Retrieves version history for Product Context or Active Context ONLY (not decisions, progress, or other entity types). Use to review past versions, audit when changes were made, or recover a previous state. Filter by timestamp range or specific version number. item_type must be
AI agents call get_item_history to retrieve information from Engrams without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries historical data without modifying, deleting, or executing operations. It performs read-only access to version history metadata. The term 'recover a previous state' refers to viewing/comparing versions, not actually reverting them (which would be Write/Execute). Severity is low because it only accesses historical snapshots with no side effects or system impact.
From the tool's definition Tool description states 'Retrieves version history' and explicitly limits scope to 'Product Context or Active Context ONLY'. Actions listed are 'review past versions, audit when changes were made, or recover a previous state'—all read-only query operations.
Documented attack patterns abuse exactly the kind of access get_item_history gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Engrams, and nothing reaches the server without passing your rules. This is the rule we recommend for get_item_history:
{
"version": "1",
"default": "deny",
"tools": {
"get_item_history": {}
}
}get_item_history 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.
Retrieves version history for Product Context or Active Context ONLY (not decisions, progress, or other entity types). Use to review past versions, audit when changes were made, or recover a previous state. Filter by timestamp range or specific version number. item_type must be. It is categorised as a Read tool in the Engrams MCP Server, which means it retrieves data without modifying state.
Register the Engrams MCP server in PolicyLayer and add a rule for get_item_history: 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 Engrams. Nothing to install.
get_item_history 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 get_item_history 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 get_item_history. 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.
get_item_history is provided by the Engrams MCP server (stevebrownlee/engrams). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Engrams, 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.
42 Engrams tools catalogued and risk-classified — across an index of 43,000+ MCP servers.