AI agents call find_pipeline_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 to search for and retrieve pipeline data by name, which is a read-only operation. While the description is empty (lowering confidence slightly), the name and context within an ADO integration server strongly indicate this is a lookup/query function. No creation, modification, deletion, or execution is implied.
From the tool's definition Tool name 'find_pipeline_by_name' indicates a search/lookup operation that retrieves pipeline information. The description is empty, but the name strongly suggests a query operation with no side effects.
Attacks that exploit this kind of access
find_pipeline_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 find_pipeline_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.
find_pipeline_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 find_pipeline_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 find_pipeline_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.
find_pipeline_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 →