Add new memories to the database without overwriting existing ones
AI agents use add-memories to create or update resources in Memory MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Memory MCP environment.
The tool creates new records in a database without destroying or irreversibly modifying existing data. While it persists state and could accumulate unintended data if misused, it is reversible (memories can be cleared or deleted via sibling tools like 'clear-memories').
From the tool's definition Tool description states 'Add new memories to the database without overwriting existing ones' — this is a create/append operation that modifies data in MongoDB persistence.
Documented attack patterns abuse exactly the kind of access add-memories gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Memory MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for add-memories:
{
"version": "1",
"default": "deny",
"tools": {
"add-memories": {
"limits": [
{
"counter": "add-memories_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
} add-memories stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Add new memories to the database without overwriting existing ones. It is categorised as a Write tool in the Memory MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Memory 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 Memory MCP. 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 Memory MCP server (jamesanz/memory-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Memory MCP, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
10 Memory MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.