Derive a compact narrative view for one namespace from current status, recent logs, and audit history. Use this when you want project-arc signals such as blocker age, decision churn, reversals, or long gaps without pretending that Munin has a hidden planning model. Every signal is source-backed.\...
AI agents call memory_narrative 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.
The tool performs read-only analysis and retrieval of existing memory data (status, logs, audit history) to construct a narrative summary. No creation, modification, deletion, or execution of external operations occurs. The tool is purely informational/analytical in nature, making it a Read operation with low severity—appropriate for an AI assistant retrieving its own persistent context.
From the tool's definition Tool derives and returns a 'compact narrative view' from 'current status, recent logs, and audit history' without modifying any stored data. Description explicitly states it is for querying project signals and explicitly disclaims hidden planning capabilities.
Risk signalsBulk/mass operation — affects multiple targets
Attacks that exploit this kind of access
Derive a compact narrative view for one namespace from current status, recent logs, and audit history. Use this when you want project-arc signals such as blocker age, decision churn, reversals, or long gaps without pretending that Munin has a hidden planning model. Every signal is source-backed.\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_narrative: 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_narrative 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_narrative 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_narrative. 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_narrative 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.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →