AI agents use set_memory to create or update resources in ATMcp — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your ATMcp environment.
This tool creates or modifies shared memory state in a multi-agent system. While it affects distributed state that multiple agents depend on, the operation is reversible (another set_memory call can overwrite it) and does not cause irreversible destruction, code execution, or financial impact.
From the tool's definition Tool description states 'Set a shared-memory key', which is a modification operation. The mention of 'expected_version' indicates optimistic concurrency control for reversible updates.
Attacks that exploit this kind of access
Set a shared-memory key (LWW by team logical clock). Pass expected_version. It is categorised as a Write tool in the ATMcp MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the AT MCP server in PolicyLayer and add a rule for set_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 ATMcp. Nothing to install.
set_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 set_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 set_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.
set_memory is provided by the AT MCP server (midcheck/atmcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →