AI agents use assets.addObjectReference to create or update resources in Gojira — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Gojira environment.
This tool creates new data (object references/relationships) in the Assets CMDB system, which is a write operation. It is not destructive (references can be removed), not financial, and not Execute (no arbitrary code/command execution). Severity is medium because misuse could corrupt asset relationship data and impact dependency tracking, but the effects are reversible via reference deletion.
From the tool's definition 'Add a reference between two Assets objects' — creates a new relationship/link between existing CMDB objects, modifying their state reversibly.
Attacks that exploit this kind of access
Add a reference between two Assets objects. It is categorised as a Write tool in the Gojira MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Gojira MCP server in PolicyLayer and add a rule for assets.addObjectReference: 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 Gojira. Nothing to install.
assets.addObjectReference 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 assets.addObjectReference 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 assets.addObjectReference. 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.
assets.addObjectReference is provided by the Gojira MCP server (windoze95/gojira-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 →