Logs multiple items of the SAME type in a single call, reducing round-trips. Supported item_types:
AI agents use batch_log_items to create or update resources in Engrams — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Engrams environment.
The tool writes multiple items to the persistent memory store in a single call. This is a bulk write operation — creating new records. No indication of deletion or irreversibility, so Write is appropriate. Medium severity because bulk operations can pollute or overwrite project memory context at scale, but effects appear reversible (sibling tool 'delete_item' exists).
From the tool's definition 'Logs multiple items' and 'reducing round-trips' indicate bulk creation/writing of data entries
Documented attack patterns abuse exactly the kind of access batch_log_items 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 batch_log_items:
{
"version": "1",
"default": "deny",
"tools": {
"batch_log_items": {
"limits": [
{
"counter": "batch_log_items_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}batch_log_items stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Logs multiple items of the SAME type in a single call, reducing round-trips. Supported item_types:. It is categorised as a Write tool in the Engrams MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Engrams MCP server in PolicyLayer and add a rule for batch_log_items: 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.
batch_log_items is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the batch_log_items 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 batch_log_items. 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.
batch_log_items 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.