taobao_read_messages
AI agents call taobao_read_messages to retrieve information from Taobao Sourcing Assistant without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool is a sibling of fetch and search operations on a Taobao sourcing server. 'Read messages' is a retrieval operation with no side effects. Even with an empty description, the naming pattern and context confirm this as a Read category tool.
From the tool's definition Tool name 'taobao_read_messages' contains 'read', indicating a retrieval operation. Description is empty, but the name and server context (sourcing product data, extracting pricing, reviews) strongly suggest this retrieves messages without modifying them.
Attacks that exploit this kind of access
taobao_read_messages. It is categorised as a Read tool in the Taobao Sourcing Assistant MCP Server, which means it retrieves data without modifying state.
Register the Taobao Sourcing Assistant MCP server in PolicyLayer and add a rule for taobao_read_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 Taobao Sourcing Assistant. Nothing to install.
taobao_read_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 taobao_read_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 taobao_read_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.
taobao_read_messages is provided by the Taobao Sourcing Assistant MCP server (randunun-eng/taobao-sourcing-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 →