AI agents call check_ado_authentication 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 performs a verification/status check of authentication credentials and connection state. It retrieves or validates information about an existing connection without creating, modifying, deleting, or executing operations. The tool is purely informational and diagnostic in nature, making it a Read category action.
From the tool's definition Tool name 'check_ado_authentication' and description 'Verifies that the connection and authentication to Azure DevOps are successful' indicate a diagnostic check operation that queries authentication status without modifying or executing anything.
Attacks that exploit this kind of access
Verifies that the connection and authentication to Azure DevOps are successful. 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 check_ado_authentication: 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.
check_ado_authentication 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 check_ado_authentication 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 check_ado_authentication. 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.
check_ado_authentication 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 →