AI agents call get_jira to retrieve information from Jira MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves or queries data about a Jira issue based on an identifier. The verb 'Fetch' and the context of 'reference and query Jira tickets' confirm this is a read-only operation. No data is created, modified, deleted, or any external operations triggered. The presence of destructive tools like 'delete_issue' and 'delete_comment' on the same server further confirms this tool is purely read-based.
From the tool's definition Tool name 'get_jira' and description 'Fetch the Jira issue identified by 'issue_key'' indicates a retrieval operation with no side effects.
Documented attack patterns abuse exactly the kind of access get_jira gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Jira MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for get_jira:
{
"version": "1",
"default": "deny",
"tools": {
"get_jira": {}
}
}get_jira is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Fetch the Jira issue identified by 'issue_key' then. It is categorised as a Read tool in the Jira MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Jira MCP Server MCP server in PolicyLayer and add a rule for get_jira: 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 MCP Server. Nothing to install.
get_jira 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 get_jira 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 get_jira. 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.
get_jira is provided by the Jira MCP Server MCP server (redhat-community-ai-tools/jira-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Jira MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
30 Jira MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.