Store information in long-term memory within a specific space.
AI agents use remember to create or update resources in Evermemos — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Evermemos environment.
This tool writes/creates data by storing information persistently in memory spaces. It is reversible (the sibling tool 'forget' exists to remove memories), so it qualifies as Write rather than Destructive. Misuse could lead to storing incorrect or misleading context that persists across sessions, affecting future AI behavior.
From the tool's definition "Store information in long-term memory within a specific space"
Documented attack patterns abuse exactly the kind of access remember gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Evermemos, and nothing reaches the server without passing your rules. This is the rule we recommend for remember:
{
"version": "1",
"default": "deny",
"tools": {
"remember": {
"limits": [
{
"counter": "remember_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}remember 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.
Store information in long-term memory within a specific space. It is categorised as a Write tool in the Evermemos MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Evermemos MCP server in PolicyLayer and add a rule for remember: 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 Evermemos. Nothing to install.
remember 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 remember 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 remember. 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.
remember is provided by the Evermemos MCP server (tt-a1i/evermemos-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Evermemos, 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.
7 Evermemos tools catalogued and risk-classified — across an index of 43,000+ MCP servers.