Low Risk

verify_claim

Verify factual claims about current DeFi market conditions. Supports two modes: - Single claim: provide claim_type, value, operator (and protocol/chain/asset as needed). Returns one verification result. - Batch mode: provide a JSON-encoded array in 'claims'. Each element has the same fields (clai...

Risk signalsHandles credentials or secrets (api_key)

Part of the PreFlyte — DeFi Financial Intelligence for AI Agents server.

verify_claim is read-only, but an agent in a loop can still rack up calls and cost. PolicyLayer caps every call before it runs. Live in minutes.

SECURE PREFLYTE — DEFI FINANCIAL INTELLIGENCE FOR AI AGENTS →

Free to start. No card required.

AI agents call verify_claim to retrieve information from PreFlyte — DeFi Financial Intelligence for AI Agents 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 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.

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "verify_claim": {}
  }
}

See the full PreFlyte — DeFi Financial Intelligence for AI Agents policy for all 9 tools.

Get this rule live on your own PreFlyte — DeFi Financial Intelligence for AI Agents server in minutes. PolicyLayer enforces it on every call, before it runs.

ENFORCE ON MY PREFLYTE — DEFI FINANCIAL INTELLIGENCE FOR AI AGENTS →

View all 9 tools →

These attack patterns abuse exactly the kind of access verify_claim gives an agent. Each links to the full case and the policy that stops it:

Browse the full MCP Attack Database →

Every attack above starts with a tool call. PolicyLayer checks each one against your policy first, so verify_claim only ever does what you allow.

SECURE PREFLYTE — DEFI FINANCIAL INTELLIGENCE FOR AI AGENTS →

Other read tools across the catalogue. The same approach applies to each: allow, with a rate cap to control cost.

What does the verify_claim tool do? +

Verify factual claims about current DeFi market conditions. Supports two modes: - Single claim: provide claim_type, value, operator (and protocol/chain/asset as needed). Returns one verification result. - Batch mode: provide a JSON-encoded array in 'claims'. Each element has the same fields (claim_type, value, operator, protocol, chain, asset). Returns all results in one response. If 'claims' is provided, single-claim parameters are ignored. Args: api_key: Your PreFlyte API key (required). claim_type: What you're checking. One of: "supply_rate" — current supply APY (%) "borrow_rate" — current borrow APY (%) "price" — current token price (USD) "gas" — current base fee (gwei) "utilization" — current pool utilization (%) value: The numeric value you believe to be true. operator: Comparison operator. One of: "above" — actual must be >= value "below" — actual must be <= value "around" — actual must be within 10% of value protocol: Required for supply_rate, borrow_rate, utilization. Use "aave-v3" or "compound-v3". chain: Chain name — "ethereum" or "arbitrum". Default "ethereum". asset: Required for supply_rate, borrow_rate, price, utilization. Use token symbol like "USDC", "WETH", etc. claims: JSON-encoded array of claim objects for batch verification. Each object contains: claim_type, value, operator, and optionally protocol, chain, asset. When provided, single-claim params are ignored. Returns: Single mode: Dictionary with status (TRUE/FALSE), actual_value, claimed_value, delta, delta_pct, data_timestamp, and summary. Batch mode: Dictionary with 'mode', 'results' array, 'summary' counts, and 'verified_at' timestamp. Examples: Single: verify_claim(api_key="...", claim_type="supply_rate", value=5.0, operator="above", protocol="aave-v3", asset="USDC") Batch: verify_claim(api_key="...", claims='[{"claim_type": "supply_rate", ...}, ...]'). It is categorised as a Read tool in the PreFlyte — DeFi Financial Intelligence for AI Agents MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on verify_claim? +

Register the PreFlyte — DeFi Financial Intelligence for AI Agents MCP server in PolicyLayer and add a rule for 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 PreFlyte — DeFi Financial Intelligence for AI Agents. Nothing to install.

What risk level is verify_claim? +

verify_claim is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit verify_claim? +

Yes. Add a rate_limit block to the 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.

How do I block verify_claim completely? +

Set action: deny in the PolicyLayer policy for 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.

What MCP server provides verify_claim? +

verify_claim is provided by the PreFlyte — DeFi Financial Intelligence for AI Agents MCP server (https://mcp.preflyte.xyz/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every PreFlyte — DeFi Financial Intelligence for AI Agents tool call.

Deterministic rules across all 9 PreFlyte — DeFi Financial Intelligence for AI Agents 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.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.