AI agents call get_failed_step_logs to retrieve information from Ado without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves log data from pipeline execution failures for diagnostic purposes. While it reads potentially sensitive build/deployment information (which warrants medium severity due to exposure of internal details, credentials in logs, or proprietary logic), it performs no write, execute, delete, or financial operations. It falls squarely in the Read category as a data retrieval function.
From the tool's definition Tool name 'get_failed_step_logs' indicates retrieval of logs from failed pipeline steps. The server description states it enables 'view logs' and 'troubleshoot builds'. No modification, deletion, or execution capability is described.
Attacks that exploit this kind of access
get_failed_step_logs. It is categorised as a Read tool in the Ado MCP Server, which means it retrieves data without modifying state.
Register the Ado MCP server in PolicyLayer and add a rule for get_failed_step_logs: 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 Ado. Nothing to install.
get_failed_step_logs 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 get_failed_step_logs 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 get_failed_step_logs. 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.
get_failed_step_logs is provided by the Ado MCP server (raboley/ado-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 →