AI agents call filter_stocks to retrieve information from Tushare MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Based on the Tushare MCP server's documented purpose and naming patterns of sibling tools, 'filter_stocks' most likely filters or searches existing stock records without modifying or deleting data. The absence of descriptive text lowers confidence slightly, but the context and naming convention indicate a Read operation. No evidence of code execution, data modification, deletion, or financial transactions.
From the tool's definition Tool name 'filter_stocks' and server context indicate querying stock data. The description is empty, but sibling tools like 'collect_stock_data', 'get_block_trade', 'get_daily_basic' and the server's stated purpose ('query and search for stock information')…
Documented attack patterns abuse exactly the kind of access filter_stocks gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Tushare MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for filter_stocks:
{
"version": "1",
"default": "deny",
"tools": {
"filter_stocks": {}
}
}filter_stocks 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.
filter_stocks. It is categorised as a Read tool in the Tushare MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Tushare MCP Server MCP server in PolicyLayer and add a rule for filter_stocks: 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 Tushare MCP Server. Nothing to install.
filter_stocks 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 filter_stocks 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 filter_stocks. 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.
filter_stocks is provided by the Tushare MCP Server MCP server (zhewenzhang/tushare_mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 66 Tushare MCP Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
66 Tushare MCP Server tools catalogued and risk-classified — across an index of 42,500+ MCP servers.