AI agents invoke workflows.publishWorkflow to trigger actions in Gojira. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
Publishing a workflow draft triggers an external asynchronous operation in Atlassian Jira that activates a workflow, making it live and affecting all projects/issue types that use it. This is an Execute action (triggering an external operation with potentially wide-reaching effects).
From the tool's definition Publish a workflow draft. Async — Atlassian returns an operation id; this tool polls it briefly and returns the eventual status.
Attacks that exploit this kind of access
Publish a workflow draft. Async — Atlassian returns an operation id; this tool polls it briefly and returns the eventual status. It is categorised as a Execute tool in the Gojira MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Gojira MCP server in PolicyLayer and add a rule for workflows.publishWorkflow: 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.
workflows.publishWorkflow is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the workflows.publishWorkflow 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 workflows.publishWorkflow. 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.
workflows.publishWorkflow 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 →