AI agents use add_memory to create or update resources in Mem0 — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Mem0 environment.
The tool name 'add_memory' clearly indicates creation of new memory entries in the Mem0 AsyncMemory API. This is a reversible modification operation (Write category). Severity is medium because misuse could pollute an AI agent's context with false or misleading memories, affecting decision-making, though the data itself is not financial and the operation is reversible via the sibling delete/erase tools.
From the tool's definition Tool name 'add_memory' combined with sibling destructive operations (delete_memory, erase_memories) and read operations (get_memory, list_memories, search_memories) indicates this tool creates or modifies memory records.
Attacks that exploit this kind of access
add_memory. It is categorised as a Write tool in the Mem0 MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Mem0 MCP server in PolicyLayer and add a rule for add_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 Mem0. Nothing to install.
add_memory is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the add_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 add_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.
add_memory is provided by the Mem0 MCP server (olk/mem0-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 →