AI agents call getAICodeReview 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.
This tool retrieves and presents code review suggestions without creating, modifying, deleting, or executing any code. It is purely informational, analyzing existing code and returning analysis results. No reversible or irreversible changes are made, no commands are executed, and no financial transactions occur.
From the tool's definition Tool name is 'getAICodeReview' and description states 'Get AI-based code review suggestions' — the verb 'Get' and framing as retrieving suggestions indicates a read-only retrieval operation with no data modification or side effects.
Documented attack patterns abuse exactly the kind of access getAICodeReview 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 getAICodeReview:
{
"version": "1",
"default": "deny",
"tools": {
"getAICodeReview": {}
}
}getAICodeReview 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.
Get AI-based code review suggestions. 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 getAICodeReview: 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.
getAICodeReview 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 getAICodeReview 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 getAICodeReview. 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.
getAICodeReview 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.