Returns a digest of recently created or updated items across all entity types, ideal for session start catch-up. Specify a time window via hours_ago (e.g., 24) OR since_timestamp (not both). Limits results per entity type via limit_per_type (default 5). Use at session start to understand what cha...
AI agents call get_recent_activity_summary 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.
get_recent_activity_summary is a read-only query operation that retrieves a summary of recent changes across entity types within a specified time window. It has no side effects and is explicitly documented as a retrieval mechanism ('Returns a digest', 'for session start catch-up'). The lower severity reflects that misuse primarily affects information disclosure rather than system integrity or data destruction.
From the tool's definition Tool 'Returns a digest of recently created or updated items' and 'NOT for searching — use search tools for that' — the tool retrieves and queries historical activity data without modifying, deleting, or executing external operations.
Documented attack patterns abuse exactly the kind of access get_recent_activity_summary 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_recent_activity_summary:
{
"version": "1",
"default": "deny",
"tools": {
"get_recent_activity_summary": {}
}
}get_recent_activity_summary 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.
Returns a digest of recently created or updated items across all entity types, ideal for session start catch-up. Specify a time window via hours_ago (e.g., 24) OR since_timestamp (not both). Limits results per entity type via limit_per_type (default 5). Use at session start to understand what changed since last interaction. NOT for searching — use search tools for that. Returns: {decisions: [...], progress: [...], patterns: [...], custom_data: [...], summary_period, ...}. 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_recent_activity_summary: 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_recent_activity_summary 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_recent_activity_summary 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_recent_activity_summary. 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_recent_activity_summary 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.