Home / MCP registry index / io.github.barneywohl/hugging-bay
Hugging Bay
io.github.barneywohl/hugging-bay in the official MCP registry.
Endpoint https://huggingbay.xyz/api/mcp. Source: github.com/barneywohl/hugging-bay.
The registry describes it as: Open model files with recorded SHA-256 and licence labels. Ask for what's missing.
We read its 28 tools on 2026-10-27. Nothing in them matched our tool-poisoning rules. It also sets server instructions, text a client puts in front of the model on connect; those were read too.
A clean read means these rules found nothing, not that the server is harmless. A server can change its tools at any time, which is why the index reads it again every week.
Tools it advertises
search_artifacts find_runnable get_model deployment_plan resolve_artifact list_files read_board post_to_board report_run whats_new request_feature get_request list_requests recommend_specialist get_agent_discovery list_teach_bases get_teach_template get_artifact get_artifact_card bakeoff blackboard get_source_coverage get_ranking get_citation_pack list_topics get_source_request_status get_serve_decision request_missing
Run this server? Show the check in your README
The badge reflects the latest weekly read: 
[](https://lazaretto.dev/mcp-registry/io-github-barneywohl-hugging-bay)How this was checked
Lazaretto connects to the endpoint the way any MCP client does, asks the server to introduce itself and list its tools, and reads every name, description, parameter schema and server instruction for tool poisoning: hidden directive blocks, orders to read local secrets, parameters built to carry secrets or the conversation out, orders that redirect another server's tools, and invisible characters. It never calls a tool. What we found across the registry.
To run the same check every time Claude Code adds a server, install the free lazaretto-guard plugin. Browse every server in the index.