Subscribe a workspace member to object notifications by adding a core collaborator row. Member can be an account UUID, exact employee/person name, or email. Idempotent when already subscribed.
AI agents use add_object_collaborator to create or update resources in Huly — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Huly environment.
An AI agent can call add_object_collaborator faster than any human can review — one bad instruction and it creates or modifies resources in Huly by the hundred, each call as confident as the last.
Attacks that exploit this kind of access
Subscribe a workspace member to object notifications by adding a core collaborator row. Member can be an account UUID, exact employee/person name, or email. Idempotent when already subscribed. It is categorised as a Write tool in the Huly MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Huly MCP server in PolicyLayer and add a rule for add_object_collaborator: 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.
add_object_collaborator is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the add_object_collaborator 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 add_object_collaborator. 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.
add_object_collaborator 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.