Get comprehensive token screening data across multiple blockchain networks with advanced filtering. A maximum of 25 results are returned out of 1000s of tokens. Use the sorting and filtering options to narrow down the results. A maximum of 5 chains can be specified per request (excess chains are ...
Part of the Nansen-MCP server.
Free to start. No card required.
AI agents may call token_discovery_screener to permanently remove or destroy resources in Nansen-MCP. Without a policy, an autonomous agent could delete critical data in a loop with no way to undo the damage. PolicyLayer blocks destructive tools by default and requires explicit human approval before enabling them.
Without a policy, an AI agent could call token_discovery_screener in a loop, permanently destroying resources in Nansen-MCP. There is no undo for destructive operations. PolicyLayer blocks this tool by default and only allows it when a human explicitly approves the action.
Destructive tools permanently remove data. Block by default. Only enable with explicit approval workflows.
{
"version": "1",
"default": "deny",
"hide": [
"token_discovery_screener"
]
}See the full Nansen-MCP policy for all 24 tools.
These attack patterns abuse exactly the kind of access token_discovery_screener gives an agent. Each links to the full case and the policy that stops it:
Other destructive tools across the catalogue. The same approach applies to each: deny by default, or require human approval.
Get comprehensive token screening data across multiple blockchain networks with advanced filtering. A maximum of 25 results are returned out of 1000s of tokens. Use the sorting and filtering options to narrow down the results. A maximum of 5 chains can be specified per request (excess chains are automatically trimmed). This tool helps with token discovery and finding trending tokens by combining different metrics: volume, liquidity, market cap, smart money activity, and token age. IMPORTANT - Hyperliquid Special Case: - Hyperliquid chain queries perpetual futures (perps), not spot tokens - When hyperliquid is mixed with other chains, two sections of up to 25 results each are returned - one for spot tokens and one for perps. - For perps, only these filters are supported: volume, buyVolume, sellVolume, openInterest, netflow, nofTraders, onlySmartTradersAndFunds - Additional orderBy fields for perps: openInterest, funding - Unsupported filters/orderBy will fallback to defaults INPUT EXAMPLES: Find tokens which are going up in price. Added some liquidity filter to remove spam and low quality tokens. { "chains": ["ethereum", "solana", "bnb", "base"], "timeframe": "24h", "liquidity": {"from": 100000}, "nofTraders": {"from": 10}, "orderBy": "priceChange", "orderByDirection": "desc" } Find top stablecoins by market cap { "chains": ["ethereum", "solana", "bnb", "base"], "timeframe": "7d", "sectors": ["Stablecoin"], "orderBy": "marketCapUsd", "orderByDirection": "desc" } Find AI memecoins with high trading activity { "chains": ["ethereum", "solana", "bnb", "base"], "timeframe": "7d", "sectors": ["AI Meme"], "liquidity": {"from": 100000}, "volume": {"from": 1000000} } Find DeFi lending tokens { "chains": ["ethereum", "solana", "bnb", "base"], "timeframe": "24h", "sectors": ["DeFi Lending (Money Markets)"], "netflow": {"from": 1000000} } Find tokens which have a lot of buying activity (high nofBuyers and buyVolume) Note that we added some filters to remove spam and low quality tokens. We added liquidity filter so that we only surface tokens which we can buy or sell. We sort by netflow descending to get tokens with the most net buying activity. { "chains": ["ethereum", "solana", "bnb", "base"], "timeframe": "24h", "liquidity": {"from": 100000}, "buyVolume": {"from": 1000000}, "marketCapUsd": {"from": 1000000}, "nofBuyers": {"from": 10}, "orderBy": "netflow", "orderByDirection": "desc" } Find Hyperliquid perps with high open interest and positive net flow { "chains": ["hyperliquid"], "timeframe": "7d", "openInterest": {"from": 100000}, "volume": {"from": 1000000}, "netflow": {"from": 0}, "nofTraders": {"from": 10}, "orderBy": "netflow", "orderByDirection": "desc" } WARNING: To avoid timeouts, it's recommended to: - Use 4 chains or less at a time (API tends to timeout with more chains) - Use shorter timeframes (e.g., 24h or 1h instead of 7d or 30d) Args: Returns: Comprehensive token metrics as markdown. Returns empty string if no tokens found. Columns returned: - Token Address: Token address (e.g., 0x1234567890123456789012345678901234567890) - Symbol: Token trading symbol (e.g., ETH, BTC, DOGE) - Chain: Blockchain network (ethereum, solana, polygon, etc.) - Price USD: Current token price in USD (currency formatted) - Price Change: Price change percentage over the date range (percentage, can be negative) - Market Cap: Current market capitalization (currency formatted) - Fully Diluted Valuation (FDV): Market cap if all tokens were circulating (currency formatted) - FDV/MC Ratio: Ratio indicating how much supply is locked/vested (numeric, >1 means locked supply) - USD Volume: Total trading volume in USD (currency formatted) - Buy USD Volume: Total buy volume in USD (currency formatted) - Sell USD Volume: Total sell volume in USD (currency formatted) - Net Flow USD: Net flow (buys minus sells) in USD (currency formatted, can be negative) - DEX Liquidity: Available liquidity for trading (currency formatted) - Inflow/FDV: Inflow as percentage of FDV (percentage formatted) - Outflow/FDV: Outflow as percentage of FDV (percentage formatted) - Token Age (Days): Days since token was first deployed - Sectors: List of token sectors/categories Notes: - Positive Net Flow indicates more buying than selling - High FDV/MC Ratio suggests significant locked or vested tokens Filtering Options (filters parameter): - Numeric Ranges: volume, liquidity, marketCapUsd, netflow, tokenAgeDays, nofTraders, nofBuyers, nofSellers, nofBuys, nofSells, buyVolume, sellVolume, fdv, fdvMcRatio, inflowFdvRatio, outflowFdvRatio - Categories: sectors (e.g. ["AI", "Meme"]), includeSmartMoneyLabels - Flags: onlySmartTradersAndFunds (boolean) - Use ONLY when user explicitly asks for "smart money". - Data with this filter is sparse. Pairing this with other filters (volume, liquidity, netflow) is likely to return no results. - Only pair onlySmartTradersAndFunds with other filters (volume, liquidity, netflow) if the user request explicitly requires it. - Instead of pairing this with other filters, you can rely on orderBy to sort by netflow, volume, liquidity, etc. CRITICAL WARNING: 'priceChange' is NOT a valid filter. You cannot filter for "tokens up > 10%". Use orderBy="priceChange" instead. Sorting Options (orderBy field): Available fields (use with orderByDirection: "asc" or "desc"): - priceUsd: Sort by token price - priceChange: Sort by price change percentage - marketCapUsd: Sort by market capitalization - volume: Sort by total trading volume - buyVolume: Sort by buy volume - sellVolume: Sort by sell volume - netflow: Sort by net flow (buys - sells) - liquidity: Sort by DEX liquidity - nofTraders: Sort by number of traders (Note: Fields like tokenAgeDays or outflowFdvRatio are for FILTERING only, not sorting) Default: orderBy="netflow", orderByDirection="desc". It is categorised as a Destructive tool in the Nansen-MCP MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Nansen- MCP server in PolicyLayer and add a rule for token_discovery_screener: 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 Nansen-MCP. Nothing to install.
token_discovery_screener is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the token_discovery_screener 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 token_discovery_screener. 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.
token_discovery_screener is provided by the Nansen- MCP server (nansen-ai/Nansen-MCP). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 24 Nansen-MCP 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.