AI agents call cairntir_session_start to retrieve information from Cairntir without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool loads/retrieves context information (described as a '4-layer context') for a session, which is a read operation. It queries the SQLite database to fetch stored decisions and facts. No data is created, modified, or deleted. The 'amnesia killer' tagline reinforces that this is about retrieving previously stored information.
From the tool's definition 'Load the 4-layer context for a wing' — 'load' indicates retrieval of stored context data from the SQLite database
Attacks that exploit this kind of access
Load the 4-layer context for a wing (the amnesia killer). It is categorised as a Read tool in the Cairntir MCP Server, which means it retrieves data without modifying state.
Register the Cairntir MCP server in PolicyLayer and add a rule for cairntir_session_start: 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_session_start 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 cairntir_session_start 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_session_start. 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_session_start 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 →