list_viewlets
List viewlets from @hcengineering/view model metadata. Use attachTo with a Huly class id such as board:class:Card to scope by rendered document class; use list_huly_classes when you need class ids. The optional viewlet locator accepts a Viewlet _id, exact title, exact variant, or descriptor _id; ...
This record as markdown: /tools/io-github-dearlordylord-huly-mcp/list-viewlets.md
What list_viewlets does on Huly
AI agents call list_viewlets to retrieve information from Huly without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Why list_viewlets is rated Low
This tool only retrieves or queries data from the Huly system's view model metadata. It has no side effects, does not modify state, does not execute commands, and does not delete or move data. The ability to filter results by class id or viewlet identifiers does not elevate the risk—these are selection parameters, not generative or mutative operations.
From the tool's definition list_viewlets retrieves viewlets from model metadata without creating, modifying, deleting, or executing code.
Attacks that exploit this kind of access
The rule that runs list_viewlets safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Huly, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For list_viewlets, this is the rule to start with:
list_viewlets is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Huly, apply this rule, and every list_viewlets call is checked against it from then on.
Questions about list_viewlets
List viewlets from @hcengineering/view model metadata. Use attachTo with a Huly class id such as board:class:Card to scope by rendered document class; use list_huly_classes when you need class ids. The optional viewlet locator accepts a Viewlet _id, exact title, exact variant, or descriptor _id; descriptor ids may return multiple viewlets. Includes descriptor metadata and matching ViewletPreference configs. It is categorised as a Read tool in the Huly MCP Server, which means it retrieves data without modifying state.
Register the Huly MCP server in PolicyLayer and add a rule for list_viewlets: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Huly. Nothing to install.
list_viewlets is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the list_viewlets rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for list_viewlets. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
list_viewlets is provided by the Huly MCP server (@firfi/huly-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Huly, and thousands of servers like it.
This server
Across the catalogue