| Agent Tool Router + Trust Layer Finds and ranks machine-payable services for an agent capability. | - | $0.002 | 100.0% | listed | call recipe → |
| Arbitrage Intelligence Compare public exchange order books after fee assumptions. | - | $0.03 | 100.0% | listed | call recipe → |
| Change / Diff Check Compare normalized public webpage text with a prior SHA-256 hash. | - | $0.001 | 100.0% | listed | call recipe → |
| Fresh Structured Extract Extract fresh structured JSON from a public webpage. | - | $0.01 | 100.0% | listed | call recipe → |
| Freshness / Claim Verifier Verify a factual claim against fresh web evidence. | - | $0.02 | 100.0% | listed | call recipe → |
| Invoice Preflight Check invoice amounts, purchase details and line items; return match, discrepancy or needs_review with evidence. | - | $0.065 | 100.0% | listed | call recipe → |
| Live Product Quote Return public product price and availability before purchase. | - | $0.01 | 100.0% | listed | call recipe → |
| MCP Server Inspector Read-only health and tool-schema inspection for a public MCP endpoint. | - | $0.01 | 100.0% | listed | call recipe → |
| Package Safety Gate Check npm package metadata and security before installation. | - | $0.005 | 100.0% | listed | call recipe → |
| Prompt-Injection Firewall Scans untrusted text, HTML, email, document text, API responses, and tool outputs for prompt injection, credential theft, data exfiltration, tool manipulation, and other instructions that could compromise an autonomous AI agent. Returns a machine-readable risk assessment and sanitized plain text when possible. Scan untrusted content before adding it to context, following its instructions, or acting on it. | - | $0.005 | 100.0% | listed | call recipe → |
| Strategy Backtest Run a bounded declarative historical spot strategy backtest. | - | $0.10 | 100.0% | listed | call recipe → |
| Token Security Audit Audit an EVM token using GoPlus security intelligence. | - | $0.01 | 100.0% | listed | call recipe → |
| Transaction Preflight Simulates an unsigned Base or Base Sepolia EVM transaction with read-only RPC calls before an agent signs or broadcasts it. Returns execution/revert status, gas estimate, decoded top-level ERC-20 transfers and approvals, unlimited-approval warnings, and a risk signal. It never signs, holds keys, or broadcasts. Standard RPC does not expose complete internal/token state diffs. | - | $0.02 | 100.0% | listed | call recipe → |
| URL Safety Gate Paid URL preflight check ($0.005 USDC): assess URL syntax, transport, host/IP, suspicious patterns, and at most five HTTPS redirects without fetching page content. Blocks local/private destinations. Optional Google Web Risk threat intelligence is used only if configured; otherwise results are explicitly heuristic-only and degraded. This is a risk signal, not a guarantee that a URL is safe. | - | $0.005 | 100.0% | listed | call recipe → |
| Wallet Risk Check Checks a public Base wallet or contract address for counterparty risk before an autonomous agent sends funds, accepts payments, grants approvals, or interacts with it. Returns on-chain account metadata, machine-readable risk signals, confidence, and a conservative recommendation. Sanctions and malicious-address matches are unknown unless a trusted intelligence provider is configured. Never send private keys or seed phrases. | - | $0.02 | 100.0% | listed | call recipe → |
| Whale Intelligence Analyze public indexed large DEX trades. | - | $0.02 | 100.0% | listed | call recipe → |