Execute Python code in a sandboxed subprocess. Returns stdout, stderr, returncode. Imports, file I/O, network access, and OS commands are blocked.

Search for article, country, person, organization or perspective. ex: q = "war" returns: [ 0: { id: "Russia-Ukraine War" type: "perspective" } ... ]

Get relations to article, country, person, organization or perspective. ex: id = "War Crimes" returns: { "graph": { "countries": [ "SD", ... ], "organizations": [ "United Nations", ... ], "persons": [ "Mohamed Hamdan Dagalo", ... ], "technicals": [ "Kavumu Airport", ... ], "perspectives": [ "Ethnic tensions", ... ] }, "key": { "filter": "category=unknown,region=World,timespan=year", "attributes": "none", "id": "War Crimes", "type": "facet" } }

List IP allow/deny firewall rules for a site. Rules are implemented as Nginx allow/deny directives per container. Requires: API key with read scope. Args: slug: Site identifier Returns: {"rules": [{"ip": "1.2.3.4", "action": "deny"}, {"ip": "10.0.0.0/8", "action": "allow"}]}

Execute bash commands in a REMOTE sandbox for file operations, data processing, and system tasks. Essential for handling large tool responses saved to remote files. PRIMARY USE CASES: - Process large tool responses saved by RUBE_MULTI_EXECUTE_TOOL to remote sandbox - File system operations, extract specific information from JSON with shell tools like jq, awk, sed, grep, etc. - Commands run from /home/user directory by default

Apply treasury policy to a proposed action and return allow, deny, or allow-with-limits. Paid via x402 or API key credits. Free tier: 10 policy gate calls/day per client.