List pull requests in a project. status options: active, completed, abandoned, all.
AI agents call list_prs to retrieve information from Az Devops Cli without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and displays pull request data without creating, modifying, deleting, or executing any operations. It is purely informational, presenting existing data to the user. The blast radius of misuse is minimal—an agent could only view PR information, not alter repositories or trigger deployments.
From the tool's definition Tool name 'list_prs' and description 'List pull requests' indicate a retrieval operation with no modification or execution. Status filtering ('active, completed, abandoned, all') confirms this is a query-only function.
Attacks that exploit this kind of access
List pull requests in a project. status options: active, completed, abandoned, all. It is categorised as a Read tool in the Az Devops Cli MCP Server, which means it retrieves data without modifying state.
Register the Az Devops Cli MCP server in PolicyLayer and add a rule for list_prs: 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 Az Devops Cli. Nothing to install.
list_prs 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 list_prs 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 list_prs. 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.
list_prs is provided by the Az Devops Cli MCP server (praisesinkamba/az-devops-cli-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 →