AI agents call get_pipeline_failure_summary_by_name 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.
The tool appears designed to fetch and summarize pipeline failure data from Azure DevOps, which is a read-only operation with no side effects. The 'get' prefix and 'summary' suffix strongly suggest data retrieval.
From the tool's definition Tool name contains 'get' and 'summary', indicating data retrieval. Description is empty, limiting definitive assessment, but context from sibling tools (analyze_pipeline_input, extract_pipeline_run_data_by_name) suggests this retrieves pipeline failure…
Attacks that exploit this kind of access
get_pipeline_failure_summary_by_name. 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_pipeline_failure_summary_by_name: 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_pipeline_failure_summary_by_name 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_pipeline_failure_summary_by_name 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_pipeline_failure_summary_by_name. 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_pipeline_failure_summary_by_name 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 →