Skip to main content
Glama

checkHoneypot

Detect honeypot scams in tokens by analyzing buy/sell taxes, risk levels, and honeypot.is data across EVM chains to identify fraudulent contracts.

Instructions

토큰의 허니팟(사기) 여부를 탐지합니다 (매수/매도 세금, 위험도, 플래그, Honeypot.is 기반)

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
tokenYes토큰 주소 (0x...) 또는 심볼
chainNoEVM 체인ethereum

Implementation Reference

  • Tool handler function for 'checkHoneypot' which resolves token metadata and invokes the honeypot check utility.
    async function handler(args: z.infer<typeof inputSchema>): Promise<ToolResult<HoneypotData>> {
      const { token, chain } = args;
    
      // 토큰 주소 해석
      let tokenAddress = token;
      if (!token.startsWith("0x") || token.length !== 42) {
        const meta = resolveTokenMeta(token, chain);
        if (!meta) return makeError(`Token '${token}' not found`, "TOKEN_NOT_FOUND");
        const addresses = meta.addresses;
        tokenAddress = addresses[chain];
        if (!tokenAddress) return makeError(`Token '${token}' not available on ${chain}`, "TOKEN_NOT_FOUND");
      }
    
      try {
        const result = await checkHoneypotToken(tokenAddress, chain);
        if (!result) return makeError("Honeypot check failed — API unavailable or unsupported chain", "API_ERROR");
    
        const data: HoneypotData = {
          token: tokenAddress,
          tokenName: result.tokenName,
          tokenSymbol: result.tokenSymbol,
          isHoneypot: result.isHoneypot,
          riskLevel: result.riskLevel,
          buyTax: result.buyTax,
          sellTax: result.sellTax,
          flags: result.flags,
          pairAddress: result.pairAddress,
        };
    
        return makeSuccess(chain, data, false);
      } catch (err) {
        const message = sanitizeError(err);
        return makeError(`Honeypot check failed: ${message}`, "API_ERROR");
      }
    }
  • Tool registration for 'checkHoneypot' in the MCP server.
    export function register(server: McpServer) {
      server.tool(
        "checkHoneypot",
        "토큰의 허니팟(사기) 여부를 탐지합니다 (매수/매도 세금, 위험도, 플래그, Honeypot.is 기반)",
        inputSchema.shape,
        async (args) => {
          const result = await handler(args as z.infer<typeof inputSchema>);
          return { content: [{ type: "text" as const, text: JSON.stringify(result, null, 2) }] };
        },
      );
    }
  • Core helper function that interacts with the Honeypot.is API to check token safety.
    export async function checkHoneypotToken(
      tokenAddress: string,
      chain: string,
    ): Promise<HoneypotResult | null> {
      if (!isValidAddress(tokenAddress)) return null;
      const chainId = CHAIN_IDS[chain as keyof typeof CHAIN_IDS];
      if (!chainId) return null;
    
      const cacheKey = `honeypot:${chain}:${tokenAddress.toLowerCase()}`;
      const cached = cache.get<HoneypotResult>(cacheKey);
      if (cached.hit) return cached.data;
    
      try {
        const res = await fetch(
          `${BASE_URL}/IsHoneypot?address=${tokenAddress}&chainID=${chainId}`,
        );
        if (!res.ok) return null;
    
        const json = (await res.json()) as {
          honeypotResult?: { isHoneypot: boolean };
          simulationResult?: { buyTax: number; sellTax: number; transferTax: number };
          contractCode?: { openSource: boolean; isProxy: boolean; hasProxyCalls: boolean };
          token?: { name: string; symbol: string; totalHolders: number };
          pair?: { address: string; pairName: string };
          flags?: string[];
        };
    
        const isHoneypot = json.honeypotResult?.isHoneypot ?? false;
        const buyTax = json.simulationResult?.buyTax ?? 0;
        const sellTax = json.simulationResult?.sellTax ?? 0;
    
        // 위험 플래그 수집
        const flags: string[] = [];
        if (isHoneypot) flags.push("honeypot");
        if (buyTax > 10) flags.push("high_buy_tax");
        if (sellTax > 10) flags.push("high_sell_tax");
        if (json.contractCode?.hasProxyCalls) flags.push("proxy_calls");
        if (!json.contractCode?.openSource) flags.push("closed_source");
        if (json.flags) flags.push(...json.flags);
    
        // 위험도 판정
        let riskLevel: "safe" | "warning" | "danger" = "safe";
        if (isHoneypot || sellTax > 50) riskLevel = "danger";
        else if (buyTax > 10 || sellTax > 10 || flags.length > 2) riskLevel = "warning";
    
        const result: HoneypotResult = {
          isHoneypot,
          riskLevel,
          buyTax: Math.round(buyTax * 100) / 100,
          sellTax: Math.round(sellTax * 100) / 100,
          flags: [...new Set(flags)],
          pairAddress: json.pair?.address ?? null,
          tokenName: json.token?.name ?? null,
          tokenSymbol: json.token?.symbol ?? null,
        };
    
        cache.set(cacheKey, result, HONEYPOT_CACHE_TTL);
        return result;
      } catch (err) {
        logCatchError("honeypot", err);
        return null;
      }
    }
  • Zod input schema for the 'checkHoneypot' tool.
    const inputSchema = z.object({
      token: z.string().describe("토큰 주소 (0x...) 또는 심볼"),
      chain: z.enum(SUPPORTED_CHAINS).default("ethereum").describe("EVM 체인"),
    });
Behavior3/5

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

With no annotations provided, the description carries the full disclosure burden. It adds valuable context about what gets analyzed (매수/매도 세금, 위험도, 플래그/buy-sell taxes, risk, flags) and the external dependency (Honeypot.is 기반). However, it lacks disclosure on error handling, rate limits, data freshness, or whether this triggers any blockchain transactions.

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?

Extremely efficient single-sentence structure with parenthetical elaboration. Every element earns its place: the core function, specific check criteria, and data source attribution. No redundancy or filler content.

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?

For a 2-parameter fraud detection tool with 100% schema coverage, the description is nearly complete. It hints at return values by listing checked criteria (taxes, risk, flags). Minor gap: explicit mention of output structure or reliability warnings would perfect it, given the high-stakes nature of financial fraud detection.

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 100%, with the schema already clearly documenting both parameters (token as address/symbol, chain as EVM enum with defaults). The description mentions '토큰' but adds no semantic meaning beyond what the schema already provides, warranting the baseline 3.

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 specifies the verb (탐지합니다/detects), resource (토큰/token), and specific scope (허니팟/사기 여부/honeypot fraud status). It distinguishes from siblings like getTokenInfo by focusing specifically on fraud detection rather than general metadata.

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?

While the specific domain (fraud detection) implies usage context, there is no explicit guidance on when to use this versus getTokenInfo or getApprovalStatus, no prerequisites mentioned, and no warnings about relying on external Honeypot.is data.

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/calintzy/evmscope'

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