AI agents use store_memory to create or update resources in ContextKeep — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your ContextKeep environment.
The name 'store_memory' strongly implies creating/writing a new memory entry to persistent storage. This is a Write operation — it creates data reversibly (a sibling tool 'delete_memory' exists, confirming deletion is possible). The description is empty, which lowers confidence slightly, but the name and server context make the Write classification highly plausible.
From the tool's definition Tool name 'store_memory' on a server described as providing persistent, searchable storage of project details, preferences, and snippets.
Documented attack patterns abuse exactly the kind of access store_memory gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and ContextKeep, and nothing reaches the server without passing your rules. This is the rule we recommend for store_memory:
{
"version": "1",
"default": "deny",
"tools": {
"store_memory": {
"limits": [
{
"counter": "store_memory_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}store_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.
Free to start. No card required.
store_memory. It is categorised as a Write tool in the ContextKeep MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the ContextKeep MCP server in PolicyLayer and add a rule for store_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 ContextKeep. Nothing to install.
store_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 store_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 store_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.
store_memory is provided by the ContextKeep MCP server (mordang7/contextkeep). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from ContextKeep, 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.
8 ContextKeep tools catalogued and risk-classified — across an index of 43,000+ MCP servers.