ethereum-tools
Claude MCP를 위한 Ethereum 도구
Claude AI 내에서 Model Context Protocol(MCP)을 사용하여 Ethereum 블록체인을 직접 분석할 수 있는 포괄적인 툴킷입니다.
특징
스마트 계약 감사 : 보안 문제에 대한 계약을 분석하고, 소스 코드를 검증하고, 토큰 표준을 감지합니다.
지갑 분석 : ETH 잔액, 토큰 보유량, 거래 내역 확인
수익성 추적 : 토큰 및 거래 전반에 걸친 지갑 수익/손실 계산
블록체인 데이터 : 간단한 명령으로 온체인 데이터를 가져오고 분석합니다.
토큰 분석 : 포괄적인 토큰 세부 정보, 가격 내역 및 거래 패턴을 확인하세요.
Related MCP server: Base MCP Server
설치
필수 조건
Node.js v16+
데스크톱용 클로드
무료 API 키:
설정 단계
이 저장소를 복제하세요:
지엑스피1
종속성 설치:
npm install구성을 생성하세요:
mcp.json.example``mcp.json으로 복사합니다.API 키와 올바른 파일 경로를 포함하도록
mcp.json편집하세요.
{ "mcpServers": { "ethereum-tools": { "command": "node", "args": ["YOUR_ABSOLUTE_PATH_TO/main.js"], "env": { "ETH_RPC_URL": "https://eth.llamarpc.com", "MORALIS_API_KEY": "your_moralis_api_key", "ETHERSCAN_API_KEY": "your_etherscan_api_key", "CODEX_API_KEY": "your_codex_api_key" } } } }데스크톱에 Claude 구성:
Windows에서:
%APPDATA%\Claude\claude_desktop_config.json생성/편집합니다.mcp.json파일의 내용을 이 구성에 복사하세요.
사용 가능한 도구
계약 분석
auditContract(address: "0x..."): 스마트 계약에 대한 보안 감사를 수행합니다.
잔액 및 토큰
getEthBalance(address: "0x..."): ETH 잔액을 가져옵니다.getTransactionCount(address: "0x..."): 거래 횟수(nonce)를 가져옵니다.getTokensBalance(address: "0x...", chain: "eth", excludeSpam: true): 모든 토큰 잔액을 가져옵니다.
수익성
getWalletPnl(address: "0x...", chain: "eth"): 지갑 수익/손실 분석
토큰 분석
getTokenInfo(address: "0x...", networkId: 1): 이름, 기호, 공급을 포함한 기본 토큰 정보를 가져옵니다.getTokenPriceHistory(address: "0x...", networkId: 1, days: 7, resolution: "1D"): 과거 가격 데이터 가져오기analyzeToken(address: "0x...", networkId: 1, days: 30): 변동성 및 거래 패턴을 포함한 포괄적인 토큰 분석을 수행합니다.
유용
add(a: 1, b: 2): 간단한 유틸리티 함수 예제
문제 해결
일반적인 문제:
환경 변수를 찾을 수 없습니다 .
mcp.json에 API 키가 올바르게 설정되어 있는지 확인하세요.공급자 오류 : ETH_RPC_URL이 유효하고 액세스 가능한지 확인하세요.
경로 오류 : Windows에서 적절한 이스케이프(
\\)를 사용하여 전체 절대 경로를 사용하고 있는지 확인하세요.Codex API 문제 : Codex API 키가 유효하고 토큰 데이터에 액세스할 수 있는 권한이 있는지 확인하세요.
개발
새로운 도구를 추가하려면:
tools/디렉토리에 파일을 생성하거나 수정합니다.main.js에 도구를 등록하세요변경 사항을 확인하려면 데스크톱용 Claude를 다시 시작하세요.
특허
이 프로젝트는 MIT 라이선스에 따라 라이선스가 부여되었습니다.
