← 返回 Skills 市场
bryan-cmc

Crypto Research using CoinMarketCap MCP

作者 CoinMarketCap · GitHub ↗ · v1.0.0
cross-platform ✓ 安全检测通过
426
总下载
0
收藏
1
当前安装
1
版本数
在 OpenClaw 中安装
/install crypto-research-using-cmc-mcp
功能描述
Performs comprehensive due diligence on a cryptocurrency using CoinMarketCap MCP data. Use when users ask about a specific coin beyond just its price. This i...
使用说明 (SKILL.md)

Crypto Research Skill

Perform comprehensive due diligence on any cryptocurrency by systematically gathering and analyzing data from multiple CMC MCP tools.

Prerequisites

Before starting research, verify the CMC MCP tools are available. If tools fail or return connection errors, ask the user to set up the MCP connection:

{
  "mcpServers": {
    "cmc-mcp": {
      "url": "https://mcp.coinmarketcap.com/mcp",
      "headers": {
        "X-CMC-MCP-API-KEY": "your-api-key"
      }
    }
  }
}

Get your API key from https://pro.coinmarketcap.com/login

Core Principle

Thorough research requires looking at a token from multiple angles. Fetch all relevant data before forming conclusions. Surface both green flags and red flags.

Research Workflow

Step 1: Identify the Token

Call search_cryptos with the token name/symbol to get the CMC ID. If multiple results, clarify with the user which one they mean.

Step 2: Basic Information

Call get_crypto_info to get:

  • Project description and category
  • Launch date
  • Website, social links, documentation
  • Tags (DeFi, Layer 1, Meme coin, etc.)

Step 3: Market Data

Call get_crypto_quotes_latest to get:

  • Current price and market cap
  • 24h, 7d, 30d, 90d, 1y price changes
  • Trading volume and volume change
  • Circulating supply vs max supply
  • Market cap rank

Step 4: Holder Analysis

Call get_crypto_metrics to get:

  • Address distribution by holding value ($0-1k, $1k-100k, $100k+)
  • Whale concentration (% held by top holders)
  • Holder behavior (traders vs cruisers vs long-term holders)

Step 5: Technical Analysis

Call get_crypto_technical_analysis to get:

  • Moving averages (7d, 30d, 200d SMA/EMA)
  • RSI (oversold \x3C 30, overbought > 70)
  • MACD signal
  • Fibonacci levels and pivot points

Step 6: Recent News

Call get_crypto_latest_news with limit 5-10 to get recent headlines and sentiment.

Step 7: Deep Dive (if needed)

Call search_crypto_info to answer specific questions about the token's technology, use case, or mechanics.

Analysis Framework

After gathering data, evaluate across these dimensions:

Fundamentals

  • What problem does it solve?
  • Is there a working product?
  • How does it compare to competitors?
  • Is the use case sustainable?

Tokenomics

  • What % of max supply is circulating?
  • Is there inflation or deflation?
  • Are there large unlocks coming?
  • How concentrated is ownership?

Market Position

  • Market cap rank and trajectory
  • Volume relative to market cap (healthy turnover?)
  • Price trend (accumulation or distribution?)

Risk Factors

Red flags and why they matter:

  • Extreme whale concentration (>10% held by few addresses): Large holders can dump and crash price instantly
  • Low holder count relative to market cap: Thin holder base means price is easily manipulated
  • Declining holder numbers: Smart money may be exiting while retail holds bags
  • Negative news sentiment: Ongoing negative coverage often precedes further declines
  • Price down >80% from ATH with no recovery: May indicate fundamental problems, not just market cycles
  • Very low trading volume: Hard to exit positions without significant slippage

Green flags and why they matter:

  • Growing holder base: Organic adoption suggests real demand, not manufactured hype
  • High % of long-term holders: Conviction from holders who have done research, less sell pressure
  • Healthy distribution across address sizes: Resilient to any single actor manipulating price
  • Active development and news flow: Team is shipping, project is alive and evolving
  • Strong community engagement: Network effects build value and create sustainable demand

Report Structure

Present findings in this format:

## [Token Name] Research Report

### Overview
- Category: [DeFi/Layer 1/Meme/etc.]
- Launched: [Date]
- Rank: #XX by market cap

### Market Data
- Price: $X.XX
- Market Cap: $X.XX B
- 24h Volume: $X.XX M
- Performance: 24h X.X% | 7d X.X% | 30d X.X% | 1y X.X%

### Supply
- Circulating: X.XX M (XX% of max)
- Max Supply: X.XX M

### Holder Analysis
- Total Addresses: X.XX M
- Whale Concentration: X.X%
- Long-term Holders: XX%
- Holder Trend: Growing/Stable/Declining

