AI agents call get_work_items_batch to retrieve information from Ado without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves work items in batch, a read-only operation with no side effects. However, Azure DevOps work items may contain sensitive project information, planning details, or credentials in descriptions, justifying medium severity if an agent over-retrieves or leaks data. Confidence is moderate due to the empty description; if it performs filtering or access control, the risk profile could differ.
From the tool's definition Tool name 'get_work_items_batch' indicates a retrieval operation with no modification. The 'get' verb and 'batch' processing pattern align with querying multiple work items. Description is empty, preventing higher confidence.
Attacks that exploit this kind of access
get_work_items_batch. It is categorised as a Read tool in the Ado MCP Server, which means it retrieves data without modifying state.
Register the Ado MCP server in PolicyLayer and add a rule for get_work_items_batch: 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 Ado. Nothing to install.
get_work_items_batch 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_work_items_batch 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_work_items_batch. 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_work_items_batch is provided by the Ado MCP server (raboley/ado-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 →