감사의 말
Anthropic의 모델 컨텍스트 프로토콜(MCP)
Available Tools
11 toolsaddD
| Name | Required | Description | Default |
|---|---|---|---|
| a | Yes | ||
| b | Yes |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Tool has no description.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Tool has no description.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Tool has no description.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Tool has no description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Tool has no description.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Tool has no description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
analyzeTokenD
| Name | Required | Description | Default |
|---|---|---|---|
| address | Yes | ||
| networkId | No | Network ID (1 for Ethereum, 101 for Solana) | |
| days | No | Number of days to analyze |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Tool has no description.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Tool has no description.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Tool has no description.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Tool has no description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Tool has no description.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Tool has no description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
auditContractD
| Name | Required | Description | Default |
|---|---|---|---|
| address | Yes | ||
| chain | No | eth |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Tool has no description.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Tool has no description.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Tool has no description.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Tool has no description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Tool has no description.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Tool has no description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
getEthBalanceD
| Name | Required | Description | Default |
|---|---|---|---|
| address | Yes |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Tool has no description.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Tool has no description.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Tool has no description.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Tool has no description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Tool has no description.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Tool has no description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
getTokenInfoD
| Name | Required | Description | Default |
|---|---|---|---|
| address | Yes | ||
| networkId | No | Network ID (1 for Ethereum, 101 for Solana) |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Tool has no description.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Tool has no description.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Tool has no description.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Tool has no description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Tool has no description.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Tool has no description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
getTokenPriceHistoryD
| Name | Required | Description | Default |
|---|---|---|---|
| address | Yes | ||
| networkId | No | Network ID (1 for Ethereum, 101 for Solana) | |
| days | No | Number of days of history | |
| resolution | No | Time resolution (e.g. 1D, 1H, 60) | 1D |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Tool has no description.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Tool has no description.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Tool has no description.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Tool has no description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Tool has no description.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Tool has no description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
getTokensBalanceD
| Name | Required | Description | Default |
|---|---|---|---|
| address | Yes | ||
| chain | No | eth | |
| excludeSpam | No |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Tool has no description.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Tool has no description.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Tool has no description.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Tool has no description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Tool has no description.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Tool has no description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
getTransactionCountD
| Name | Required | Description | Default |
|---|---|---|---|
| address | Yes |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Tool has no description.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Tool has no description.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Tool has no description.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Tool has no description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Tool has no description.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Tool has no description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
getWalletPnlD
| Name | Required | Description | Default |
|---|---|---|---|
| address | Yes | ||
| chain | No | eth |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Tool has no description.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Tool has no description.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Tool has no description.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Tool has no description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Tool has no description.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Tool has no description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
searchTwitterD
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | ||
| section | No | latest | |
| limit | No | ||
| min_retweets | No | ||
| min_likes | No | ||
| min_replies | No | ||
| start_date | No | ||
| end_date | No | ||
| language | No |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Tool has no description.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Tool has no description.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Tool has no description.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Tool has no description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Tool has no description.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Tool has no description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
twitterSearchHelpD
| Name | Required | Description | Default |
|---|---|---|---|
| topic | No | general |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Tool has no description.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Tool has no description.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Tool has no description.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Tool has no description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Tool has no description.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Tool has no description.
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.
11 tool updates
- First observed
add - First observed
analyzeToken - First observed
auditContract - First observed
getEthBalance - First observed
getTokenInfo - First observed
getTokenPriceHistory - First observed
getTokensBalance - First observed
getTransactionCount - First observed
getWalletPnl - First observed
searchTwitter - First observed
twitterSearchHelp
TDQS
Scored across 11 tools
Most tools have distinct purposes targeting different Ethereum-related functions like balances, token analysis, and contract auditing, but there is some overlap between 'searchTwitter' and 'twitterSearchHelp' which could cause confusion. The lack of descriptions exacerbates potential ambiguity for tools like 'add' which has no clear domain context.
Naming is inconsistent with a mix of camelCase ('analyzeToken', 'getEthBalance') and snake_case ('get_token_info' implied but not used), and vague verbs like 'add' without a clear pattern. While some tools follow a 'getX' structure, the overall convention is mixed and lacks predictability.
With 11 tools, the count is reasonable for an Ethereum-focused server, covering areas like wallet management, token analysis, and social media search. It's slightly high but well within typical bounds for such a domain without feeling overly heavy or thin.
The tool set covers key Ethereum operations like balance checks, token info, and contract auditing, but has notable gaps such as transaction sending, smart contract interaction beyond auditing, and wallet creation. The inclusion of Twitter search tools feels tangential and incomplete for core blockchain functionality.
Maintenance
Related MCP Connectors
Claude-ready DeFi MCP — risk-scored yields, profit sims & whale tracking across 86 blockchains
Claude-powered AI tools: research, write, code, analyze, translate, debate, pitch, score, and more.
Blockchain analytics API for AI agents. Smart Money signals, wallet profiling, token analytics.
Blockchain analytics API for AI agents. Smart Money signals, wallet profiling, token analytics.
Related MCP Servers
- AlicenseBqualityDmaintenanceEnables Claude to interact with Ethereum nodes, allowing users to check ENS token balances, view smart contract code, and decode transactions through natural language.51MIT

Base MCP Serverofficial
AlicenseNot gradedqualityFmaintenanceProvides onchain tools for Claude AI to interact with the Base blockchain and Coinbase API, enabling wallet management, fund transfers, and smart contract deployment.148 npm350MIT- AlicenseBqualityDmaintenanceProvides Claude with access to Ethereum and EVM-compatible blockchain operations, enabling wallet management, transaction handling, contract interactions, and blockchain queries through natural language.43558 npm10MIT
- FlicenseBqualityDmaintenanceA local Ethereum contract analysis tool that retrieves on-chain information, integrates Etherscan and RPC data, and automatically executes view functions to provide comprehensive contract insights.23-