Read raw details of a Jira issue (description, subtasks, changelog, labels, priority, parent, attachments). Data-only — does NOT guide analysis or post comments. Use jira_analyze_task when you need the full investigation workflow.
AI agents call jira_read_task to retrieve information from Jira Dev without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a pure retrieval operation that queries Jira data without creating, modifying, deleting, or executing any actions. The description explicitly distinguishes it from analysis or comment posting. The blast radius of misuse is minimal—an agent could read sensitive issue information, but cannot alter state or trigger external operations.
From the tool's definition Tool description states it "Read raw details of a Jira issue" and explicitly notes "Data-only — does NOT guide analysis or post comments." The tool retrieves issue metadata (description, subtasks, changelog, labels, priority, parent, attachments) with no…
Attacks that exploit this kind of access
Read raw details of a Jira issue (description, subtasks, changelog, labels, priority, parent, attachments). Data-only — does NOT guide analysis or post comments. Use jira_analyze_task when you need the full investigation workflow. It is categorised as a Read tool in the Jira Dev MCP Server, which means it retrieves data without modifying state.
Register the Jira Dev MCP server in PolicyLayer and add a rule for jira_read_task: 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 Jira Dev. Nothing to install.
jira_read_task 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 jira_read_task 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 jira_read_task. 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.
jira_read_task is provided by the Jira Dev MCP server (jira-dev-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 →