AI agents call get_issue to retrieve information from Jira-Context-MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries existing Jira issue information. It performs a read-only operation that returns data about a ticket without creating, modifying, deleting, or executing any changes. The sibling tools (get_assigned_issues, get_issue_types, get_issues_by_type, get_projects) all follow the same read-only pattern, confirming this is a data retrieval function.
From the tool's definition Tool name 'get_issue' and description 'Get detailed information about a Jira issue' indicate retrieval of existing Jira ticket data with no modification or side effects.
Documented attack patterns abuse exactly the kind of access get_issue gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Jira-Context-MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for get_issue:
{
"version": "1",
"default": "deny",
"tools": {
"get_issue": {}
}
}get_issue 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.
Get detailed information about a Jira issue. It is categorised as a Read tool in the Jira-Context-MCP MCP Server, which means it retrieves data without modifying state.
Register the Jira-Context- MCP server in PolicyLayer and add a rule for get_issue: 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-Context-MCP. Nothing to install.
get_issue 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_issue 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_issue. 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_issue is provided by the Jira-Context- MCP server (rahulthedevil/jira-context-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Jira-Context-MCP, 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.
5 Jira-Context-MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.