查询某项目的仓库列表
AI agents call list_depots to retrieve information from CODING DevOps MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and lists repositories within a project. It is a retrieval operation with no capability to create, modify, delete, or execute actions. The description explicitly uses '查询' (query), confirming it is a read operation. No destructive, financial, or execution capabilities are present.
From the tool's definition Tool name 'list_depots' and description '查询某项目的仓库列表' (query a project's repository list) indicate a read-only operation that retrieves data without modification or side effects.
Attacks that exploit this kind of access
查询某项目的仓库列表. It is categorised as a Read tool in the CODING DevOps MCP Server MCP Server, which means it retrieves data without modifying state.
Register the CODING DevOps MCP Server MCP server in PolicyLayer and add a rule for list_depots: 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 CODING DevOps MCP Server. Nothing to install.
list_depots 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_depots 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_depots. 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_depots is provided by the CODING DevOps MCP Server MCP server (yupengfei1209/coding_devops_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 →