Medium Risk

token_dex_trades

Get DEX trades for a specific token. Modes: - onchain_tokens (default): Analyze on-chain tokens by contract address - perps: Analyze Hyperliquid perpetual futures by symbol (chain auto-set to "hyperliquid") Args: request: TokenDexTradesRequest containing parameters, pagination settings, and optio...

Part of the Nansen-MCP server.

token_dex_trades can modify Nansen-MCP data, with no limits today. PolicyLayer puts allow, deny, and rate-limit rules on every call. Live in minutes.

SECURE NANSEN-MCP →

Free to start. No card required.

AI agents use token_dex_trades to create or modify resources in Nansen-MCP. Write operations carry medium risk because an autonomous agent could trigger bulk unintended modifications. Rate limits prevent a single agent session from making hundreds of changes in rapid succession. Argument validation ensures the agent passes expected values.

Without a policy, an AI agent could call token_dex_trades repeatedly, creating or modifying resources faster than any human could review. PolicyLayer's rate limiting ensures write operations happen at a controlled pace, and argument validation catches malformed or unexpected inputs before they reach Nansen-MCP.

Write tools can modify data. A rate limit prevents runaway bulk operations from AI agents.

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "token_dex_trades": {
      "limits": [
        {
          "counter": "token_dex_trades_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

See the full Nansen-MCP policy for all 24 tools.

Get this rule live on your own Nansen-MCP server in minutes. PolicyLayer enforces it on every call, before it runs.

ENFORCE ON MY NANSEN-MCP →

View all 24 tools →

These attack patterns abuse exactly the kind of access token_dex_trades gives an agent. Each links to the full case and the policy that stops it:

Browse the full MCP Attack Database →

Every attack above starts with a tool call. PolicyLayer checks each one against your policy first, so token_dex_trades only ever does what you allow.

SECURE NANSEN-MCP →

Other write tools across the catalogue. The same approach applies to each: rate-limit and validate the arguments.

What does the token_dex_trades tool do? +

Get DEX trades for a specific token. Modes: - onchain_tokens (default): Analyze on-chain tokens by contract address - perps: Analyze Hyperliquid perpetual futures by symbol (chain auto-set to "hyperliquid") Args: request: TokenDexTradesRequest containing parameters, pagination settings, and optional sorting Returns: DEX trading activity as markdown. Returns empty string if no trades found. Common Columns (all modes): - Time: Timestamp when the trade occurred (datetime: YYYY-MM-DD HH:MM:SS) - Token: Symbol of the token/perpetual contract - Price USD: Price per token in USD at time of trade (currency formatted) - Value USD: Total USD value of the trade/position change (currency formatted) - Trader: Nansen label or name of the trading address - Tx Hash: Blockchain transaction hash for verification onchain_tokens mode: - Action: Trade direction - BUY or SELL from perspective of the token - Token Amount: Quantity of the target token traded (numeric) - Traded Amount: Quantity of the other token in the swap (numeric) - Traded Token: Symbol of the token traded against (e.g., WETH, USDC) perps mode: - Side: Position direction - Long or Short - Action: Order action - Add, Reduce, Open, Close - Size: Quantity of the perpetual contract (numeric) Sorting Options (all fields support "asc"/"desc"): Available for sorting: timestamp, valueUsd, amount, priceUsd Examples: # On-chain tokens (default mode) { "mode": "onchain_tokens", "chain": "ethereum", "tokenAddress": "0xa0b86a33e6b6c4b3add000b44b3a1234567890ab", "dateRange": {"from": "24H_AGO", "to": "NOW"} } # Hyperliquid perpetual futures { "mode": "perps", "tokenAddress": "PENGU", "dateRange": {"from": "7D_AGO", "to": "NOW"}, "action": "Open", "side": "Long" } # Find biggest trades by USD value (whale watching) { "mode": "onchain_tokens", "chain": "ethereum", "tokenAddress": "0xa0b86a33e6b6c4b3add000b44b3a1234567890ab", "dateRange": {"from": "7D_AGO", "to": "NOW"}, "order_by": "valueUsd", "order_by_direction": "desc" } # Find who bought the dip vs who bought the top (price analysis) { "chain": "ethereum", "tokenAddress": "0xa0b86a33e6b6c4b3add000b44b3a1234567890ab", "dateRange": {"from": "30D_AGO", "to": "NOW"}, "order_by": "priceUsd", "order_by_direction": "asc" }. It is categorised as a Write tool in the Nansen-MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on token_dex_trades? +

Register the Nansen- MCP server in PolicyLayer and add a rule for token_dex_trades: 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.

What risk level is token_dex_trades? +

token_dex_trades is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit token_dex_trades? +

Yes. Add a rate_limit block to the token_dex_trades 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.

How do I block token_dex_trades completely? +

Set action: deny in the PolicyLayer policy for token_dex_trades. 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.

What MCP server provides token_dex_trades? +

token_dex_trades 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.

Enforce policy on every Nansen-MCP tool call.

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.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.