Skip to main content
Glama
enesjakozh
ahnlabio

BICScan MCP Server

by ahnlabio
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Remote

BICScan MCP 서버

강력하고 효율적인 블록체인 주소 위험 평가 API MCP 서버는 BICScan API를 활용하여 블록체인 주소, 도메인 및 분산 애플리케이션(dApp)에 대한 포괄적인 위험 평가와 자산 정보를 제공합니다.

🎉 공식 통합을 위해 https://github.com/modelcontextprotocol/servers 에 등록되었습니다 🎉

https://github.com/user-attachments/assets/f9425429-1cb1-4508-b962-81351075258b

주요 특징

  • 위험 점수 : 암호화폐 주소, 도메인 이름, 분산 애플리케이션 URL을 포함한 다양한 블록체인 엔터티에 대한 위험 점수를 0~100점 범위로 얻습니다. 100점은 높은 위험을 나타냅니다.

  • 자산 정보 : 여러 블록체인 네트워크를 지원하여 암호화폐와 토큰을 포함한 지정된 암호화폐 주소에 대한 자세한 자산 보유 내역을 검색합니다.

  • 실시간 스캐닝 : BICScan API를 활용하여 실시간 스캔을 수행하고 잠재적 위험과 자산 보유에 대한 최신 정보를 받습니다.

  • 안전하고 신뢰할 수 있는 기능 : 강력한 오류 처리 및 로깅 기능을 구축하여 안전하고 신뢰할 수 있는 운영을 보장합니다.

Related MCP server: hive-mcp-aml-screen

출력 예

사용 방법

선호도에 따라 uv 나 docker 이용한 Python을 사용할 수 있습니다.

환경에 따라 uv , docker 또는 uvx 선택하여 사용할 수 있습니다.

1. uv 로 실행

1-1. 요구 사항

  1. Python 3.10 이상

  2. 자외선 0.6.x

  3. git

1.2. 저장소 복제

지엑스피1

1.3. claude_desktop_config.json 구성

claude_desktop_config.json 에 다음을 추가합니다.

다음 사항을 반드시 교체하세요.

  • YOUR_BICSCAN_REPO_DIR_HERE : C:\\Users\\ABC\\repo\\bicscan-mcp 또는 /home/abc/repo/bicscan-mcp 와 비슷하게 변경합니다.

  • YOUR_BICSCAN_API_KEY_HERE : 무료 API 키는 https://bicscan.io 에서 얻을 수 있습니다(자세한 내용은 아래 참조)

{
  "mcpServers": {
    ... some other mcp servers ...,
    "bicscan": {
      "command": "uv",
      "args": [
        "--directory",
        "YOUR_BICSCAN_REPO_DIR_HERE",
        "run",
        "bicscan-mcp"
      ],
      "env": {
        "BICSCAN_API_KEY": "YOUR_BICSCAN_API_KEY_HERE"
      }
    }
  }
}

2. Docker 로 실행

2.1. 요구 사항

  1. 도커 환경

2.2. 저장소 복제

git clone https://github.com/ahnlabio/bicscan-mcp

2.3. Docker 이미지 빌드.

저장소 디렉토리에서 make 실행하여 Docker 이미지를 빌드합니다.

2.4. 구성

claude_desktop_config.json 에 다음을 추가합니다.

다음 사항을 반드시 교체하세요.

  • https://bicscan.io 에서 얻은 API 키에 YOUR_BICSCAN_API_KEY_HERE 입력합니다(자세한 내용은 아래 참조).

{
  "mcpServers": {
    ... some other mcp servers ...,
    "bicscan": {
      "command": "docker",
      "args": [
        "run",
        "--rm",
        "--interactive",
        "--env", "BICSCAN_API_KEY=YOUR_BICSCAN_API_KEY_HERE",
        "bicscan-mcp"
      ]
    }
  }
}

3. uvx 로 실행

3.1. 요구 사항

  1. Python 3.10 이상

  2. 자외선 0.6.x

  3. git

3.2. claude_desktop_config.json 구성

claude_desktop_config.json 에 다음을 추가합니다.

다음 사항을 반드시 교체하세요.

  • YOUR_BICSCAN_API_KEY_HERE : 무료 API 키는 https://bicscan.io 에서 얻을 수 있습니다(자세한 내용은 아래 참조)

{
  "mcpServers": {
    ... some other mcp servers ...,
    "bicscan": {
      "command": "uvx",
      "args": [
        "--from",
        "git+https://github.com/ahnlabio/bicscan-mcp",
        "bicscan-mcp"
      ],
      "env": {
        "BICSCAN_API_KEY": "YOUR_BICSCAN_API_KEY_HERE"
      }
    }
  }
}

무료 BICScan API 키를 얻는 방법은 무엇입니까?

  1. https://bicscan.io 에 방문하여 등록하세요.

  2. 프로필로 가서 "앱 만들기"를 만드세요

  3. 선택한 항목의 이름과 설명을 입력하세요.

  4. 위의 구성에서 YOUR_BICSCAN_API_KEY_HERE 부분을 새로 얻은 키로 바꾸세요.

  5. Claude Desktop을 다시 시작하세요.

Available Tools

2 tools
get_assetsB

Get Assets holdings by CryptoAddress

Args:
    address: EOA, CA, ENS, CNS, KNS.
Returns:
    Dict: where assets is a list of assets
ParametersJSON Schema
NameRequiredDescriptionDefault
addressYes

TDQS

B3.1/5.0
Behavior2/5

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It states this is a 'Get' operation which implies read-only behavior, but doesn't disclose any behavioral traits like rate limits, authentication requirements, error conditions, or what happens with invalid addresses. The description mentions the return format ('Dict: where assets is a list of assets') but provides minimal detail about the response structure.

