飞鸽客服消息列表 — 获取与指定用户的飞鸽客服聊天记录。
AI agents call get_feige_messages to retrieve information from Pypi:mcp Cn Commerce without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves existing customer service messages/chat history from the Feige (飞鸽) system, which is a communication module used by Chinese e-commerce platforms. It performs no mutations, deletions, or side effects—it only reads and returns data. The read-only nature of the entire server and the retrieval semantics of the tool name/description confirm Read category classification.
From the tool's definition Tool name 'get_feige_messages' and description '获取与指定用户的飞鸽客服聊天记录' (retrieve customer service chat history with specified user) indicate data retrieval. The server description explicitly states 'read-only access'.
Attacks that exploit this kind of access
飞鸽客服消息列表 — 获取与指定用户的飞鸽客服聊天记录。. It is categorised as a Read tool in the Pypi:mcp Cn Commerce MCP Server, which means it retrieves data without modifying state.
Register the Pypi:mcp Cn Commerce MCP server in PolicyLayer and add a rule for get_feige_messages: 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 Pypi:mcp Cn Commerce. Nothing to install.
get_feige_messages 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 get_feige_messages 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 get_feige_messages. 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.
get_feige_messages is provided by the Pypi:mcp Cn Commerce MCP server (tonywang-hub/mcp-cn-commerce). 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 →