verdix
OfficialServer Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| VERDIX_API_URL | No | Only for testing against another deployment. | https://api.verdixapi.com |
| EVM_PRIVATE_KEY | No | Alternative to VERDIX_PRIVATE_KEY, also accepted. | |
| VERDIX_PRIVATE_KEY | No | Your Base wallet's private key (hex). Required to use check_address_risk. | |
| VERDIX_MAX_PRICE_USD | No | Most one call may cost, in USD. | 0.10 |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| check_address_riskA | Screen an EVM address on Base before sending it money or interacting with it. Returns Verdix's verdict JSON unchanged: verdict (safe | caution | danger), risk_score (0-100), reasons, checked, tier, price_usd, as_of. 'danger' means sanctioned, a known scam/exploit/phishing address, an address-poisoning lookalike, a burn address or similar - do not send funds. 'caution' means not enough evidence to call it safe (new, unverified, or a data source was unavailable) - confirm with the user first. Every tier runs OFAC sanctions, scam/phishing/exploit lists, address-poisoning lookalikes, burn-address and contract/deployer checks; quick adds a fast address-age read, standard and deep run deeper on-chain behaviour analysis instead (deep runs the same checks as standard today - pick it for high-value or first-time transfers, not for extra checks). PAID: each call costs USDC on Base via x402, paid from the wallet configured in this server (VERDIX_PRIVATE_KEY), never more than VERDIX_MAX_PRICE_USD. Tiers: quick ($0.02), standard ($0.10, default), deep ($0.50); call get_pricing for current prices. A 503 answer (data unavailable) is not charged. |
| check_address_risk_quickA | Screen an EVM address on Base before sending it money or interacting with it, pinned to the quick tier (fixed $0.02; use check_address_risk with tier="quick" if you want that price without a dedicated tool). Returns Verdix's verdict JSON unchanged: verdict (safe | caution | danger), risk_score (0-100), reasons, checked, tier, price_usd, as_of. 'danger' means sanctioned, a known scam/exploit/phishing address, an address-poisoning lookalike, a burn address or similar - do not send funds. 'caution' means not enough evidence to call it safe (new, unverified, or a data source was unavailable) - confirm with the user first. Every tier runs OFAC sanctions, scam/phishing/exploit lists, address-poisoning lookalikes, burn-address and contract/deployer checks; this tier additionally runs a fast address-age read. PAID: calling this tool always costs $0.02 USDC on Base via x402, paid from the wallet configured in this server (VERDIX_PRIVATE_KEY), and is refused up front if that is above VERDIX_MAX_PRICE_USD. A 503 answer (data unavailable) is not charged. |
| check_address_risk_standardA | Screen an EVM address on Base before sending it money or interacting with it, pinned to the standard tier (fixed $0.10; use check_address_risk with tier="standard" if you want that price without a dedicated tool). Returns Verdix's verdict JSON unchanged: verdict (safe | caution | danger), risk_score (0-100), reasons, checked, tier, price_usd, as_of. 'danger' means sanctioned, a known scam/exploit/phishing address, an address-poisoning lookalike, a burn address or similar - do not send funds. 'caution' means not enough evidence to call it safe (new, unverified, or a data source was unavailable) - confirm with the user first. Every tier runs OFAC sanctions, scam/phishing/exploit lists, address-poisoning lookalikes, burn-address and contract/deployer checks; this tier additionally runs deeper on-chain behaviour analysis. PAID: calling this tool always costs $0.10 USDC on Base via x402, paid from the wallet configured in this server (VERDIX_PRIVATE_KEY), and is refused up front if that is above VERDIX_MAX_PRICE_USD. A 503 answer (data unavailable) is not charged. |
| check_address_risk_deepA | Screen an EVM address on Base before sending it money or interacting with it, pinned to the deep tier (fixed $0.50; use check_address_risk with tier="deep" if you want that price without a dedicated tool). Returns Verdix's verdict JSON unchanged: verdict (safe | caution | danger), risk_score (0-100), reasons, checked, tier, price_usd, as_of. 'danger' means sanctioned, a known scam/exploit/phishing address, an address-poisoning lookalike, a burn address or similar - do not send funds. 'caution' means not enough evidence to call it safe (new, unverified, or a data source was unavailable) - confirm with the user first. Every tier runs OFAC sanctions, scam/phishing/exploit lists, address-poisoning lookalikes, burn-address and contract/deployer checks; this tier additionally runs the same checks as standard today - pick it for high-value or first-time transfers, not for extra checks. PAID: calling this tool always costs $0.50 USDC on Base via x402, paid from the wallet configured in this server (VERDIX_PRIVATE_KEY), and is refused up front if that is above VERDIX_MAX_PRICE_USD. A 503 answer (data unavailable) is not charged. |
