列出项目的所有发布版本。用户可以通过此工具查看版本名称和对应的 ID。
AI agents call list_releases to retrieve information from PingCode MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and displays release information from PingCode without creating, modifying, or deleting any data. It is a straightforward data retrieval operation that returns project release metadata. No side effects or irreversible actions are possible. The low severity reflects minimal risk even if misused by an AI agent, as it only exposes already-accessible project release information.
From the tool's definition Tool name is 'list_releases' and description states it lists (列出) all releases of a project, allowing users to view version names and corresponding IDs.
Attacks that exploit this kind of access
列出项目的所有发布版本。用户可以通过此工具查看版本名称和对应的 ID。. It is categorised as a Read tool in the PingCode MCP Server MCP Server, which means it retrieves data without modifying state.
Register the PingCode MCP Server MCP server in PolicyLayer and add a rule for list_releases: 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 PingCode MCP Server. Nothing to install.
list_releases 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_releases 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_releases. 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_releases is provided by the PingCode MCP Server MCP server (ratatatat1/pingcode-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 →