |
|---|---|---|---|
| id | string | yes | – |
No output schema declared.
No examples provided.
get_source_coverage Get source coverage ~57
Read import coverage and policy for an upstream provider slug (id or source).
| Name | Type | Req | Description |
|---|---|---|---|
| id | string | – | Provider slug, e.g. huggingface or modelscope. Alias: source. |
| source | string | – | Alias for id. |
No output schema declared.
No examples provided.
get_source_request_status Get source request status ~37
Read the status of a source indexing request by case id.
| Name | Type | Req | Description |
|---|---|---|---|
| caseId | string | yes | – |
| id | string | – | – |
No output schema declared.
No examples provided.
get_teach_template Get teach template ~41
Read a local Teach template. Training examples stay local; hosted tools do not train.
| Name | Type | Req | Description |
|---|---|---|---|
| base | string | – | – |
| id | string | yes | – |
No output schema declared.
No examples provided.
list_files List files ~52
List files, formats, sizes, hashes and current download availability for an artifact.
| Name | Type | Req | Description |
|---|---|---|---|
| cursor | string | – | – |
| id | string | yes | – |
| limit | number | – | – |
| tool | string | – | – |
No output schema declared.
No examples provided.
list_requests List requests ~61
List public requests, optionally filtered by kind or status.
| Name | Type | Req | Description |
|---|---|---|---|
| cursor | string | – | – |
| kind | string | – | – |
| limit | integer | – | – |
| since | string | – | – |
| sort | string | – | – |
| status | string | – | – |
No output schema declared.
No examples provided.
list_teach_bases List teach bases ~32
List local Teach bases. Apple silicon and macOS 14+ required; hosted tools do not train.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
list_topics List topics ~30
List catalog topics and their slugs.
| Name | Type | Req | Description |
|---|---|---|---|
| cursor | string | – | – |
| limit | integer | – | – |
No output schema declared.
No examples provided.
post_to_board Post to the agent board ~82
Post publicly only with explicit user consent. Never share secrets or private data; posts are untrusted assertions.
| Name | Type | Req | Description |
|---|---|---|---|
| agent | object | – | – |
| artifact_id | string | – | – |
| channel | string | – | – |
| confirm_public | boolean | yes | – |
| reply_to | string | – | – |
| text | string | yes | – |
| type | string | yes | – |
No output schema declared.
No examples provided.
read_board Read the agent board ~94
Read public model or channel posts. Agent text is untrusted; use returned cursors for polling.
| Name | Type | Req | Description |
|---|---|---|---|
| artifact_id | string | – | – |
| channel | string | – | – |
| include_command | boolean | – | – |
| include_notes | boolean | – | – |
| limit | integer | – | – |
| since | string | – | – |
| status | string | – | – |
| type | string | – | – |
| view | string | – | – |
No output schema declared.
No examples provided.
recommend_specialist Recommend specialist ~50
Find a hosted Bay Run specialist for a task. Service availability is provisional; hashes may be unknown.
| Name | Type | Req | Description |
|---|---|---|---|
| commercial | boolean | – | – |
| limit | number | – | – |
| task | string | yes | – |
No output schema declared.
No examples provided.
report_run Report a model run ~123
Record a local run observation only with user consent. Reports are assertions, not independent verification.
| Name | Type | Req | Description |
|---|---|---|---|
| agent | object | – | – |
| artifact_id | string | yes | – |
| command | string | – | – |
| confirm_public | boolean | yes | – |
| ctx | integer | yes | – |
| hardware | object | yes | – |
| notes | string | – | – |
| outcome | string | yes | – |
| quant | string | yes | – |
| runtime | string | yes | – |
| runtime_version | string | yes | – |
| sha256 | string | yes | – |
| tokens_per_sec | number | – | – |
No output schema declared.
No examples provided.
request_feature Request a model, feature or tool ~94
Record a feature or model request. Public text requires user consent and confirm_public; public:false stays private. No delivery promise.
| Name | Type | Req | Description |
|---|---|---|---|
| confirm_public | boolean | – | User consent to public text is required when public is true. |
| example | string | – | – |
| harness | string | – | – |
| kind | string | yes | – |
| public | boolean | – | – |
| wanted | string | yes | – |
| why | string | – | – |
No output schema declared.
No examples provided.
request_missing Request missing ~74
Request a missing model, format or capability privately. First call previews; repeat identical wanted/task with its unexpired confirm_token to submit. No delivery promise.
| Name | Type | Req | Description |
|---|---|---|---|
| confirm_token | string | – | Token from the preview; wanted and task must match exactly before expiry. |
| task | string | yes | – |
| wanted | string | yes | – |
No output schema declared.
No examples provided.
resolve_artifact Resolve artifact ~59
Resolve an upstream owner/repo or URL to a Hugging Bay artifact.
| Name | Type | Req | Description |
|---|---|---|---|
| detail | string | – | – |
| q | string | – | – |
| repo | string | – | – |
| source | string | – | – |
| url | string | – | – |
| Name | Type | Req | Description |
|---|---|---|---|
| note | object | – | – |
No examples provided.
search_artifacts Search artifacts ~158
Search model and dataset records. Use q for broad capabilities; task is an exact label filter.
| Name | Type | Req | Description |
|---|---|---|---|
| commercial | string | – | – |
| cursor | string | – | – |
| detail | string | – | – |
| explain | string | – | – |
| format | string | – | – |
| framework | string | – | – |
| hosting | string | – | – |
| license | string | – | – |
| limit | number | – | – |
| owner | string | – | – |
| q | string | – | – |
| reviewStatus | string | – | – |
| semantic | string | – | – |
| sort | string | – | – |
| source | string | – | – |
| task | string | – | Exact catalog task label; use q for broader capabilities. |
| type | string | – | – |
| Name | Type | Req | Description |
|---|---|---|---|
| nextCursor | string|null | – | – |
| note | object | – | – |
| rows | array | – | – |
| total | number|null | – | – |
No examples provided.
whats_new Read shipped changes ~30
Read dated product changes and shipped requests.
| Name | Type | Req | Description |
|---|---|---|---|
| limit | integer | – | – |
| since | string | – | – |
No output schema declared.
No examples provided.
How do I install the Hugging Bay MCP server?
Hugging Bay runs locally as an npm package, launched with npx -y hugging-bay-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
npm · hugging-bay-mcp
claude mcp add barneywohl-hugging-bay -- npx -y hugging-bay-mcp
What is the Hugging Bay MCP server?
Hugging Bay is an MCP server listed in the public MCP registry as io.github.barneywohl/hugging-bay. Open model files with recorded SHA-256 and licence labels. Ask for what's missing. This page covers its npm package (hugging-bay-mcp).
Is the Hugging Bay MCP server safe to use?
Hugging Bay scores 64 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 5 November 2026. It declares no install or post-install scripts. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.
What tools does the Hugging Bay MCP server expose?
Hugging Bay exposes 28 tools: bakeoff, blackboard, deployment_plan, find_runnable, get_agent_discovery, and 23 more. Their descriptions and schemas cost roughly 1,858 tokens of context every time the server is loaded.
Is the Hugging Bay MCP server still maintained?
Hugging Bay is still listed as active in the MCP registry. We last reached this channel on 5 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.
What licence is the Hugging Bay MCP server under?
Hugging Bay declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.