AI agents call get_work_item_type 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 'get' prefix combined with 'work_item_type' indicates a read-only query operation that retrieves configuration or metadata about work item types in Azure DevOps. No side effects or data modification are implied. Confidence is slightly reduced due to empty description, but semantic naming and sibling tool patterns provide sufficient evidence for Read classification.
From the tool's definition Tool name 'get_work_item_type' indicates retrieval/query operation. No description provided, but naming convention and context within an ADO integration server (alongside read operations like analyze_pipeline_input, extract_pipeline_run_data) strongly…
Attacks that exploit this kind of access
get_work_item_type. 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_item_type: 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_item_type 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_item_type 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_item_type. 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_item_type 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 →