AI agents call get_my_project_workitems 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 |
|---|---|---|---|
status | string | — | Comma-separated status IDs applied to every category. |
userId | string | Yes | User ID (string) to filter work items by. Use list_project_members to find user IDs in the project. |
relation | string | — | Filter relation: assigned or created. Defaults to assigned. |
projectId | string | Yes | Project ID. Use search_projects to discover valid IDs. |
categories | string | — | Comma-separated work item categories. Defaults to Task,Bug. |
sampleLimit | number | — | Samples returned per category. Defaults to 5, clamped to 0-200. |
organizationId | string | — | Yunxiao organization ID. When omitted, the server uses the user's default organization. |
Parameters from the server's own tool schema.
This tool retrieves and queries work item data from the Yunxiao DevOps platform filtered by user and project. It has no side effects—it does not create, modify, delete, or execute any operations. The stated purpose (workload review and stand-up summaries) confirms a read-only, informational use case.
From the tool's definition Tool description explicitly states 'Get work items' and indicates retrieval operations ('assigned to or created by') for 'workload review and stand-up summaries'. No modification, deletion, execution, or financial operations are described.
Attacks that exploit this kind of access
Get work items assigned to or created by a specific user for one project, grouped by category. Useful for workload review and stand-up summaries. It is categorised as a Read tool in the Yunxiao MCP Server, which means it retrieves data without modifying state.
get_my_project_workitems accepts 7 parameters: status, userId, relation, projectId, categories, sampleLimit, organizationId. Required: userId, 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_my_project_workitems: 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_my_project_workitems 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_my_project_workitems 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_my_project_workitems. 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_my_project_workitems 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 →