Use this when you need to quickly verify whether a factual claim is true or false. Simpler and cheaper than full event resolution -- designed for fast claim checking without structured market settlement. 1. claim: the original claim being verified 2. verdict: "true", "false", or "unverifiable" if...
Part of the Event Resolver API server.
Free to start. No card required.
AI agents call event_verify_claim to retrieve information from Event Resolver API without modifying any data. This is common in research, monitoring, and reporting workflows where the agent needs context before taking action. Because read operations don't change state, they are generally safe to allow without restrictions -- but you may still want rate limits to control API costs.
Even though event_verify_claim only reads data, uncontrolled read access can leak sensitive information or rack up API costs. An agent caught in a retry loop could make thousands of calls per minute. A rate limit gives you a safety net without blocking legitimate use.
Read-only tools are safe to allow by default. No rate limit needed unless you want to control costs.
{
"version": "1",
"default": "deny",
"tools": {
"event_verify_claim": {}
}
}See the full Event Resolver API policy for all 3 tools.
These attack patterns abuse exactly the kind of access event_verify_claim gives an agent. Each links to the full case and the policy that stops it:
Other read tools across the catalogue. The same approach applies to each: allow, with a rate cap to control cost.
Use this when you need to quickly verify whether a factual claim is true or false. Simpler and cheaper than full event resolution -- designed for fast claim checking without structured market settlement. 1. claim: the original claim being verified 2. verdict: "true", "false", or "unverifiable" if insufficient data 3. confidence: 0-100 score indicating certainty of the verdict 4. evidence: array of strings summarizing supporting or contradicting evidence found Example output: { "claim": "Tesla stock is above $300", "verdict": "true", "confidence": 90, "evidence": ["CoinGecko/financial APIs confirm current price above threshold", "Multiple news sources corroborate"] } Use this for quick fact-checking before making decisions, verifying claims in conversation, or pre-screening questions before full resolution. Faster and cheaper than event_resolve_outcome for simple true/false checks. Do NOT use for prediction market odds -- use prediction_list_markets instead. Do NOT use for full fact checking with sources -- use research_check_fact instead. Do NOT use for stock prices -- use stock_get_quote instead. Do NOT use for crypto prices only -- use token_get_price instead.. It is categorised as a Read tool in the Event Resolver API MCP Server, which means it retrieves data without modifying state.
Register the Event Resolver API MCP server in PolicyLayer and add a rule for event_verify_claim: 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 Event Resolver API. Nothing to install.
event_verify_claim 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 event_verify_claim 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 event_verify_claim. 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.
event_verify_claim is provided by the Event Resolver API MCP server (https://event-resolver.api.klymax402.com/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 3 Event Resolver API 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.