AI agents use update_memory to create or update resources in Memlord — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Memlord environment.
Update operations create or modify data reversibly, fitting the Write category. Severity is medium because the tool modifies personal/team memory data which could affect decision-making or knowledge bases, but the changes are reversible (unlike Destructive) and don't involve financial or code execution risks.
From the tool's definition Tool name 'update_memory' indicates modification of stored data. Server context confirms it operates on a memory system with sibling tools including delete_memory, get_memory, store_memory, and recall_memory, establishing that this tool modifies existing…
Documented attack patterns abuse exactly the kind of access update_memory gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Memlord, and nothing reaches the server without passing your rules. This is the rule we recommend for update_memory:
{
"version": "1",
"default": "deny",
"tools": {
"update_memory": {
"limits": [
{
"counter": "update_memory_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}update_memory 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.
update_memory. It is categorised as a Write tool in the Memlord MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Memlord MCP server in PolicyLayer and add a rule for update_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 Memlord. Nothing to install.
update_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 update_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 update_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.
update_memory is provided by the Memlord MCP server (myrikld/memlord). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Memlord, 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 Memlord tools catalogued and risk-classified — across an index of 43,000+ MCP servers.