AI agents call list_change_request_comments 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 |
|---|---|---|---|
state | string | — | Comment state: OPENED or DRAFT. Defaults to OPENED. |
localId | string | Yes | Merge request local ID within the repository. Use list_change_requests to discover valid local IDs. |
filePath | string | — | File path filter for inline comments. Use this to narrow comments to a specific file. |
resolved | boolean | — | Whether to list resolved comments. Defaults to false. Set to true to see resolved threads. |
commentType | string | — | Comment type: GLOBAL_COMMENT (general comments) or INLINE_COMMENT (code-level comments). Defaults to GLOBAL_COMMENT. |
repositoryId | string | Yes | Repository numeric ID or full path such as org/repo. Use list_repositories to discover valid repositories. |
organizationId | string | — | Yunxiao organization ID. When omitted, the server uses the user's default organization. |
patchSetBizIds | string | — | Comma-separated patch set IDs to filter comments by. Use list_change_request_patch_sets to discover valid patch set IDs. |
Parameters from the server's own tool schema.
This tool retrieves and displays comments on a merge request—a pure read operation with no ability to modify, delete, or execute actions. The blast radius if misused by an AI agent is minimal: it can only expose existing comments that are likely already visible to authorized users. No data is changed, deleted, or executed.
From the tool's definition Tool is named 'list_change_request_comments' and described as 'List comments on a CodeUp merge request. Use this to review feedback, inline discussions, and approval threads.' The verbs 'List' and 'review' indicate retrieval of existing data with no…
Risk signalsAccepts file system path (filePath)
Attacks that exploit this kind of access
List comments on a CodeUp merge request. Use this to review feedback, inline discussions, and approval threads. It is categorised as a Read tool in the Yunxiao MCP Server, which means it retrieves data without modifying state.
list_change_request_comments accepts 8 parameters: state, localId, filePath, resolved, commentType, repositoryId, organizationId, patchSetBizIds. Required: localId, repositoryId. 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_change_request_comments: 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_change_request_comments 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_change_request_comments 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_change_request_comments. 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_change_request_comments 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 →