Query work items using WIQL (Work Item Query Language)
AI agents call query_work_items to retrieve information from MCP Server for Azure DevOps without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
WIQL is a read-only query language for Azure DevOps that retrieves work item data without creating, modifying, deleting, or executing operations. While it accesses potentially sensitive project information, it has no side effects and cannot alter system state. The blast radius of misuse is limited to unauthorized data exposure rather than destructive or operational impacts.
From the tool's definition Tool name is 'query_work_items' and description states 'Query work items using WIQL (Work Item Query Language)' - query indicates retrieval without modification.
Attacks that exploit this kind of access
Query work items using WIQL (Work Item Query Language). It is categorised as a Read tool in the MCP Server for Azure DevOps MCP Server, which means it retrieves data without modifying state.
Register the MCP Server for Azure DevOps 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 MCP Server for Azure DevOps. 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 MCP Server for Azure DevOps MCP server (sepal7/mcp-ado). 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 →