Responded16 / 22 checks passed
Remote MCP server to run your Atako AI agents: chat, projects, files, integrations and channels.
- Passed: Handshake
- Passed: Tools listed
- Passed: Updated recently
Median latency 132 ms · Last checked
Independent monitoring
Health & checks
Responded
The server completed its last measured handshake. This is an observation, not a guarantee.
Last checked| Test area | Passed | Failed | Unmeasured |
|---|---|---|---|
ConnectionCan a client connect and discover tools? | 5 | 0 | 0 |
Reliability & speedDoes it respond consistently and quickly? | 0 | 1 | 3 |
Access & authenticationWhat is required to use this server? | 1 | 0 | 2 |
Tool qualityAre the tool definitions usable by an agent? | 4 | 0 | 0 |
Publisher identityCan the publisher be traced to its source? | 4 | 0 | 2 |
Unmeasured means there is not enough evidence to decide. How these checks work
Inspect individual checks 22 recorded
Core
- Pass
- Pass
- Pass
- Pass
- Pass
Performance
- Not measured
- Not measured
- Not measured
- Fail
removed bakeoff, blackboard, deployment_plan, get_agent_discovery, get_artifact, get_artifact_card, get_citation_pack, get_ranking, get_request, get_source_coverage, get_source_request_status, get_teach_template, list_files, list_requests, list_teach_bases, list_topics, post_to_board, read_board, recommend_specialist, report_run, request_crawl_access, request_feature, request_missing, resolve_artifact, whats_new
Access
- Pass
- Not measured
- Not measured
Tools
- Pass
- Pass
- Pass
- Pass
Publisher
- Pass
- Not measured
- Pass
- Pass
- Pass
- Not measured
Start using Hugging Bay
Connect to this server
Choose your client, copy the configuration, then enable the server in your client’s MCP settings.
Run this command in your terminal, then restart Claude Code.
Claude Code
claude mcp add --transport http hugging-bay https://huggingbay.xyz/api/mcpCapabilities
Tools 5
find_runnable
Models for a task and memory budget. provenOnly can return tested commands and a signed proof receipt when enabled. Use when the user states RAM or VRAM and needs model recommendations, not fine-tuning. Example: {"task":"chat","hardware":"8gb-laptop"}. Download is not run proof. provenOnly needs exact hardware and a run under 24 hours old. Read no-match reasons and retry guidance. Default answer is concise (at most 3200 bytes); use detail=full for the full record.
Discoveredget_model
One model's license, download readiness, main file, SHA-256, size and RAM estimate, plus runKit tested commands when Hugging Bay has run that exact file. Use when you have a model id and need its short file, license and hardware summary. Example: {"id":"hf-model-qwen-qwen3-0-6b-gguf"}. If unavailable, read the retry guidance and the model's metadata or file-plan links. Default answer is concise (at most 2400 bytes); use detail=full for the full record.
Discoveredget_serve_decision
One model's current file-download decision and its recorded reason. Use when you need to check whether listed files are currently offered to download. Example: {"id":"hf-model-qwen-qwen3-0-6b-gguf"}. Read-only. Runtime evidence is separate.
Discoveredhb_run_plan
Choose the best available model with a fresh signed run on your exact hardware class. Returns a recorded one-line command and hb.lock, or an explicit no-match. No key. Does not download or run anything. Example: {"task":"chat","hardware":"apple-m2-16gb"}.
Discoveredsearch_artifacts
Keyword search over model and dataset records, with task, license, size and format filters, when you have no exact name; returns ids and short summaries. Use when you need keyword or filtered catalog results without an exact model name. Example: {"q":"embedding","limit":5}. Reads records; does not change files. Default answer is concise (at most 2800 bytes); use detail=full for the full record.
DiscoveredRecent measurements
Probe history
| Checked | Result | Response | Tools |
|---|---|---|---|
| Connected | 1202 ms | 5 | |
| Connected | 918 ms | 29 |