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 appropriately sized and well-structured with clear sections for Args and Returns. The main purpose is stated upfront, followed by parameter details and return information. There's minimal wasted text, though the formatting could be slightly cleaner (e.g., consistent capitalization in the Returns section).

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?

Given the tool's moderate complexity (single parameter with multiple formats), no annotations, and no output schema, the description is minimally adequate. It covers the basic purpose and parameter semantics well, but lacks behavioral context and usage guidance. For a tool that presumably queries blockchain data, more information about limitations, data freshness, or error handling would be beneficial.

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

Parameters4/5

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

The description adds significant value beyond the input schema, which has 0% description coverage. It explains that the 'address' parameter accepts multiple formats: 'EOA, CA, ENS, CNS, KNS' (presumably Externally Owned Account, Contract Address, Ethereum Name Service, etc.). This semantic clarification is crucial for proper tool invocation and compensates well for the schema's lack of documentation.

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

Purpose4/5

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

The description clearly states the tool's purpose: 'Get Assets holdings by CryptoAddress' specifies both the action (get) and the resource (assets holdings). It distinguishes from the sibling tool 'get_risk_score' by focusing on asset holdings rather than risk assessment. However, it doesn't fully differentiate from potential other asset-related tools beyond the single sibling.

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

Usage Guidelines2/5

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

The description provides no guidance on when to use this tool versus alternatives. There's no mention of when this tool is appropriate, what scenarios it's designed for, or any prerequisites for its use. The single sibling tool 'get_risk_score' is not referenced, leaving the agent with no comparative context.

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

get_risk_scoreB

Get Risk Score for Crypto, Domain Name, ENS, CNS, KNS or even Hostname Address

Args:
    address: EOA, CA, ENS, CNS, KNS or even HostName
Returns:
    Dict: where summary.bicscan_score is from 0 to 100. 100 is high risk.
ParametersJSON Schema
NameRequiredDescriptionDefault
addressYes

TDQS

B3.3/5.0
Behavior3/5

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It adds some context by explaining the return format and risk score range (0-100, where 100 is high risk), which is useful beyond basic functionality. However, it lacks details on error handling, rate limits, or authentication needs, leaving gaps in behavioral understanding.

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 appropriately sized and front-loaded, with the purpose stated first, followed by parameter and return details. It avoids unnecessary fluff, but the formatting with 'Args:' and 'Returns:' could be more integrated for better flow.

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?

Given the tool's complexity (risk scoring with various address types), no annotations, and no output schema, the description is moderately complete. It covers purpose, parameter semantics, and return format, but lacks usage guidelines, error details, or behavioral traits like rate limits, making it adequate but with clear gaps.

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

Parameters4/5

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

The schema description coverage is 0%, so the description must compensate. It adds meaning by listing examples of address types (EOA, CA, ENS, CNS, KNS, HostName), which clarifies the parameter's semantics beyond the schema's generic 'string' type. This significantly enhances understanding, though it could be more detailed on format constraints.

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

Purpose4/5

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

The description clearly states the tool's purpose: 'Get Risk Score for Crypto, Domain Name, ENS, CNS, KNS or even Hostname Address.' It specifies the verb 'Get' and the resource 'Risk Score,' with explicit examples of address types. However, it doesn't differentiate from the sibling tool 'get_assets,' which might have overlapping functionality, preventing a perfect score.

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

Usage Guidelines2/5

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

The description provides no guidance on when to use this tool versus alternatives, such as the sibling tool 'get_assets.' It lists address types but doesn't specify contexts or exclusions for usage, leaving the agent without clear direction on tool selection.

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

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

  1. 2 tool updates
    • First observedget_assets
    • First observedget_risk_score
Deploy Server
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

B3.3/5.0

Scored across 2 tools

Disambiguation5/5

The two tools have clearly distinct purposes: get_assets retrieves asset holdings, while get_risk_score calculates risk scores. There is no overlap in functionality, and an agent can easily differentiate between them based on their names and descriptions.

Naming Consistency5/5

Both tools follow a consistent verb_noun pattern with get_assets and get_risk_score. The naming is predictable and readable, using snake_case throughout without any deviations or mixed conventions.

Tool Count2/5

With only 2 tools, the server feels thin for a BICScan MCP Server, which suggests a domain involving crypto and risk analysis. This limited set may not cover essential operations like querying transactions, checking contract details, or updating data, making it borderline inadequate for the apparent scope.

Completeness2/5

The tool surface has significant gaps for a crypto/risk analysis domain. While it includes asset retrieval and risk scoring, it lacks basic operations such as querying transaction histories, verifying contract addresses, or performing deeper analytics. This incompleteness could lead to agent failures when handling common tasks in this domain.

Maintenance

ActivityInactive
ResponsivenessNo issues

Resources

Related MCP Connectors

Related MCP Servers

  • address-intel-api

    TKtokyo
    F
    license
    Not graded
    quality
    D
    maintenance
    Provides counterparty risk checks for any EVM address, returning malicious-history flags, tiered risk scoring, and plain-language summaries via x402 payment.
    -
  • traql MCP server by traql

    traql MCP serverofficial

    traql
    A
    license
    A
    quality
    A
    maintenance
    Enables AI agents to perform AML and compliance risk scoring for crypto addresses and transactions on Ethereum, BSC, TRON, TON, and Bitcoin, returning 0–100 risk scores, bands, flags, and detailed signals.
    2
    50 npm
    MIT

  • web3-risk-mcp

    MelvTheGoat
    A
    license
    A
    quality
    B
    maintenance
    Enables AI assistants to assess the risk of crypto wallets, tokens, and smart contracts by providing read-only on-chain analysis, 0-100 risk scoring with explanations, fund tracing, and contract inspection before interaction.
    6
    MIT

Appeared in Searches