AI agents call auditSecretUsage to retrieve information from Azure Devops without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Auditing secrets is fundamentally a read operation that queries and retrieves information about secret usage patterns. However, the severity is elevated to 'high' because the tool accesses sensitive security data (secrets and their usage); misuse by an AI agent could lead to unauthorized disclosure of secret metadata or usage information, though it does not create, modify, or delete secrets themselves.
From the tool's definition The tool is described as 'Audit usage of secrets across services' — the verb 'audit' and the stated function of reviewing/examining secret usage indicates data retrieval and analysis without modification.
Documented attack patterns abuse exactly the kind of access auditSecretUsage gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Azure Devops, and nothing reaches the server without passing your rules. This is the rule we recommend for auditSecretUsage:
{
"version": "1",
"default": "deny",
"tools": {
"auditSecretUsage": {}
}
}auditSecretUsage is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Audit usage of secrets across services. It is categorised as a Read tool in the Azure Devops MCP Server, which means it retrieves data without modifying state.
Register the Azure Devops MCP server in PolicyLayer and add a rule for auditSecretUsage: 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 Azure Devops. Nothing to install.
auditSecretUsage 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 auditSecretUsage 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 auditSecretUsage. 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.
auditSecretUsage is provided by the Azure Devops MCP server (ryancardin15/azuredevops-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 97 Azure Devops tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
97 Azure Devops tools catalogued and risk-classified — across an index of 42,500+ MCP servers.