log_episode
Log a structured episodic event to the episodic memory store.
This record as markdown: /tools/ashlesh-t-cognirepo/log-episode.md
What log_episode does on CogniRepo
AI agents use log_episode to create or update resources in CogniRepo, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your CogniRepo environment.
Why log_episode is rated Medium
This tool writes/creates new records in the episodic memory store. It is a write operation (logging/creating data) with no indication of deletion or irreversibility. Misuse could pollute the memory store with false or misleading episodic data, affecting future AI context and decisions, hence medium severity.
From the tool's definition "Log a structured episodic event to the episodic memory store"
Attacks that exploit this kind of access
The rule that runs log_episode safely
PolicyLayer is an MCP gateway: it sits between your AI agents and CogniRepo, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For log_episode, this is the rule to start with:
log_episode 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.
The button opens the PolicyLayer dashboard: create your workspace, connect CogniRepo, apply this rule, and every log_episode call is checked against it from then on.
Questions about log_episode
Log a structured episodic event to the episodic memory store. It is categorised as a Write tool in the CogniRepo MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the CogniRepo MCP server in PolicyLayer and add a rule for log_episode: 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 CogniRepo. Nothing to install.
log_episode 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 log_episode 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 log_episode. 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.
log_episode is provided by the CogniRepo MCP server (pypi:cognirepo). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on CogniRepo, and thousands of servers like it.
This server
Across the catalogue