Low Risk

input_tips

input_tips

How to control input_tips ↓

What input_tips does on XiaozhiMCP-MapNAVI

AI agents call input_tips to retrieve information from XiaozhiMCP-MapNAVI without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

Low Risk

Why input_tips needs a policy

Based on naming convention and context within a map/navigation API (Amap), 'input_tips' likely retrieves search suggestions or autocomplete data. This is a read-only operation with no state modification or side effects. Severity is low as it only returns informational data. Confidence is moderate (0.6) due to missing description.

From the tool's definition Tool name 'input_tips' suggests autocomplete or suggestion functionality typical of map/navigation services. No description provided, limiting certainty.

Documented attack patterns abuse exactly the kind of access input_tips gives an agent:

How to control input_tips

PolicyLayer is an MCP gateway — it sits between your AI agents and XiaozhiMCP-MapNAVI, and nothing reaches the server without passing your rules. This is the rule we recommend for input_tips:

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "input_tips": {}
  }
}

input_tips is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.

  1. Create a free account and register XiaozhiMCP-MapNAVI — nothing to install.
  2. Add this policy — paste it, or build it visually.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
CAP THIS TOOL →

Free to start. No card required.

Related tools and policies

Go deeper

Questions about input_tips

What does the input_tips tool do? +

input_tips. It is categorised as a Read tool in the XiaozhiMCP-MapNAVI MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on input_tips? +

Register the XiaozhiMCP-MapNAVI MCP server in PolicyLayer and add a rule for input_tips: 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 XiaozhiMCP-MapNAVI. Nothing to install.

What risk level is input_tips? +

input_tips is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit input_tips? +

Yes. Add a rate_limit block to the input_tips 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.

How do I block input_tips completely? +

Set action: deny in the PolicyLayer policy for input_tips. 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.

What MCP server provides input_tips? +

input_tips is provided by the XiaozhiMCP-MapNAVI MCP server (rickeylaiii/xiaoai_mapmcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every XiaozhiMCP-MapNAVI tool call.

Start from XiaozhiMCP-MapNAVI, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

Free to start. No card required.

8 XiaozhiMCP-MapNAVI tools catalogued and risk-classified — across an index of 43,000+ MCP servers.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.