put_memory

SERVERAI Cortex Storage SOURCEhttps://memory.aic0rt3x.dev/mcp

Medium RISK CLASS

Category Write

Parameters 63 required

Recommended Rate-limitedsee the rule below

Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/dev-aic0rt3x-memory-mcp/put-memory.md

WHAT IT DOES

What put_memory does on AI Cortex Storage

AI agents use put_memory to create or update resources in AI Cortex Storage, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your AI Cortex Storage environment.

Parameter	Type	Required	Description
`key`	string	Yes	≤ 255 characters, no '/'
`tags`	array	—	Labels for searching and grouping. Duplicates are deduplicated automatically.
`months`	integer	—	How long to store this entry in months (default 1, minimum 1). Ignored on overwrite — existing expiry is scaled by the KB size ratio of old to new value.
`priority`	integer	—	Importance 1–10; higher = more important. Default 5. Used by top_memories to surface the most relevant context.
`namespace`	string	Yes	≤ 255 characters, no '/'
`value_json`	string	Yes	JSON-encoded value

Parameters from the server's own tool schema.

RISK

Why put_memory is rated Medium

This tool creates or modifies key-value data in persistent cloud storage. The operation is reversible (via delete_memory, which is available as a sibling tool), so it does not qualify as Destructive. There is no code execution, financial transaction, or data retrieval involved.

From the tool's definition Tool name is 'put_memory' and description states it will 'Store a value' with optional metadata. The description explicitly addresses the overwrite behavior ('On overwrite, the existing expiry is scaled...'), confirming this is a write operation that creates…

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs put_memory safely

PolicyLayer is an MCP gateway: it sits between your AI agents and AI Cortex Storage, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For put_memory, this is the rule to start with:

put_memory Rate-limited

put_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.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "put_memory": {
      "limits": [
        {
          "counter": "put_memory_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL → Instant setup, no code required.

The button opens the PolicyLayer dashboard: create your workspace, connect AI Cortex Storage, apply this rule, and every put_memory call is checked against it from then on.

FAQ

Questions about put_memory

What does the put_memory tool do? +

Store a value with optional tags, priority, and storage duration in months (default 1). value_json must be ≤ 1 MB. On overwrite, the existing expiry is scaled by the KB size ratio of old to new value. It is categorised as a Write tool in the AI Cortex Storage MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

What parameters does put_memory accept? +

put_memory accepts 6 parameters: key, tags, months, priority, namespace, value_json. Required: key, namespace, value_json. The full parameter table on this page comes from the server's own tool schema.

How do I enforce a policy on put_memory? +

Register the AI Cortex Storage MCP server in PolicyLayer and add a rule for put_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 AI Cortex Storage. Nothing to install.

What risk level is put_memory? +

put_memory is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit put_memory? +

Yes. Add a rate_limit block to the put_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.

How do I block put_memory completely? +

Set action: deny in the PolicyLayer policy for put_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.

What MCP server provides put_memory? +

put_memory is provided by the AI Cortex Storage MCP server (https://memory.aic0rt3x.dev/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on AI Cortex Storage, and thousands of servers like it.

This server

All 15 AI Cortex Storage tools →

Across the catalogue

team_manager_write_memory on Team Manager MCP → The MCP Attack Database →

Guides

Govern customer-ops agents →Argument validation →Scoped token →