AI agents call get_sse_summary to retrieve information from Stock-MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries aggregate market data from stock exchanges. It has no side effects, does not modify data, does not execute code or external operations, and does not involve financial transactions. It is purely a read operation accessing public market summary information. Low severity due to minimal blast radius—returning market overview data carries negligible risk of harm from misuse.
From the tool's definition Tool name 'get_sse_summary' and description '获取A股市场总览（上交所和深交所数据）' (Get A-share market overview for Shanghai and Shenzhen stock exchange data) indicate retrieval of market summary information with no modification or execution capability.
Attacks that exploit this kind of access
获取A股市场总览（上交所和深交所数据）. It is categorised as a Read tool in the Stock-MCP MCP Server, which means it retrieves data without modifying state.
Register the Stock- MCP server in PolicyLayer and add a rule for get_sse_summary: 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 Stock-MCP. Nothing to install.
get_sse_summary 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_sse_summary 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_sse_summary. 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_sse_summary is provided by the Stock- MCP server (nomi982/stock-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →