AI agents call match_score to retrieve information from Jishics 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 evaluation metrics and scoring details. It reads existing data from an AI-calculated database without modifying, executing commands, or committing financial obligations. The retrieval of comparison/rating data is a classic Read operation with minimal blast radius—misuse would only expose or selectively present rating information.
From the tool's definition Tool retrieves and returns evaluation scores and ratings for a service provider ("获取某个服务商的 AI 4 维评分详情" = 'get AI 4-dimensional rating details for a service provider').
Attacks that exploit this kind of access
获取某个服务商的 AI 4 维评分详情：综合评分、行业匹配度、地域匹配度、能力评分。每项含分数、满分、含义解释、数据来源说明。所有评分由 AI 引擎基于真实经营数据实时计算。. It is categorised as a Read tool in the Jishics MCP Server, which means it retrieves data without modifying state.
Register the Jishics MCP server in PolicyLayer and add a rule for match_score: 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 Jishics. Nothing to install.
match_score 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 match_score 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 match_score. 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.
match_score is provided by the Jishics MCP server (lpxuesir5555/jishics-mcp-server). 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 →