List all pull requests in a repository. Returns comprehensive PR information including title, description, status, reviewers, work items, commits, and thread counts. Supports filtering and pagination. Results are automatically truncated if they exceed size limits.
AI agents call azure_devops_pull_requests to retrieve information from Cursor Azure Devops without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a straightforward Read operation that retrieves pull request metadata from Azure DevOps. It performs no writes, deletions, code execution, or financial operations. The mention of automatic truncation confirms it is read-only. Even though pull request information may be sensitive in some contexts, the tool itself cannot modify, execute, or delete anything—it only fetches and displays existing data.
From the tool's definition The tool 'List all pull requests in a repository' with description explicitly stating it 'Returns comprehensive PR information' and 'Supports filtering and pagination' is fundamentally a query/retrieval operation with no side effects.
Documented attack patterns abuse exactly the kind of access azure_devops_pull_requests gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Cursor Azure Devops, and nothing reaches the server without passing your rules. This is the rule we recommend for azure_devops_pull_requests:
{
"version": "1",
"default": "deny",
"tools": {
"azure_devops_pull_requests": {}
}
}azure_devops_pull_requests 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.
List all pull requests in a repository. Returns comprehensive PR information including title, description, status, reviewers, work items, commits, and thread counts. Supports filtering and pagination. Results are automatically truncated if they exceed size limits. It is categorised as a Read tool in the Cursor Azure Devops MCP Server, which means it retrieves data without modifying state.
Register the Cursor Azure Devops MCP server in PolicyLayer and add a rule for azure_devops_pull_requests: 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 Cursor Azure Devops. Nothing to install.
azure_devops_pull_requests 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 azure_devops_pull_requests 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 azure_devops_pull_requests. 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.
azure_devops_pull_requests is provided by the Cursor Azure Devops MCP server (maximtitovich/cursor-azure-devops-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Cursor Azure Devops, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
20 Cursor Azure Devops tools catalogued and risk-classified — across an index of 43,000+ MCP servers.