This record as markdown: /tools/baidu-map/overall-rating.md
What overall_rating does on Baidu Map
AI agents call overall_rating to retrieve information from Baidu Map without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Why overall_rating is rated Low
The tool name implies fetching an overall rating value, which is a read operation. However, the description provides no useful information, so confidence is low. Given the context of Baidu Map API with sibling tools like 'business_info', 'comment_num', and 'address', this likely retrieves a business or location rating score — a read-only operation with minimal blast radius.
From the tool's definition Tool name 'overall_rating' suggests retrieval of rating data; description is uninformative ('string')
Attacks that exploit this kind of access
The rule that runs overall_rating safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Baidu Map, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For overall_rating, this is the rule to start with:
overall_rating is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Baidu Map, apply this rule, and every overall_rating call is checked against it from then on.
Questions about overall_rating
string. It is categorised as a Read tool in the Baidu Map MCP Server, which means it retrieves data without modifying state.
Register the Baidu Map MCP server in PolicyLayer and add a rule for overall_rating: 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 Baidu Map. Nothing to install.
overall_rating 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 overall_rating 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 overall_rating. 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.
overall_rating is provided by the Baidu Map MCP server (@baidumap/mcp-server-baidu-map). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Baidu Map, and thousands of servers like it.
This server
Across the catalogue