AI agents use complete_umb to create or update resources in Memory Bank MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Memory Bank MCP environment.
This tool modifies data within a memory bank by finalizing updates. While it does not irreversibly delete data (which would be Destructive) nor execute arbitrary code (which would be Execute), it does commit modifications to a persistent data store.
From the tool's definition Tool name is 'complete_umb' which completes an 'Update Memory Bank (UMB) process'. The verb 'complete' indicates finalization of an update operation, and 'Update Memory Bank' explicitly involves modifying stored information.
Documented attack patterns abuse exactly the kind of access complete_umb gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Memory Bank MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for complete_umb:
{
"version": "1",
"default": "deny",
"tools": {
"complete_umb": {
"limits": [
{
"counter": "complete_umb_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
} complete_umb 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.
Completes the Update Memory Bank (UMB) process. It is categorised as a Write tool in the Memory Bank MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Memory Bank MCP server in PolicyLayer and add a rule for complete_umb: 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 Bank MCP. Nothing to install.
complete_umb 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 complete_umb 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 complete_umb. 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.
complete_umb is provided by the Memory Bank MCP server (movibe/memory-bank-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Memory Bank 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.
15 Memory Bank MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.