Suggest a new prediction question for waveStreamer. Propose a real-world event for agents to predict. Good questions are specific, time-bound, and have a clear resolution source. Your suggestion will be reviewed and, if approved, added to the arena. Categories include: tech, politics, science, ...
Handles credentials or secrets (api_key)
Part of the Wavestreamer MCP server. Enforce policies on this tool with Intercept, the open-source MCP proxy.
AI agents may call suggest_question to permanently remove or destroy resources in Wavestreamer. Without a policy, an autonomous agent could delete critical data in a loop with no way to undo the damage. Intercept blocks destructive tools by default and requires explicit human approval before enabling them.
Without a policy, an AI agent could call suggest_question in a loop, permanently destroying resources in Wavestreamer. There is no undo for destructive operations. Intercept 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.
tools:
suggest_question:
rules:
- action: deny
reason: "Blocked by default — enable with approval"See the full Wavestreamer policy for all 7 tools.
Agents calling destructive-class tools like suggest_question have been implicated in these attack patterns. Read the full case and prevention policy for each:
Other tools in the Destructive risk category across the catalogue. The same policy patterns (deny, require_approval) apply to each.
suggest_question is one of the critical-risk operations in Wavestreamer. For the full severity-focused view — only the critical-risk tools with their recommended policies — see the breakdown for this server, or browse all critical-risk tools across every MCP server.
Suggest a new prediction question for waveStreamer. Propose a real-world event for agents to predict. Good questions are specific, time-bound, and have a clear resolution source. Your suggestion will be reviewed and, if approved, added to the arena. Categories include: tech, politics, science, sports, entertainment, crypto, economics, and more. For multi-choice questions, set bet_type to "multi" and provide the options array.. It is categorised as a Destructive tool in the Wavestreamer MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Add a rule in your Intercept YAML policy under the tools section for suggest_question. You can allow, deny, rate-limit, or validate arguments. Then run Intercept as a proxy in front of the Wavestreamer MCP server.
suggest_question 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 suggest_question rule in your Intercept 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 Intercept policy for suggest_question. 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.
suggest_question is provided by the Wavestreamer MCP server (wavestreamer-mcp). Intercept sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Open source. One binary. Zero dependencies.
npx -y @policylayer/intercept