Search shared memory items by title or content.
AI agents call shared-memory-search to retrieve information from MCP LLM Generator v2 without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves or queries existing shared memory data without side effects. The use of 'search' combined with the read-only parameters (title or content matching) clearly places it in the Read category. While it may expose information stored in shared memory, the severity is low because search operations themselves do not modify, execute, or delete data.
From the tool's definition Tool name 'shared-memory-search' and description 'Search shared memory items by title or content' indicate a query operation with no modification or deletion of data.
Attacks that exploit this kind of access
Search shared memory items by title or content. It is categorised as a Read tool in the MCP LLM Generator v2 MCP Server, which means it retrieves data without modifying state.
Register the MCP LLM Generator v2 MCP server in PolicyLayer and add a rule for shared-memory-search: 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 MCP LLM Generator v2. Nothing to install.
shared-memory-search 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 shared-memory-search 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 shared-memory-search. 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.
shared-memory-search is provided by the MCP LLM Generator v2 MCP server (mako10k/mcp-llm-generator). 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 →