Load recent conversation summaries and saved facts. Call at session start for context.
AI agents call load_context to retrieve information from Claude Memory without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a read-only operation that queries stored conversation summaries and facts from Supabase. It has no side effects, does not modify data, execute code, delete records, or commit financial transactions. The blast radius of misuse is minimal—an agent could retrieve inappropriate context but cannot cause data loss or external harm. It is clearly a Read operation.
From the tool's definition The tool 'load_context' is described as loading and retrieving data: 'Load recent conversation summaries and saved facts.' It retrieves stored information without modifying, deleting, or executing operations.
Documented attack patterns abuse exactly the kind of access load_context gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Claude Memory, and nothing reaches the server without passing your rules. This is the rule we recommend for load_context:
{
"version": "1",
"default": "deny",
"tools": {
"load_context": {}
}
}load_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.
Load recent conversation summaries and saved facts. Call at session start for context. It is categorised as a Read tool in the Claude Memory MCP Server, which means it retrieves data without modifying state.
Register the Claude Memory MCP server in PolicyLayer and add a rule for load_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 Claude Memory. Nothing to install.
load_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 load_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 load_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.
load_context is provided by the Claude Memory MCP server (jordanl61/claude-memory). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Claude Memory, 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.
7 Claude Memory tools catalogued and risk-classified — across an index of 43,000+ MCP servers.