AI agents call get_work_item_comments 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 retrieves or queries work item comments with no side effects. While the description is uninformative, the naming convention strongly suggests read-only access to existing data. There is no indication this tool modifies, deletes, or executes operations. The low confidence penalty is offset by consistent naming patterns across the server.
From the tool's definition Tool name 'get_work_item_comments' indicates retrieval of existing comments. The description is empty but the sibling tools show patterns: 'add_work_item_comment' (Write), 'create_work_item' (Write), 'delete_work_item' (Destructive).
Attacks that exploit this kind of access
get_work_item_comments. 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_comments: 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_comments 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_comments 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_comments. 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_comments 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 →