Get a read-only project risk dashboard with category samples, overdue work items, and optional high-priority/stale sections. Best used for project health checks and sprint retrospectives.
AI agents call get_project_risk_dashboard to retrieve information from Yunxiao without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
tag | string | — | Comma-separated tag IDs applied to every section. |
sprint | string | — | Comma-separated sprint IDs applied to every section. |
status | string | — | Comma-separated active status IDs applied to every section. |
creator | string | — | Comma-separated creator user IDs applied to every section. |
subject | string | — | Subject contains filter applied to every section. |
projectId | string | Yes | Project ID. Use search_projects to discover valid IDs. |
assignedTo | string | — | Comma-separated assignee user IDs applied to every section. |
categories | string | — | Comma-separated categories for category totals. Defaults to Risk,Bug,Task. |
sampleLimit | number | — | Samples returned per section. Defaults to 5, clamped to 0-200. |
staleBefore | string | — | Status update date upper bound for the stale section. |
statusStage | string | — | Comma-separated status stage IDs applied to every section. |
highPriority | string | — | Comma-separated priority IDs for the high-priority section. |
Parameters from the server's own tool schema.
This tool queries and retrieves project metrics and status information for visibility purposes only. It performs no modifications, deletions, or external operations. The read-only nature and use case ('project health checks and sprint retrospectives') indicate pure information retrieval with no blast radius from misuse.
From the tool's definition Tool is explicitly described as 'read-only project risk dashboard' that retrieves category samples, overdue work items, and optional sections. The verb 'Get' and modifier 'read-only' confirm no side effects.
Risk signalsHigh parameter count (15 properties)
Attacks that exploit this kind of access
Get a read-only project risk dashboard with category samples, overdue work items, and optional high-priority/stale sections. Best used for project health checks and sprint retrospectives. It is categorised as a Read tool in the Yunxiao MCP Server, which means it retrieves data without modifying state.
get_project_risk_dashboard accepts 12 parameters: tag, sprint, status, creator, subject, projectId, assignedTo, categories, sampleLimit, staleBefore, statusStage, highPriority. Required: projectId. The full parameter table on this page comes from the server's own tool schema.
Register the Yunxiao MCP server in PolicyLayer and add a rule for get_project_risk_dashboard: 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 Yunxiao. Nothing to install.
get_project_risk_dashboard 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_project_risk_dashboard 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_project_risk_dashboard. 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_project_risk_dashboard is provided by the Yunxiao MCP server (@futuretea/yunxiao-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 →