This record as markdown: /tools/heznpc-airmcp/memory-put.md
What memory_put does on AirMCP
AI agents use memory_put to create or update resources in AirMCP, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your AirMCP environment.
Why memory_put is rated Medium
This tool creates new or modifies existing memory/context entries. It is reversible (entries can be updated again or removed by other tools), so it does not qualify as Destructive. It does not execute code, trigger external operations, move money, or merely read data. Write is the appropriate category.
From the tool's definition Tool name is 'memory_put' and description states 'Insert or update a context-memory entry', which are direct write operations that create or modify data.
Attacks that exploit this kind of access
The rule that runs memory_put safely
PolicyLayer is an MCP gateway: it sits between your AI agents and AirMCP, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For memory_put, this is the rule to start with:
memory_put 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.
The button opens the PolicyLayer dashboard: create your workspace, connect AirMCP, apply this rule, and every memory_put call is checked against it from then on.
Questions about memory_put
Insert or update a context-memory entry. Use. It is categorised as a Write tool in the AirMCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Air MCP server in PolicyLayer and add a rule for memory_put: 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 AirMCP. Nothing to install.
memory_put 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_put 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_put. 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_put is provided by the Air MCP server (airmcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Air, and thousands of servers like it.
This server
Across the catalogue