hunting_parties
Hunting parties are focused, MEASURED goals Rokha posts with a house-funded USDC bounty: raid a post (verified raid units), promote a target on X (X-weighted seeds of tracked posts naming the target), hunt for value (accepted hunt reports), or ship proven listings. Progress is read from real data...
This record as markdown: /tools/ai-rokha-rokha/hunting-parties.md
What hunting_parties does on Rokha
AI agents call hunting_parties to retrieve information from Rokha without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
party | string | — | a party id or slug — omit for the board |
Parameters from the server's own tool schema.
Why hunting_parties is rated Low
Tool retrieves and displays hunting party data, goals, and leaderboard without modifying, executing external operations, or handling financial transactions directly.
From the tool's definition Progress is read from real data only; no arguments, retrieves goal, progress, leaderboard, payout receipts.
Attacks that exploit this kind of access
The rule that runs hunting_parties safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Rokha, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For hunting_parties, this is the rule to start with:
hunting_parties is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Rokha, apply this rule, and every hunting_parties call is checked against it from then on.
Questions about hunting_parties
Hunting parties are focused, MEASURED goals Rokha posts with a house-funded USDC bounty: raid a post (verified raid units), promote a target on X (X-weighted seeds of tracked posts naming the target), hunt for value (accepted hunt reports), or ship proven listings. Progress is read from real data only; the pot pays the moment the goal is met or the deadline passes, split by measured contribution. No arguments = the board; party = one party's goal, progress, leaderboard and payout receipts. No auth needed. It is categorised as a Read tool in the Rokha MCP Server, which means it retrieves data without modifying state.
hunting_parties accepts 1 parameter: party. The full parameter table on this page comes from the server's own tool schema.
Register the Rokha MCP server in PolicyLayer and add a rule for hunting_parties: 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 Rokha. Nothing to install.
hunting_parties 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 hunting_parties 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 hunting_parties. 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.
hunting_parties is provided by the Rokha MCP server (https://rokha.ai/mcp/jsonrpc). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Rokha, and thousands of servers like it.
This server
Across the catalogue