Execute a read-only Yunxiao OpenAPI call. Use this as a fallback for endpoints not covered by dedicated tools. GET is supported; POST is limited to read-only search/list-style endpoints. Prefer dedicated tools (e.g., search_workitems, list_pipelines) when available, as they provide better paramet...
AI agents invoke call_yunxiao_api to trigger actions in Yunxiao. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
| Parameter | Type | Required | Description |
|---|---|---|---|
body | string | — | JSON string of request body for POST requests. |
path | string | Yes | API path relative to the base URL, e.g. /projex/organizations/{orgId}/projects/{projectId} |
method | string | — | HTTP method: GET or POST. Defaults to GET. |
queryParams | string | — | JSON string of query parameters to append to the URL. |
Parameters from the server's own tool schema.
Although the description emphasizes 'read-only' constraints, the tool fundamentally executes arbitrary API calls to an external DevOps platform (Alibaba Yunxiao). The ability to make POST requests to 'read-only search/list-style endpoints' and call unspecified endpoints creates a risk that an AI agent could: (1) bypass the read-only restriction if the platform has inconsistent endpoint behavior, (2) trigger side…
From the tool's definition Tool description states 'Execute a read-only Yunxiao OpenAPI call' and explicitly supports 'GET' and 'POST' methods for making API calls.
Risk signalsAccepts file system path (path) · Accepts raw HTML/template content (body)
Attacks that exploit this kind of access
Execute a read-only Yunxiao OpenAPI call. Use this as a fallback for endpoints not covered by dedicated tools. GET is supported; POST is limited to read-only search/list-style endpoints. Prefer dedicated tools (e.g., search_workitems, list_pipelines) when available, as they provide better parameter validation and error guidance. It is categorised as a Execute tool in the Yunxiao MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
call_yunxiao_api accepts 4 parameters: body, path, method, queryParams. Required: path. 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 call_yunxiao_api: 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.
call_yunxiao_api is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the call_yunxiao_api 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 call_yunxiao_api. 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.
call_yunxiao_api 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 →