Skip to main content
Glama

hyperd.wallet.anomaly

Detect wallet behavioral anomalies by comparing recent activity to a 180-day baseline. Identifies compromised wallets, dormant whales, and MEV-bot shifts.

Instructions

Wallet behavioral anomaly detection. Compares recent activity against the wallet's own 180-day baseline — surfaces tx-volume spikes, dormant-wakeup patterns, new-protocol interactions, counterparty diversification. Catches compromised hot wallets, dormant whales, MEV-bot strategy shifts. Costs $0.10 in USDC.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
addressYes0x EVM wallet address
chainNoChain to analyze. Default 'base'.
windowNoRecent activity window. "24h", "7d", "30d", or bare integer days. Default "24h".

Implementation Reference

  • src/server.ts:371-387 (registration)
    Tool registration for 'hyperd.wallet.anomaly' using the McpServer. Registers the tool with a description, Zod schema for input params (address, chain, window), and a handler that calls paidGet('/api/wallet/anomaly', args) and wraps the result with asText().
    // hyperd.wallet.anomaly — behavioral anomaly detection ($0.10)
    server.tool(
      "hyperd.wallet.anomaly",
      "Wallet behavioral anomaly detection. Compares recent activity against the wallet's own 180-day baseline — surfaces tx-volume spikes, dormant-wakeup patterns, new-protocol interactions, counterparty diversification. Catches compromised hot wallets, dormant whales, MEV-bot strategy shifts. Costs $0.10 in USDC.",
      {
        address: z.string().describe("0x EVM wallet address"),
        chain: z
          .enum(["base", "ethereum", "polygon", "arbitrum", "optimism", "avalanche", "bnb"])
          .optional()
          .describe("Chain to analyze. Default 'base'."),
        window: z
          .string()
          .optional()
          .describe('Recent activity window. "24h", "7d", "30d", or bare integer days. Default "24h".'),
      },
      async (args) => asText(await paidGet("/api/wallet/anomaly", args)),
    );
  • Handler logic for hyperd.wallet.anomaly: delegates to paidGet('/api/wallet/anomaly', args), which performs an x402 payment-gated GET request to the hyperD API, then formats the JSON response as text via asText().
    async (args) => asText(await paidGet("/api/wallet/anomaly", args)),
  • Input schema for hyperd.wallet.anomaly using Zod: 'address' (required string, EVM address), 'chain' (optional enum of chains, default 'base'), 'window' (optional string for time window like '24h', '7d', '30d').
    {
      address: z.string().describe("0x EVM wallet address"),
      chain: z
        .enum(["base", "ethereum", "polygon", "arbitrum", "optimism", "avalanche", "bnb"])
        .optional()
        .describe("Chain to analyze. Default 'base'."),
      window: z
        .string()
        .optional()
        .describe('Recent activity window. "24h", "7d", "30d", or bare integer days. Default "24h".'),
    },
  • paidGet helper function used by the tool handler. Constructs the API URL with query params and initiates the x402 payment-gated GET request via paidRequest.
    async function paidGet(
      path: string,
      query: Record<string, string | number | boolean | undefined>,
    ): Promise<unknown> {
      if (!httpClient) {
        throw new Error(WALLET_NOT_CONFIGURED_MSG);
      }
    
      const url = new URL(`${API_BASE}${path}`);
      for (const [k, v] of Object.entries(query)) {
        if (v !== undefined && v !== "" && v !== null) url.searchParams.set(k, String(v));
      }
      return paidRequest("GET", url, undefined);
    }
  • asText helper function that wraps JSON data into the MCP content response format { content: [{ type: 'text', text: ... }] }.
    function asText(data: unknown) {
      return { content: [{ type: "text" as const, text: JSON.stringify(data, null, 2) }] };
    }
Behavior3/5

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

No annotations are provided, so the description carries the full burden. It mentions the tool's cost ($0.10 in USDC), which is a behavioral trait, and implies read-only analysis (detecting anomalies). However, it does not disclose side effects, destruction, rate limits, or authorization requirements. The description is fairly transparent but lacks some behavioral specifics.

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

Conciseness5/5

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

The description is concise: three sentences. First sentence states purpose, second sentence enumerates detected patterns, third sentence gives use cases and cost. Each sentence adds value without redundancy. It's well-structured and front-loaded.

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

Completeness3/5

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

No output schema is provided, so the description does not explain return values. It also omits error conditions or rate limits. Given the tool's complexity (analysis, cost), the description is moderately complete but could mention expected output format or error handling.

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 coverage is 100% with each parameter described adequately. The description adds context about the 180-day baseline and cost, but does not further enrich the meaning of parameters beyond what the schema already provides. Per guidelines, baseline is 3 for high 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 clearly states the tool's purpose: 'Wallet behavioral anomaly detection.' It explains what it does (compares recent activity against a 180-day baseline, surfaces specific patterns) and provides use cases (catches compromised hot wallets, dormant whales, MEV-bot strategy shifts). This distinguishes it from siblings like hyperd.wallet.persona or hyperd.wallet.risk, which likely focus on profiling or risk scoring.

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

Usage Guidelines3/5

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

The description does not explicitly state when to use this tool versus alternatives. It implies use for anomaly detection, but lacks guidance such as 'use this when you need to detect behavioral anomalies' or 'for overall wallet risk, use hyperd.wallet.risk instead.' Some implicit guidance exists but is not explicit.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/hyperd-ai/hyperd-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server