AI agents use cairntir_remember to create or update resources in Cairntir — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Cairntir environment.
This tool writes new memory entries into the local SQLite database. It creates data persistently but is reversible (memories can presumably be deleted or overwritten). The blast radius is medium because a misused AI agent could pollute the memory store with false or misleading information that persists across sessions, affecting future context-aware conversations.
From the tool's definition "Store a verbatim memory drawer" — creates/writes data to the SQLite memory system
Attacks that exploit this kind of access
Store a verbatim memory drawer in a wing/room. It is categorised as a Write tool in the Cairntir MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Cairntir MCP server in PolicyLayer and add a rule for cairntir_remember: 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 Cairntir. Nothing to install.
cairntir_remember 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 cairntir_remember 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 cairntir_remember. 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.
cairntir_remember is provided by the Cairntir MCP server (pnmcguire480/cairntir). 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 →