AI agents call get_income_statement to retrieve information from Cn Financial without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves financial statement data (income statement) without any side effects. It queries existing financial information and returns it to the user. There is no ability to modify, delete, execute commands, or perform financial transactions. This is a straightforward read/query operation typical of financial data APIs.
From the tool's definition Tool name 'get_income_statement' and description '获取利润表（按季度）' (Get income statement by quarter) indicate data retrieval only. No modification, deletion, execution, or financial transaction capability is present.
Documented attack patterns abuse exactly the kind of access get_income_statement gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Cn Financial, and nothing reaches the server without passing your rules. This is the rule we recommend for get_income_statement:
{
"version": "1",
"default": "deny",
"tools": {
"get_income_statement": {}
}
}get_income_statement is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
获取利润表（按季度）。. It is categorised as a Read tool in the Cn Financial MCP Server, which means it retrieves data without modifying state.
Register the Cn Financial MCP server in PolicyLayer and add a rule for get_income_statement: 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 Cn Financial. Nothing to install.
get_income_statement 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 get_income_statement 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 get_income_statement. 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.
get_income_statement is provided by the Cn Financial MCP server (ccq1/cn-financial-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Cn Financial, 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.
42 Cn Financial tools catalogued and risk-classified — across an index of 43,000+ MCP servers.