Low Risk

icost_categories

iCost支持的收入、支出分类

How to control icost_categories ↓

What icost_categories does on Icost App

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

Low Risk

Why icost_categories needs a policy

The tool appears to list or retrieve the supported income and expense categories in the iCost app. This is a read-only query operation with no ability to modify, delete, or execute anything. Low severity since misuse only exposes category names.

From the tool's definition 'iCost支持的收入、支出分类' translates to 'Income and expense categories supported by iCost' — this retrieves/lists category data with no side effects

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

How to control icost_categories

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

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

icost_categories 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 Icost App — 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 icost_categories

What does the icost_categories tool do? +

iCost支持的收入、支出分类. It is categorised as a Read tool in the Icost App MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on icost_categories? +

Register the Icost App MCP server in PolicyLayer and add a rule for icost_categories: 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 Icost App. Nothing to install.

What risk level is icost_categories? +

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

Can I rate-limit icost_categories? +

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

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

icost_categories is provided by the Icost App MCP server (toolife/icost-app-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 Icost App tool call.

Start from Icost App, 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.

4 Icost App 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.