AI agents call match_for_demand 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.
The tool retrieves and ranks existing provider data against demand criteria. It performs no side effects: no data is created, modified, deleted, or financial commitments made. Even though it may be used in an automated 'AI Agent autonomous matching process' (AI Agent 自主撮合流程), the tool itself only reads and ranks data.
From the tool's definition Tool description states it 'matches service providers based on demand attributes' and 'returns a weighted scoring sorted matching list' (根据需求属性匹配服务商，返回加权评分排序的匹配列表).
Attacks that exploit this kind of access
根据需求属性匹配服务商，返回加权评分排序的匹配列表。用于 AI Agent 自主撮合流程。. 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_for_demand: 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_for_demand 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_for_demand 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_for_demand. 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_for_demand 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 →