Store or update a state entry in memory. If an entry with the same namespace+key exists, it will be overwritten. Use this for mutable facts and non-tracked state. For
AI agents use memory_write to create or update resources in Munin Memory — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Munin Memory environment.
memory_write performs reversible creation and modification of data stored in a SQLite database. It does not execute code, delete data irreversibly, move money, or read without side effects. The severity is medium because misuse could corrupt application state or context, but the effects are confined to the memory system and are theoretically reversible (via memory_delete or subsequent writes).
From the tool's definition Tool description states 'Store or update a state entry in memory' and 'If an entry with the same namespace+key exists, it will be overwritten.' These are classic write operations that create or modify data reversibly.
Attacks that exploit this kind of access
Store or update a state entry in memory. If an entry with the same namespace+key exists, it will be overwritten. Use this for mutable facts and non-tracked state. For. It is categorised as a Write tool in the Munin Memory MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Munin Memory MCP server in PolicyLayer and add a rule for memory_write: 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_write 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 memory_write 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_write. 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_write 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 →