### Technical Outlook
- RSI: XX (oversold/neutral/overbought)
- Trend: Above/Below 200d MA
- Key Support: $X.XX
- Key Resistance: $X.XX

### Recent News
- [Headline 1]
- [Headline 2]
- ...

### Green Flags
- [List positive indicators]

### Red Flags
- [List concerns]

### Summary
[2-3 sentence synthesis of the research findings]

Important Notes

  • This is research, not financial advice
  • Always present both positive and negative findings
  • If data is missing or unavailable, note it explicitly
  • For very new tokens, some metrics may be limited

Handling Tool Failures

If individual tools fail during research:

  1. search_cryptos fails: Cannot proceed without token ID. Ask user to verify spelling or try the contract address.
  2. get_crypto_info fails: Skip Overview section, note "Project details unavailable" in report.
  3. get_crypto_quotes_latest fails: Report is incomplete without price data. Retry once, then note "Market data unavailable."
  4. get_crypto_metrics fails: Skip Holder Analysis section, note "Distribution data unavailable."
  5. get_crypto_technical_analysis fails: Skip Technical Outlook section, note "Technical analysis unavailable."
  6. get_crypto_latest_news fails: Skip Recent News section, proceed with other data.

Always complete the report with available data rather than abandoning the research entirely.

安全使用建议
This skill is an instruction-only connector that uses CoinMarketCap MCP tools to compile a research report. Before installing, confirm that your agent's CMC MCP integration is configured with an API key you trust (the SKILL.md tells you how to set one up). The skill does not request other credentials or access to your files. Remember this is research, not financial advice—review the generated report yourself and do not share unrelated sensitive credentials with the agent.
功能分析
Type: OpenClaw Skill Name: crypto-research-using-cmc-mcp Version: 1.0.0 The skill bundle is classified as benign. The `SKILL.md` clearly defines its purpose as cryptocurrency research using specific CoinMarketCap (CMC) APIs. The `allowed-tools` list is restricted to CMC data retrieval functions, and the instructions for the AI agent consistently guide it to use these tools for data gathering and analysis. There is no evidence of prompt injection designed to subvert the agent, exfiltrate data, execute arbitrary commands, establish persistence, or interact with unauthorized network endpoints or local files. All content aligns with a legitimate, well-defined data analysis task.
能力评估
Purpose & Capability
Name/description match the actions in SKILL.md: it calls CMC MCP search/info/quotes/metrics/news/TA endpoints. No unrelated services, binaries, or credentials are requested.
Instruction Scope
Instructions are scoped to gathering and analyzing CMC MCP data, describing specific API calls to use and what to extract. They do not instruct reading arbitrary files, system state, or external endpoints beyond the MCP service, and they explicitly handle tool failures.
Install Mechanism
There is no install spec and no code files; this is instruction-only, so nothing is written to disk or downloaded by the skill itself.
Credentials
The skill does not declare required environment variables or credentials. The README shows how to configure the MCP connection (API key) which is appropriate and proportional for accessing CMC MCP data; no unrelated secrets are requested.
Persistence & Privilege
always is false and the skill does not request persistent system-level privileges or modify other skill configurations. Normal autonomous invocation is allowed (platform default) and appropriate for an integration-style skill.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install crypto-research-using-cmc-mcp
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /crypto-research-using-cmc-mcp 触发
  4. 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v1.0.0
- Initial release of the crypto-research skill for comprehensive due diligence on cryptocurrencies using CoinMarketCap MCP data. - Supports deep research workflows: market data, tokenomics, holder analysis, technical analysis, and latest news. - Uses multiple MCP tools for systematic data gathering. - Includes clear guidance for handling missing or unavailable data and provides a consistent report structure. - Designed for user-invocable research on any token beyond just price queries.
元数据
Slug crypto-research-using-cmc-mcp
版本 1.0.0
许可证
累计安装 1
当前安装数 1
历史版本数 1
常见问题

Crypto Research using CoinMarketCap MCP 是什么?

Performs comprehensive due diligence on a cryptocurrency using CoinMarketCap MCP data. Use when users ask about a specific coin beyond just its price. This i... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 426 次。

如何安装 Crypto Research using CoinMarketCap MCP?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install crypto-research-using-cmc-mcp」即可一键安装,无需额外配置。

Crypto Research using CoinMarketCap MCP 是免费的吗?

是的,Crypto Research using CoinMarketCap MCP 完全免费(开源免费),可自由下载、安装和使用。

Crypto Research using CoinMarketCap MCP 支持哪些平台?

Crypto Research using CoinMarketCap MCP 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。

谁开发了 Crypto Research using CoinMarketCap MCP?

由 CoinMarketCap(@bryan-cmc)开发并维护,当前版本 v1.0.0。

💬 留言讨论