获取单个因子的详细评分指标：年化收益、夏普比率、最大回撤、波动率、Alpha、Beta、IC均值等。
AI agents call get_factor_scores to retrieve information from FactorHub MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and retrieves pre-calculated financial analysis metrics for factors in the A-share market. It has no side effects, does not modify data, execute code, delete records, or move money. It is a straightforward data retrieval operation that returns read-only analytical information.
From the tool's definition Tool name 'get_factor_scores' and description indicating it retrieves detailed scoring metrics (annualized returns, Sharpe ratio, max drawdown, volatility, Alpha, Beta, IC mean, etc.) for a single factor.
Attacks that exploit this kind of access
获取单个因子的详细评分指标：年化收益、夏普比率、最大回撤、波动率、Alpha、Beta、IC均值等。. It is categorised as a Read tool in the FactorHub MCP Server MCP Server, which means it retrieves data without modifying state.
Register the FactorHub MCP Server MCP server in PolicyLayer and add a rule for get_factor_scores: 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 FactorHub MCP Server. Nothing to install.
get_factor_scores 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_factor_scores 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_factor_scores. 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_factor_scores is provided by the FactorHub MCP Server MCP server (michaelfeng/factorhub-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 →