AI agents call lithtrix_memory_search to retrieve information from Lithtrix without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries existing memory data and returns search results without creating, modifying, deleting, or executing operations. It has minimal blast radius—misuse would only expose stored information to the agent, not cause external damage or irreversible changes. The GET semantics and 'search' function classify it as a Read operation.
From the tool's definition Tool performs 'Semantic search over your memories' with GET request method, which is a retrieval operation with no data modification capability.
Attacks that exploit this kind of access
Semantic search over your memories (GET /v1/memory/search). It is categorised as a Read tool in the Lithtrix MCP Server, which means it retrieves data without modifying state.
Register the Lithtrix MCP server in PolicyLayer and add a rule for lithtrix_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 Lithtrix. Nothing to install.
lithtrix_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 lithtrix_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 lithtrix_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.
lithtrix_memory_search is provided by the Lithtrix MCP server (lithtrix/lithtrix-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 →