AI agents call query_work_items 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.
The tool performs a read-only query operation on work items in Azure DevOps. WIQL (Work Item Query Language) and simple filtering are both querying mechanisms that retrieve and display data without creating, modifying, deleting, or executing arbitrary operations. Pagination support further confirms this is a data retrieval tool. No side effects or state changes occur from executing queries.
From the tool's definition Tool name is 'query_work_items' and description states it 'Query work items using WIQL or simple filtering with pagination support.' This is a retrieval operation with no modification capability.
Attacks that exploit this kind of access
Query work items using WIQL or simple filtering with pagination support. 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 query_work_items: 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.
query_work_items 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 query_work_items 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 query_work_items. 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.
query_work_items 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 →