AI agents call read_cached_tasks to retrieve information from Jira without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool purely retrieves cached task data with no side effects. It does not create, modify, delete, or execute any operations. The local cache access means minimal blast radius even if misused by an agent. Classified as Read with low severity.
From the tool's definition Tool name explicitly contains 'read' and description states it 'Read[s] tasks from local cache without hitting the Jira API.' The action is query/retrieval only with no modification, deletion, or execution.
Attacks that exploit this kind of access
Read tasks from local cache without hitting the Jira API. Returns a single task when task_key is provided, or all cached tasks otherwise. It is categorised as a Read tool in the Jira MCP Server, which means it retrieves data without modifying state.
Register the Jira MCP server in PolicyLayer and add a rule for read_cached_tasks: 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. Nothing to install.
read_cached_tasks 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 read_cached_tasks 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 read_cached_tasks. 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.
read_cached_tasks is provided by the Jira MCP server (softspark/jira-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 →