search_jira_issues
AI agents call search_jira_issues 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.
The tool searches and retrieves JIRA issues without modifying data. It has no side effects beyond returning results. While the description is empty, the name and server context clearly indicate a read-only query operation. Confidence is slightly reduced due to the empty description, but the tool's purpose and name are unambiguous. Blast radius is minimal—an AI agent cannot cause damage by searching issues.
From the tool's definition Tool name 'search_jira_issues' combined with server description stating it supports 'JQL queries' and 'comprehensive issue details retrieval' indicates this is a search/query operation.
Attacks that exploit this kind of access
search_jira_issues. 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 search_jira_issues: 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.
search_jira_issues 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 search_jira_issues 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 search_jira_issues. 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.
search_jira_issues is provided by the JIRA MCP Server MCP server (rajsodhi-2/jira-mcp-server). 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 →