AI agents use memory_update to create or update resources in Rekal — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Rekal environment.
The tool updates memory records in a reversible manner (Write category). Severity is medium because misconfiguration or agent misuse could corrupt or overwrite important memory context needed across sessions, but data is stored locally and not irreversibly destroyed. Confidence is reduced slightly (0.85 vs.
From the tool's definition Tool name 'memory_update' indicates modification of stored data in the local SQLite memory system. Sibling tools show write operations (memory_delete, memory_prune) and the server manages persistent data storage with hybrid search across sessions.
Documented attack patterns abuse exactly the kind of access memory_update gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Rekal, and nothing reaches the server without passing your rules. This is the rule we recommend for memory_update:
{
"version": "1",
"default": "deny",
"tools": {
"memory_update": {
"limits": [
{
"counter": "memory_update_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}memory_update 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.
memory_update. It is categorised as a Write tool in the Rekal MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Rekal MCP server in PolicyLayer and add a rule for memory_update: 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 Rekal. Nothing to install.
memory_update 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 memory_update 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 memory_update. 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.
memory_update is provided by the Rekal MCP server (janbjorge/rekal). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Rekal, 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.
21 Rekal tools catalogued and risk-classified — across an index of 43,000+ MCP servers.