Nansen

Analyzing recent activity

token_recent_flows_summary

Get an on-chain flow snapshot across ALL wallet categories in one call. This tool supports native ETH on Ethereum and native SOL on Solana, and is the correct choice for standard lookbacks such as 1d.

Returns TOTAL token flows per segment: 1. Public Figures 2. Top PnL Traders 3. Whales 4. Smart Traders 5. Exchanges 6. Fresh Wallets

Inflow and outflow of tokens between the segments is CRITICAL in identifying token price trends.

The values provided are aggregated over the specific lookback period (last 5min, 1d, 7d etc) specified. If you have SPECIFIC date ranges in mind, use token_flows instead.

NOTE Use token_flows for more granular data as it can filter between exact dates and provides HOURLY breakdowns.

Returns: Categorized token flow analysis as markdown.

For each segment, returns:
- Flow amount in USD
- Ratio compared to average flow
- Number of wallets

Format: "{Segment} wallet flow of {amount} ({ratio}x average, from {count} wallets)"

Notes: - Positive flow = net buying, negative flow = net selling - For Exchange Flow, positive means more inflow to exchanges, negative means more outflow from exchanges - Categorizes market participants by their historical behavior and characteristics

NOTE: Bitcoin is not supported. DO NOT use this tool for bitcoin.

Modes:

onchain_tokens (default): On-chain token flow intelligence across cohorts
perps: Hyperliquid perpetual futures — returns position intelligence (current aggregate long/short/total USD by cohort: Smart Money, Whales, Public Figures). Native tokens (SOL, ETH, BTC etc) are fully supported in perps mode.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`request`	Yes

Output Schema

TableJSON Schema

Name	Required	Description	Default
`result`	Yes

TDQS

A4.3/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description must carry the behavioral disclosure. It reveals aggregation over lookback periods, the meaning of positive/negative flow, supported assets (native ETH/SOL, not BTC), and the categorization of wallet segments. It does not explicitly state read-only behavior or data latency, but these are less critical for a query tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is long but well-organized with clear sections for returns, notes, and modes. It is front-loaded with the primary purpose and repeated guidance to use token_flows for granular data is slightly redundant, but the structure helps readability without excessive wordiness.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description covers purpose, when to use, alternatives, return format, limitations (Bitcoin not supported), and modes. It does not explicitly explain how to specify the token or chain, but the schema provides that detail. For a tool with no annotations and a nested schema, this is a fairly complete description.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, and the description does not explicitly mention the tokenAddress or chain parameters. However, it does add meaning by explaining modes and supported assets (native ETH/SOL in onchain mode; SOL, ETH, BTC in perps mode). The schema itself contains descriptions for mode, chain, and lookbackPeriod, partially compensating for the lack of description coverage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific action and scope: 'Get an on-chain flow snapshot across ALL wallet categories in one call.' It clearly distinguishes from the sibling tool token_flows by noting this is for standard lookbacks while token_flows is for granular data and specific date ranges.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicit guidance is provided: 'correct choice for standard lookbacks such as 1d', 'If you have SPECIFIC date ranges in mind, use `token_flows` instead', and 'DO NOT use this tool for bitcoin.' It also explains the two modes (onchain_tokens and perps), telling when each is appropriate.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All Nansen tools Inspect

Try in Browser

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A3.8/5.0

Disambiguation5/5

Each tool has a clearly defined purpose, and overlapping tools (e.g., token_flows vs token_recent_flows_summary, nansen_score_top_tokens vs token_discovery_screener) include explicit guidance on when to use them. Even with similar names like prediction_market_trades and prediction_market_address_trades, the descriptions and parameters make the distinction unambiguous.

Naming Consistency4/5

Most tools follow a domain_prefix_noun pattern (address_, token_, prediction_market_), making them predictable within families. However, outliers like general_search, growth_chain_rank, hyperliquid_leaderboard, and transaction_lookup break the pattern, and some names are long or inconsistently formatted (e.g., smart_traders_and_funds_perp_trades vs smart_traders_and_funds_token_balances).

Tool Count3/5

With 38 tools, the server is far above the typical 3-15 range, making it heavy for agents to navigate. However, Nansen is a broad analytics platform covering wallets, tokens, prediction markets, and smart money activity, so the high count is justifiable as each tool serves a distinct function.

Completeness5/5

The tool set provides comprehensive coverage across token analysis (ohlcv, trading, holders, flows, PnL, technicals), wallet analysis (portfolio, transactions, counterparties), prediction markets (lookup, orderbook, trades, PnL), and discovery. The only obvious omission is NFT support, but it is explicitly documented as out of scope, so no critical dead ends exist.

Resources

Need Help?