Simple text search in JIRA
AI agents call search_jira_by_text to retrieve information from Regression-JIRA Integration System without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a search operation that queries and retrieves data from JIRA. It has no capability to create, modify, delete, or execute operations. The search functionality is a typical read-only operation with minimal blast radius if misused by an AI agent—worst case would be exposure of existing issue information already accessible to the authenticated user.
From the tool's definition Tool is described as 'Simple text search in JIRA' and named 'search_jira_by_text', which retrieves matching JIRA issues without modifying data.
Attacks that exploit this kind of access
Simple text search in JIRA. It is categorised as a Read tool in the Regression-JIRA Integration System MCP Server, which means it retrieves data without modifying state.
Register the Regression-JIRA Integration System MCP server in PolicyLayer and add a rule for search_jira_by_text: 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 Regression-JIRA Integration System. Nothing to install.
search_jira_by_text 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_by_text 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_by_text. 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_by_text is provided by the Regression-JIRA Integration System MCP server (nanyang12138/regression-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 →