Build a dependency/relationship graph starting from a seed issue. Returns a map of connected issues (parent/child hierarchy, blocks, relates to, duplicates, etc.) with nodes and edges, plus a Mermaid diagram for visualization. Use this to understand how issues are connected across epics, stories,...
AI agents call jira_get_issue_graph to retrieve information from Mcp Jira Stdio without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
issueKey | string | Yes | Seed issue key to start graph traversal from (e.g., PROJECT-123) |
maxDepth | number | — | Maximum BFS traversal depth from seed issue (default: 2, max: 5) |
maxNodes | number | — | Maximum number of nodes to include in the graph (default: 50, max: 200) |
direction | string | — | Which link directions to follow: "all", "inward", or "outward" (default: "all") |
linkTypes | array | — | Filter to specific link types (e.g., ["Blocks", "Relates"]). If omitted, includes all link types. |
includeHierarchy | boolean | — | Include parent/child/subtask edges (default: true) |
Parameters from the server's own tool schema.
This tool performs read-only operations that retrieve and visualize existing Jira issue relationships. It has no side effects—it does not create, modify, delete, or execute any actions. The primary function is data retrieval and presentation of issue graph structure. Low severity because misuse would only expose information without operational impact.
From the tool's definition Tool description states it 'Build[s] a dependency/relationship graph' and 'Returns a map of connected issues' with 'a Mermaid diagram for visualization'. It retrieves and queries issue relationships without modifying any data.
Attacks that exploit this kind of access
Build a dependency/relationship graph starting from a seed issue. Returns a map of connected issues (parent/child hierarchy, blocks, relates to, duplicates, etc.) with nodes and edges, plus a Mermaid diagram for visualization. Use this to understand how issues are connected across epics, stories, and subtasks. It is categorised as a Read tool in the Mcp Jira Stdio MCP Server, which means it retrieves data without modifying state.
jira_get_issue_graph accepts 6 parameters: issueKey, maxDepth, maxNodes, direction, linkTypes, includeHierarchy. Required: issueKey. The full parameter table on this page comes from the server's own tool schema.
Register the Mcp Jira Stdio MCP server in PolicyLayer and add a rule for jira_get_issue_graph: 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 Mcp Jira Stdio. Nothing to install.
jira_get_issue_graph 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 jira_get_issue_graph 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 jira_get_issue_graph. 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.
jira_get_issue_graph is provided by the Mcp Jira Stdio MCP server (mcp-jira-stdio). 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 →