AI agents call ado_get_pull_request_commits to retrieve information from Mcp Azure without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves commit metadata from an existing pull request without modifying state, executing code, or triggering external operations. It is a simple data retrieval operation with no side effects, fitting the Read category. The blast radius is minimal—an AI agent cannot cause harm by querying commit history.
From the tool's definition Tool name and description indicate a retrieval operation: 'Obtiene todos los commits de un Pull Request' (Gets all commits from a Pull Request).
Attacks that exploit this kind of access
Obtiene todos los commits de un Pull Request. It is categorised as a Read tool in the Mcp Azure MCP Server, which means it retrieves data without modifying state.
Register the Mcp Azure MCP server in PolicyLayer and add a rule for ado_get_pull_request_commits: 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 Mcp Azure. Nothing to install.
ado_get_pull_request_commits 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 ado_get_pull_request_commits 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 ado_get_pull_request_commits. 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.
ado_get_pull_request_commits is provided by the Mcp Azure MCP server (soulberto/mcp-azure). 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 →