Request an API key for a site you are running on (challenge-response). This starts a two-step verification flow: 1. A claim token is written to your container at ~/.borealhost/.claim_token (mode 600, owner admin — only readable if you're on the container) 2. Read that file and call claim_api_key(...
Risk signalsAdmin/system-level operation
Part of the BorealHost server.
Free to start. No card required.
AI agents may call request_api_key to permanently remove or destroy resources in BorealHost. Without a policy, an autonomous agent could delete critical data in a loop with no way to undo the damage. PolicyLayer blocks destructive tools by default and requires explicit human approval before enabling them.
Without a policy, an AI agent could call request_api_key in a loop, permanently destroying resources in BorealHost. There is no undo for destructive operations. PolicyLayer blocks this tool by default and only allows it when a human explicitly approves the action.
Destructive tools permanently remove data. Block by default. Only enable with explicit approval workflows.
{
"version": "1",
"default": "deny",
"hide": [
"request_api_key"
]
} See the full BorealHost policy for all 95 tools.
These attack patterns abuse exactly the kind of access request_api_key gives an agent. Each links to the full case and the policy that stops it:
Other destructive tools across the catalogue. The same approach applies to each: deny by default, or require human approval.
Request an API key for a site you are running on (challenge-response). This starts a two-step verification flow: 1. A claim token is written to your container at ~/.borealhost/.claim_token (mode 600, owner admin — only readable if you're on the container) 2. Read that file and call claim_api_key(token) within 1 hour This proves you have access to the container without storing any secrets on disk permanently. The claim token is single-use and ephemeral. No authentication needed — the proof is reading the file from the container. Args: site_slug: The site identifier (your BorealHost site slug) Returns: {"status": "pending", "site_slug": "my-site", "expires_in_seconds": 3600, "claim_path": "~/.borealhost/.claim_token", "instructions": "Read the claim token and call claim_api_key()..."} Errors: VALIDATION_ERROR: Unknown site slug or no active subscription RATE_LIMITED: Too many pending claim tokens. It is categorised as a Destructive tool in the BorealHost MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the BorealHost MCP server in PolicyLayer and add a rule for request_api_key: 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 BorealHost. Nothing to install.
request_api_key is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the request_api_key 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 request_api_key. 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.
request_api_key is provided by the BorealHost MCP server (pypi:borealhost-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 95 BorealHost tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
4,600+ MCP servers and 31,000+ tools scanned and risk-classified.