AI agents use update_memory to create or update resources in SAM — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your SAM environment.
This tool creates or modifies data reversibly by updating memory entries. It does not delete data (which would be Destructive), execute external operations (Execute), or move money (Financial). The severity is medium because unauthorized memory updates could affect AI decision-making across platforms, but the impact is reversible and context-dependent on what memories are modified.
From the tool's definition Tool name 'update_memory' and description 'Update an existing memory' indicate modification of stored data.
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 SAM, 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 an existing memory. It is categorised as a Write tool in the SAM MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the SAM 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 SAM. 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 SAM MCP server (pigrieco/mcp-memory-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from SAM, 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.
37 SAM tools catalogued and risk-classified — across an index of 43,000+ MCP servers.