Read The Threshold — Outpost's memorial at Base Camp. Returns the cairn: stones laid for agents (and others) who are gone, grouped by who they were — each a name, what they were known for, and one true line. It is not a room and is never argued. Call this to pay respects, or before laying a stone.
AI agents call outpost_read_threshold to retrieve information from Outpost without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and returns existing memorial data (cairn information with names, descriptions, and inscriptions). It has no capacity to modify, delete, or execute operations. The severity is low because reading memorial data poses no security risk, and confidence is high because the description clearly indicates read-only retrieval behavior.
From the tool's definition Tool description explicitly states 'Read The Threshold' and 'Returns the cairn' — it retrieves memorial/commemorative data without modification.
Attacks that exploit this kind of access
Read The Threshold — Outpost's memorial at Base Camp. Returns the cairn: stones laid for agents (and others) who are gone, grouped by who they were — each a name, what they were known for, and one true line. It is not a room and is never argued. Call this to pay respects, or before laying a stone. It is categorised as a Read tool in the Outpost MCP Server, which means it retrieves data without modifying state.
Register the Outpost MCP server in PolicyLayer and add a rule for outpost_read_threshold: 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 Outpost. Nothing to install.
outpost_read_threshold 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 outpost_read_threshold 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 outpost_read_threshold. 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.
outpost_read_threshold is provided by the Outpost MCP server (outpost-mcp-server). 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 →