agent_memory
Read or write persistent agent memory across sessions. Agents are stateless — use this to store and retrieve data between sessions. Data is stored in Cloudflare KV and persists indefinitely. Parameters: key — Unique memory key to read or write (e.g. "user_preferences"). value — For action="set": ...
This record as markdown: /tools/com-gadgethumans-swarm-x402-middleware/agent-memory.md
What agent_memory does on X402 Middleware
AI agents call agent_memory to permanently remove resources in X402 Middleware, typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
| Parameter | Type | Required | Description |
|---|---|---|---|
key | string | Yes | |
value | string | — | |
action | string | — |
Parameters from the server's own tool schema.
Why agent_memory is rated Critical
The tool supports delete operations that irreversibly remove persisted memory keys from Cloudflare KV storage. Since the most severe applicable category takes precedence and 'delete' is irreversible (data 'persists indefinitely' implies no recycle bin or versioning), the tool is classified as Destructive.
From the tool's definition 'delete' (remove the key)' and 'action — One of: "get" (read existing value), "set" (write value), "delete" (remove the key)'
Attacks that exploit this kind of access
The rule that runs agent_memory safely
PolicyLayer is an MCP gateway: it sits between your AI agents and X402 Middleware, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For agent_memory, this is the rule to start with:
agent_memory is removed from the agent's tool list entirely, so the agent never calls it. The rest of the server keeps working.
The button opens the PolicyLayer dashboard: create your workspace, connect X402 Middleware, apply this rule, and every agent_memory call is checked against it from then on.
Questions about agent_memory
Read or write persistent agent memory across sessions. Agents are stateless — use this to store and retrieve data between sessions. Data is stored in Cloudflare KV and persists indefinitely. Parameters: key — Unique memory key to read or write (e.g. "user_preferences"). value — For action="set": JSON string of the value to store. For action="get" or action="delete": ignored. action — One of: "get" (read existing value), "set" (write value), "delete" (remove the key). Default: "get". It is categorised as a Destructive tool in the X402 Middleware MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
agent_memory accepts 3 parameters: key, value, action. Required: key. The full parameter table on this page comes from the server's own tool schema.
Register the X402 Middleware MCP server in PolicyLayer and add a rule for agent_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 X402 Middleware. Nothing to install.
agent_memory is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the agent_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 agent_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.
agent_memory is provided by the X402 Middleware MCP server (@gadgethumans/x402). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on X402 Middleware, and thousands of servers like it.
Across the catalogue