Create a new object (page, note, or any custom type) in Capacities. Use get_space_info first to find available structureIds for the space.
AI agents use capacities_create_object to create or update resources in Capacities MCP Worker — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Capacities MCP Worker environment.
This tool creates new objects in a knowledge management system. It modifies data but does not delete, destroy, or financially obligate. Creation is reversible (objects can be deleted later), making it a Write operation. Severity is medium because misuse could create unwanted clutter in a user's knowledge base, but the impact is limited to that user's Capacities instance and the action is non-destructive.
From the tool's definition Tool description explicitly states 'Create a new object (page, note, or any custom type) in Capacities', which is a create operation that modifies data in the knowledge base reversibly.
Attacks that exploit this kind of access
Create a new object (page, note, or any custom type) in Capacities. Use get_space_info first to find available structureIds for the space. It is categorised as a Write tool in the Capacities MCP Worker MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Capacities MCP Worker MCP server in PolicyLayer and add a rule for capacities_create_object: 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 Capacities MCP Worker. Nothing to install.
capacities_create_object 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 capacities_create_object 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 capacities_create_object. 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.
capacities_create_object is provided by the Capacities MCP Worker MCP server (tieubao/capacities-mcp-worker). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →