Retrieve a memory by its key. Args: key: The unique identifier of the memory.
AI agents call retrieve_memory to retrieve information from ContextKeep without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a simple lookup/retrieval operation on stored memories. It queries data by a unique identifier and returns information without modifying, deleting, or executing any operations. The blast radius of misuse is minimal—an AI agent could only access memories it is given keys for, which is a read-only information disclosure risk rather than a destructive or operational one.
From the tool's definition Tool name 'retrieve_memory' and description 'Retrieve a memory by its key' indicates a retrieval operation with no side effects.
Documented attack patterns abuse exactly the kind of access retrieve_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 retrieve_memory:
{
"version": "1",
"default": "deny",
"tools": {
"retrieve_memory": {}
}
}retrieve_memory is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Retrieve a memory by its key. Args: key: The unique identifier of the memory. It is categorised as a Read tool in the ContextKeep MCP Server, which means it retrieves data without modifying state.
Register the ContextKeep MCP server in PolicyLayer and add a rule for retrieve_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.
retrieve_memory is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the retrieve_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 retrieve_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.
retrieve_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.