Skip to main content
Glama

Nansen

by io.github.hurcanNansen

Ranking top tokens by Nansen Score

nansen_score_top_tokens

Discover and filter a daily list of attractive tokens using Nansen Score Indicators weighted by coefficients (= Performance Score).

Use this tool when you don't know which tokens to buy and need recommendations based on backtested indicators. For specific token analysis (e.g., "should I buy AAVE?"), use token_quant_scores instead.

When to use this tool vs token_discovery_screener:

  • Use this tool when you want pre-scored buying recommendations without specifying criteria. It answers "what should I buy?" by returning tokens that already meet a quantitative buying threshold (Performance Score ≥15) based on alpha indicators like price momentum, chain fees, and protocol fees. Data is updated in batches.

  • Use token_discovery_screener when you want live data or to explore tokens by specific criteria like sectors (e.g., "AI memecoins"), token age (e.g., "new launches"), smart money activity, or custom volume/liquidity thresholds. It's a filtering tool with real-time metrics where you define what you're looking for.

Returns tokens pre-filtered by: performance_score >= 15 (buying threshold).

Example queries: "what tokens should I buy?", "which tokens look good?", "best tokens to buy today"

Scoring:

  • Performance Score (range -60 to +75): Higher = better alpha opportunity. Buy threshold: ≥15

  • Risk Score (range -60 to +80): Higher = safer token. >0 indicates low to medium risk.

Every time you give the Performance Score to the user, explain the scoring thresholds above. Same for the Risk Score. Every time quote the underlying indicators that contributed the most to the Performance/ Risk score and recall their definition to the user.

Returns: A list of tokens with the highest Performance Score as markdown.

Core fields: Token Address, Token Symbol, Chain, Performance Score, Risk Score.
Indicator columns are included dynamically based on data availability (columns with all zeros are excluded).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
requestYes

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
resultYes

TDQS

A4.2/5.0
Behavior4/5

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

No annotations are provided, so the description bears the full burden. It discloses batch data updates, pre-filtering threshold (performance_score >= 15), scoring ranges, risk score meaning, return format (markdown), and dynamic inclusion of indicator columns. It does not mention rate limits or pagination, but for a read-only recommendation tool, the key behavioral traits are covered.

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 longer than average but well-structured with clear sections (when to use, comparison, scoring, return format). It front-loads the core purpose and avoids fluff, though the repeated instructions about explaining thresholds to users could be seen as slightly redundant.

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?

Given the complexity of the scoring system and sibling differentiation, the description covers most relevant context: usage scenarios, scoring ranges, buy threshold, return fields, and dynamic columns. The key gap is parameter documentation, but for a tool that can be called without arguments, it's largely complete.

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

Parameters2/5

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

The description never explains the required 'request' parameter or the optional 'marketCapGroup' filter. Schema description coverage is 0%, so the description was expected to compensate, but it provides zero parameter semantics beyond the tool's general purpose. The agent would not know how to pass filters from the description alone.

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 opens with a specific verb and resource ('Discover and filter a daily list of attractive tokens'), and immediately distinguishes itself from sibling tools by explaining it uses Nansen Score Indicators to produce buy recommendations. It clearly differentiates from token_quant_scores and token_discovery_screener.

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?

Includes explicit 'Use this tool when...' guidance, plus a dedicated comparison section with token_discovery_screener, stating when to use each, including live data vs batch updates and predefined criteria. This far exceeds the minimum for usage guidance.

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

All Nansen toolsInspect
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