Searches stored memories by query text with filtering options for project, importance level, and result limits. Searches both title and content fields.
AI agents call recall_context to retrieve information from Memory Pickle MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and searches existing memory data with no side effects. It supports filtering but performs no writes, executions, or destructive operations. The blast radius of misuse is minimal - an agent could retrieve unintended context but cannot alter data or trigger external operations.
From the tool's definition Tool description states it "Searches stored memories by query text with filtering options" - this is a search/query operation that retrieves data without modifying it.
Documented attack patterns abuse exactly the kind of access recall_context gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Memory Pickle MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for recall_context:
{
"version": "1",
"default": "deny",
"tools": {
"recall_context": {}
}
}recall_context 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.
Searches stored memories by query text with filtering options for project, importance level, and result limits. Searches both title and content fields. It is categorised as a Read tool in the Memory Pickle MCP MCP Server, which means it retrieves data without modifying state.
Register the Memory Pickle MCP server in PolicyLayer and add a rule for recall_context: 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 Memory Pickle MCP. Nothing to install.
recall_context 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 recall_context 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 recall_context. 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.
recall_context is provided by the Memory Pickle MCP server (justar96/memory-pickle). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Memory Pickle MCP, 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.
13 Memory Pickle MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.