AI agents call search_memory 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 is a Read operation—it queries and retrieves historical data (tool calls, errors, deployment records) without modifying or deleting anything. However, severity is elevated to 'medium' rather than 'low' because the memory contents could include sensitive information such as past financial requests, provider details, pricing data, or system configuration that an AI agent could exfiltrate.
From the tool's definition Tool name 'search_memory' and description indicates it searches MCP Server runtime memory including historical tool calls, errors, and deployment records. The verbs 'search' and 'retrieve' indicate data retrieval with no modification or deletion.
Attacks that exploit this kind of access
搜索 MCP Server 的运行记忆，包括历史工具调用、错误、部署记录。适用场景：排查故障、回顾历史操作、了解系统状态。. 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 search_memory: 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.
search_memory 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 search_memory 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 search_memory. 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.
search_memory 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 →