AI agents call list_pipeline_runs to retrieve information from Yunxiao without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
page | number | — | Page number for pagination. Starts at 1. |
status | string | — | Filter by run status. Common values: FAIL, SUCCESS, RUNNING. |
endTime | number | — | Run end time as a Unix timestamp in milliseconds. |
perPage | number | — | Page size for pagination. Yunxiao supports up to 30. |
startTime | number | — | Run start time as a Unix timestamp in milliseconds. |
pipelineId | string | Yes | Pipeline ID (string). Use list_pipelines to find the pipeline ID. |
triggerMode | number | — | Filter by trigger mode: 1 manual, 2 scheduled, 3 code push, 5 pipeline, 6 webhook. |
organizationId | string | — | Yunxiao organization ID. When omitted, the server uses the user's default organization. |
Parameters from the server's own tool schema.
This tool retrieves and lists historical pipeline execution data without creating, modifying, deleting, or executing anything. It is a pure data retrieval operation analogous to a search or list query, placing it firmly in the Read category with low severity since unauthorized access to logs poses minimal operational risk compared to destructive or execute-class operations.
From the tool's definition Tool description explicitly states 'List execution runs' and 'review historical runs and their statuses', which are read-only query operations with no modification or side effects.
Attacks that exploit this kind of access
List execution runs for a Flow pipeline. Use this to review historical runs and their statuses. For the latest run only, use get_latest_pipeline_run. It is categorised as a Read tool in the Yunxiao MCP Server, which means it retrieves data without modifying state.
list_pipeline_runs accepts 8 parameters: page, status, endTime, perPage, startTime, pipelineId, triggerMode, organizationId. Required: pipelineId. The full parameter table on this page comes from the server's own tool schema.
Register the Yunxiao MCP server in PolicyLayer and add a rule for list_pipeline_runs: 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 Yunxiao. Nothing to install.
list_pipeline_runs 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 list_pipeline_runs 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 list_pipeline_runs. 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.
list_pipeline_runs is provided by the Yunxiao MCP server (@futuretea/yunxiao-mcp-server). 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 →