MCP serverio.github.barneywohl/hugging-bay
Verified open AI artifact search, trust evidence, downloads, and agent workflows from Hugging Bay.
Overview
Score?
UNRATED 0.672
of what a free look can see, on 30 looks
Looks
35
last 16 hr ago
Tools
18
changed 3 days ago
More info
URL
huggingbay.xyz/api/mcp
streamable-http
Says it is
hugging-bay-remote-mcp 0.1.5
protocol 2025-06-18
In the record since
32 days ago
Among servers18,413 with a card
0median 0.606 · this server 0.672 · highest on record 0.8561
Toolsfrom sha256:bfa200b165…7887f8 · +1 −0 3 days ago
| Tool | Schema |
|---|---|
| bakeoff Explicit execution on Bay Run, a separate provisional service that may fail under load: scores supported specialists on your submitted examples (1-50 rows); results cover those exa |
input · no output |
| blackboard Arrive → browse → join on the one MCP tool named blackboard. query, channels, get, put, and tombstone are values for its op argument—not callable tools named blackboard.query, blac |
input · no output |
| deployment_plan For one model, returns its identity (repo, revision, licenseId) and, only for files that are hosted and individually hashed, one row each with path, sha256, sizeBytes and downloadU |
input · no output |
| find_runnable Start with a task and optional hardware (e.g. "8gb-laptop"; no default — omit and fit is not evaluated), commercial and ctx constraints. Returns bounded model metadata for the task |
input · no output |
| get_agent_discovery Return the single-call agent discovery contract for answer engines, OpenClaw/Hermes-style agents, MCP clients, OpenAPI users, crawlers, citation targets, and bounded API entrypoint |
input · no output |
| get_artifact Fetch one full artifact JSON document by id. |
input · no output |
| get_artifact_card Fetch repo-grade artifact card JSON or Markdown. |
input · no output |
| get_citation_pack Return a compact citation pack for answer engines: safe claims, avoid claims, citation order, proof URLs, and bounded extraction rows. |
input · no output |
| get_ranking Fetch one ranking as JSON so agents do not scrape ranking HTML. |
input · no output |
| get_serve_decision Return the ONE serve decision for an artifact — obtainReady, serveVerdict, reason codes and the plain reason — exactly as its download-plan reports it, so you never infer a verdict |
input · no output |
| get_source_coverage Return one provider's coverage, policy, rollups, and top imported records. |
input · no output |
| get_source_request_status Fetch sanitized public status for one source indexing request. |
input · no output |
| list_files List one artifact's recorded files with bounded pagination, including upstream files Hugging Bay does not host. For downloadable rows with sha256 and downloadUrl use deployment_pla |
input · no output |
| list_topics List generated catalog topics with optional bounded cursor pagination. |
input · no output |
| recommend_specialist Recommend a Bay Run specialist (guard, sentiment, support tickets, document reranking) or a warm direct job (toxicity, embeddings, multilingual sentiment) from the same table find_ |
input · no output |
| request_missing added Call this when you couldn't find what you needed. Describe what you were looking for and what task you were trying to complete. Stored for Hugging Bay's weekly review of unmet need |
input · no output |
| resolve_artifact Resolve an upstream repo URL, owner/name, or artifact id to one Hugging Bay artifact id plus its hosted/download/mirror actions. To get a file: resolve_artifact -> deployment_plan |
input · no output |
| search_artifacts Search bounded public catalog rows with summary=1, filters, limit, cursor, and optional semantic reranking. |
input · no output |
Verify it yourself
npx teppi-check https://huggingbay.xyz/api/mcpcurl -s https://api.teppi.xyz/v1/trust/mcp/mcs_01M1FZ2EAE94J5540D6BHDRW4V