Create a new object in your Cosmic bucket.
AI agents use create_object to create or update resources in Cosmic MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Cosmic MCP Server environment.
This tool creates new data (objects) in a headless CMS system. Creation is a reversible operation—objects can be updated or deleted—making it a Write action rather than Destructive. Severity is medium because misuse could add unwanted content to a production CMS, but the operation is not irreversible and the blast radius is limited to new object creation within a single bucket.
From the tool's definition Tool name 'create_object' and description 'Create a new object in your Cosmic bucket' indicate creation of new data in a CMS bucket.
Attacks that exploit this kind of access
Create a new object in your Cosmic bucket. It is categorised as a Write tool in the Cosmic MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Cosmic MCP Server MCP server in PolicyLayer and add a rule for 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 Cosmic MCP Server. Nothing to install.
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 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 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.
create_object is provided by the Cosmic MCP Server MCP server (patgpt/cosmic-mcp). 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 →