Low Risk

maps_text_search

关键词搜索 API 根据用户输入的关键字进行 POI 搜索,并返回相关的信息

How to control maps_text_search ↓

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

Low Risk

This is a search/query tool that retrieves map data based on keywords. It has no side effects—it only reads and returns information about points of interest. No data is created, modified, deleted, or executed. This aligns clearly with the Read category for retrieval operations.

From the tool's definition Tool performs keyword-based POI (point of interest) search and returns related information. The description indicates data retrieval: '根据用户输入的关键字进行 POI 搜索,并返回相关的信息' (performs POI search based on user input keywords and returns related information).

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

PolicyLayer is an MCP gateway — it sits between your AI agents and 高德地图, and nothing reaches the server without passing your rules. This is the rule we recommend for maps_text_search:

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

maps_text_search 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 高德地图 — 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.

Go deeper

What does the maps_text_search tool do? +

关键词搜索 API 根据用户输入的关键字进行 POI 搜索,并返回相关的信息. It is categorised as a Read tool in the 高德地图 MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on maps_text_search? +

Register the 高德地图 MCP server in PolicyLayer and add a rule for maps_text_search: 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 高德地图. Nothing to install.

What risk level is maps_text_search? +

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

Can I rate-limit maps_text_search? +

Yes. Add a rate_limit block to the maps_text_search 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 maps_text_search completely? +

Set action: deny in the PolicyLayer policy for maps_text_search. 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 maps_text_search? +

maps_text_search is provided by the 高德地图 MCP server (sugarforever/amap-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every 高德地图 tool call.

Deterministic rules across all 16 高德地图 tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

Free to start. No card required.

16 高德地图 tools catalogued and risk-classified — across an index of 42,500+ 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.