Get changes to context items since a specific point in time (timestamp, checkpoint, or relative time)
AI agents call context_diff to retrieve information from MCP Memory Keeper without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
context_diff performs a comparison and retrieval of historical context changes. It queries existing data to show what has changed since a specified point, which is a classic read operation with no side effects, modifications, or destructive actions. No data is created, modified, deleted, or executed.
From the tool's definition Tool retrieves and queries changes to context items ('Get changes to context items') without modifying or deleting data. The verb 'Get' and the read-only nature of diffing historical changes indicate a retrieval operation.
Documented attack patterns abuse exactly the kind of access context_diff gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and MCP Memory Keeper, and nothing reaches the server without passing your rules. This is the rule we recommend for context_diff:
{
"version": "1",
"default": "deny",
"tools": {
"context_diff": {}
}
} context_diff 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.
Get changes to context items since a specific point in time (timestamp, checkpoint, or relative time). It is categorised as a Read tool in the MCP Memory Keeper MCP Server, which means it retrieves data without modifying state.
Register the MCP Memory Keeper MCP server in PolicyLayer and add a rule for context_diff: 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 MCP Memory Keeper. Nothing to install.
context_diff 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 context_diff 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 context_diff. 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.
context_diff is provided by the MCP Memory Keeper MCP server (mkreyman/mcp-memory-keeper). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from MCP Memory Keeper, 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.
40 MCP Memory Keeper tools catalogued and risk-classified — across an index of 43,000+ MCP servers.