find_memories_by_name
AI agents call find_memories_by_name to retrieve information from DAI MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool name and positioning within a memory retrieval system indicate this performs a search/lookup function to find stored memories by name attribute. No mutation, deletion, or side effects are implied. The empty description lowers confidence slightly, but the naming convention and sibling tools provide sufficient context to classify as Read with low severity.
From the tool's definition Tool name 'find_memories_by_name' indicates a search/retrieval operation. Server context describes 'retrieval of interconnected knowledge' and 'querying of information'.
Attacks that exploit this kind of access
find_memories_by_name. It is categorised as a Read tool in the DAI MCP Server MCP Server, which means it retrieves data without modifying state.
Register the DAI MCP Server MCP server in PolicyLayer and add a rule for find_memories_by_name: 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 DAI MCP Server. Nothing to install.
find_memories_by_name 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 find_memories_by_name 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 find_memories_by_name. 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.
find_memories_by_name is provided by the DAI MCP Server MCP server (patgpt/dai-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 →