AI agents call assets.aqlSearch to retrieve information from Gojira without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves configuration data from the Assets CMDB using AQL queries. It has no side effects—it only reads and returns data. No data is created, modified, deleted, or financial operations are triggered. This is a straightforward Read operation with low severity, as misuse would only expose existing data.
From the tool's definition Tool name 'assets.aqlSearch' and description 'AQL (Assets Query Language) search' indicate a query/search operation. AQL is a read-only query language for Atlassian Assets (CMDB). No keywords suggesting mutations (create, update, delete, drop) are present.
Attacks that exploit this kind of access
AQL (Assets Query Language) search. It is categorised as a Read tool in the Gojira MCP Server, which means it retrieves data without modifying state.
Register the Gojira MCP server in PolicyLayer and add a rule for assets.aqlSearch: 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.aqlSearch 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 assets.aqlSearch 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.aqlSearch. 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.aqlSearch 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 →