add_memories
AI agents use add_memories to create or update resources in Mem0 Mcp Toggle — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Mem0 Mcp Toggle environment.
This tool creates or adds new memory entries to the local Chroma database. While not destructive or irreversible in the traditional sense, it modifies stored state by inserting data. The severity is medium because an AI agent could add numerous false or misleading memories, polluting the memory store and causing downstream errors in decision-making, but the memories can be deleted via the delete_memory tool.
From the tool's definition Tool name 'add_memories' (plural of add_memory) indicates creation of new memory records. Server context shows 'add_memory' is listed as a sibling tool on a memory storage system (Chroma vector database).
Attacks that exploit this kind of access
add_memories. It is categorised as a Write tool in the Mem0 Mcp Toggle MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Mem0 Mcp Toggle MCP server in PolicyLayer and add a rule for add_memories: 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 Mcp Toggle. Nothing to install.
add_memories 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_memories 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_memories. 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_memories is provided by the Mem0 Mcp Toggle MCP server (ost527/mem0-mcp-toggle). 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 →