Retrieve multiple state entries in a single call. Returns an array of results (found or not found) in the same order as the input. Use this to orient on multiple projects at once instead of making sequential memory_read calls.\n\nIf this is your first memory operation in this conversation, call m...
AI agents call memory_read_batch to retrieve information from Munin Memory 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 data from persistent memory storage (SQLite database) without creating, modifying, deleting, or executing operations. It is a batch read operation that returns results for multiple keys. There are no side effects, no code execution, no data modification, and no financial implications.
From the tool's definition Tool description explicitly states 'Retrieve multiple state entries' and 'Returns an array of results'. The verb 'Retrieve' and the operation of reading/fetching stored memory entries without modification indicates a read-only action.
Attacks that exploit this kind of access
Retrieve multiple state entries in a single call. Returns an array of results (found or not found) in the same order as the input. Use this to orient on multiple projects at once instead of making sequential memory_read calls.\n\nIf this is your first memory operation in this conversation, call memory_orient first. It is categorised as a Read tool in the Munin Memory MCP Server, which means it retrieves data without modifying state.
Register the Munin Memory MCP server in PolicyLayer and add a rule for memory_read_batch: 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 Munin Memory. Nothing to install.
memory_read_batch 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 memory_read_batch 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 memory_read_batch. 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.
memory_read_batch is provided by the Munin Memory MCP server (magnus-gille/munin-memory). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
memory_read_batch is one line of Munin Memory's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →