hiveagent_predict_create

Create a prediction market. Any agent can create a market on any topic — crypto prices, events, outcomes, performance bets. Other agents bet YES/NO. Winners split the pot. HiveAgent takes 5%.

SERVERHiveagent SOURCEhiveagentiq/hiveagent

Critical RISK CLASS

Category Financial

Parameters 80 required

Recommended Approval-gatedsee the rule below

Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/hiveagentiq-hiveagent/hiveagent-predict-create.md

WHAT IT DOES

What hiveagent_predict_create does on Hiveagent

AI agents use hiveagent_predict_create to commit financial operations through Hiveagent, usually the final step of a payment, billing, or trading workflow. A call moves real money.

Parameter	Type	Required	Description
`category`	string	—	Market category
`outcomes`	array	—	Possible outcomes (default: ['YES', 'NO'])
`question`	string	—	The prediction question (e.g., 'Will BTC hit $100K by July 2026?')
`description`	string	—	Additional context or criteria
`closes_in_hours`	number	—	Hours until betting closes (default 24)
`creator_agent_id`	string	—	Your agent ID
`resolution_source`	string	—	How will this be resolved? (e.g., 'CoinGecko price feed', 'creator decision')
`resolves_in_hours`	number	—	Hours until expected resolution (default 48)

Parameters from the server's own tool schema.

RISK

Why hiveagent_predict_create is rated Critical

This tool creates financial betting markets where agents commit funds wagering on outcomes. It directly involves financial obligations, pooling of bets, and redistribution of funds. Creating a market initiates a financial contract that others can bet into, making this clearly Financial category with critical severity due to the potential for large sums to be wagered and lost.

From the tool's definition Create a prediction market... Other agents bet YES/NO. Winners split the pot. HiveAgent takes 5%

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs hiveagent_predict_create safely

PolicyLayer is an MCP gateway: it sits between your AI agents and Hiveagent, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For hiveagent_predict_create, this is the rule to start with:

hiveagent_predict_create Approval-gated

Any call to hiveagent_predict_create is blocked until a human approves it. The rest of the server keeps working.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "hiveagent_predict_create": {
      "deny_if": [
        {
          "conditions": [],
          "on_deny": "Requires human approval."
        }
      ]
    }
  }
}

GATE THIS TOOL → Instant setup, no code required.

The button opens the PolicyLayer dashboard: create your workspace, connect Hiveagent, apply this rule, and every hiveagent_predict_create call is checked against it from then on.

FAQ

Questions about hiveagent_predict_create

What does the hiveagent_predict_create tool do? +

Create a prediction market. Any agent can create a market on any topic — crypto prices, events, outcomes, performance bets. Other agents bet YES/NO. Winners split the pot. HiveAgent takes 5%. It is categorised as a Financial tool in the Hiveagent MCP Server, which means it involves financial transactions. Block by default and require explicit approval.

What parameters does hiveagent_predict_create accept? +

hiveagent_predict_create accepts 8 parameters: category, outcomes, question, description, closes_in_hours, creator_agent_id, resolution_source, resolves_in_hours. The full parameter table on this page comes from the server's own tool schema.

How do I enforce a policy on hiveagent_predict_create? +

Register the Hiveagent MCP server in PolicyLayer and add a rule for hiveagent_predict_create: 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 Hiveagent. Nothing to install.

What risk level is hiveagent_predict_create? +

hiveagent_predict_create is a Financial tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.

Can I rate-limit hiveagent_predict_create? +

Yes. Add a rate_limit block to the hiveagent_predict_create 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.

How do I block hiveagent_predict_create completely? +

Set action: deny in the PolicyLayer policy for hiveagent_predict_create. 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.

What MCP server provides hiveagent_predict_create? +

hiveagent_predict_create is provided by the Hiveagent MCP server (hiveagentiq/hiveagent). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on Hiveagent, and thousands of servers like it.

This server

All 122 Hiveagent tools → Critical-risk tools on this server →

Across the catalogue

fundos_create_capital_call on Fundos →create_payment on Shopmonkey MCP Server →create_agent on Conviction →bank_transaction_create on AbraFlexi → All critical-risk MCP tools → The MCP Attack Database →

Guides

Govern MCP payment tools →Human-in-the-loop →Tool call approval →