Store a new episodic memory/reflection for future learning.
AI agents use episodic_store to create or update resources in MidOS - MCP Community Library — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your MidOS - MCP Community Library environment.
The tool creates/writes new data (episodic memories or reflections) to a persistent store. This is a reversible write operation — it adds new records rather than deleting or overwriting existing ones. Misuse could allow an AI agent to pollute the knowledge base with false or misleading memories, hence medium severity.
From the tool's definition 'Store a new episodic memory/reflection for future learning'
Attacks that exploit this kind of access
Store a new episodic memory/reflection for future learning. It is categorised as a Write tool in the MidOS - MCP Community Library MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the MidOS - MCP Community Library MCP server in PolicyLayer and add a rule for episodic_store: 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 MidOS - MCP Community Library. Nothing to install.
episodic_store 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 episodic_store 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 episodic_store. 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.
episodic_store is provided by the MidOS - MCP Community Library MCP server (midos-mcp). 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 →