| check_address_risk_liteA | Cheapest Verdix check ($0.01): screen an EVM address on Base before sending it USDC or other funds, when the recipient is unknown or new to you. It checks OFAC sanctions, scam/phishing lists, address-poisoning lookalikes, burn addresses, phishing tokens and flagged contract deployers; it skips address age and the caution-only contract checks. Returns Verdix's JSON unchanged: verdict (no_known_risk | caution | danger), risk_score, reasons, checked, limited_checks (always true), checks_performed, not_checked, full_check, as_of. This tool NEVER returns "safe": the clean answer is "no_known_risk", which only means the address is on none of these lists - it is not a safety verdict. 'danger' means do not send funds. 'caution' means confirm with the user first. If you need a "safe" verdict (e.g. before a large or irreversible transfer), call check_address_risk_quick ($0.02) instead or after this one. Optional chain: "base" (default, live data) or "ethereum" (Ethereum mainnet: OFAC, scam/phishing lists, burn addresses and address-poisoning lookalikes from a DAILY scan, not live; the answer adds data_through, the last complete UTC day, and coverage "daily, not live"; phishing-token and deployer checks are Base only, and there is no quick tier for Ethereum). PAID: calling this tool always costs $0.01 USDC on Base via x402 (also for chain=ethereum), paid from the wallet configured in this server (VERDIX_PRIVATE_KEY), and is refused up front if that is above VERDIX_MAX_PRICE_USD. A 503 answer (data unavailable, or Ethereum data out of date) is not charged. |
| check_address_poisoningA | Free (no wallet, nothing paid): look up whether Verdix's address-poisoning watcher has flagged an EVM address as a lookalike or poisoning bait, on Base (default, live) or Ethereum mainnet (chain "ethereum": a DAILY scan, not live). Returns Verdix's JSON unchanged: flagged (true/false), first_seen, kind; on Ethereum also data_through (the last complete UTC day; lookalikes planted after it are not seen yet) and coverage "daily, not live". flagged=true means do not send funds there. flagged=false is NOT a safety verdict: this checks address poisoning only (no sanctions, scam lists or other checks) - use check_address_risk_lite or check_address_risk_quick for a pre-send screen. Rate-limited per IP (30 per minute, 500 per day). A mixed-case address must have a valid checksum. |
| get_pricingA | Free. Current Verdix price per tier (USDC on Base, via x402), the payment recipient, your configured max price per call, and whether a wallet is configured (with its public address, so it can be funded). |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 7 tools
Four tools (check_address_risk, check_address_risk_quick, check_address_risk_standard, check_address_risk_deep) all perform the same pre-send address screen on Base and differ only by price tier, while the generic tool can already select a tier. The descriptions explicitly address this redundancy and explain when to use each, which prevents the set from being genuinely confusing, but the boundaries are still overlapping by design.
All risk-screening tools follow a consistent snake_case check_address_risk[_tier] pattern, and check_address_poisoning fits the same verb_noun convention. get_pricing is the only different verb, which is appropriate for its free utility role.
Seven tools is a reasonable size for a focused address-risk API and keeps the surface manageable. However, the three tier-pinned wrappers largely duplicate the generic check_address_risk tool, so the set is slightly larger than strictly necessary.
The surface covers the core lifecycle: free poisoning lookup, lite/quick/standard/deep screening, a flexible tiered tool, and pricing/wallet status. Minor gaps remain, such as batch screening or explicit supported-chain discovery, but the main pre-send workflows are covered.