Octagon MCP 服务器通过与 Octagon Market Intelligence API 集成，提供专门的人工智能金融研究和分析，使用户能够轻松分析和提取来自 Claude Desktop 和其他流行 MCP 客户端中的公开文件、收益电话会议记录、财务指标、股票市场数据和广泛的私人市场交易的详细见解。
✅ 专门针对公开市场数据的AI 代理
SEC 文件分析和数据提取（8000 多家上市公司 10-K、10-Q、8-K、20-F、S-1）
收益电话会议记录分析（10 年历史和当前）
财务指标和比率分析（10 年历史和当前）
股票市场数据访问（超过 10,000 个活跃股票代码，每日历史和当前数据）
✅ 专门针对私人市场数据的AI 代理
私营公司研究（300 多万家公司）
融资轮次和风险投资研究（50 万笔以上交易）
并购及IPO交易研究（200万+笔交易）
债务交易研究（100万+笔交易）
✅ 专门用于深入研究的AI 代理
Web 抓取功能（json、csv、python 脚本）
全面的深度研究工具
Related MCP server: FundzWatch MCP Server
要使用 Octagon MCP，您需要：
在Octagon注册免费账户
登录后，从左侧菜单导航至API Keys
生成新的 API 密钥
在您的配置中使用此 API 密钥作为OCTAGON_API_KEY值
在安装或运行 Octagon MCP 之前，您需要在系统上安装npx （随 Node.js 和 npm 提供）。
安装 Homebrew （如果你没有）：
/bin/bash -c "$(curl -fsSL https://raw.githubusercontent.com/Homebrew/install/HEAD/install.sh)"安装 Node.js（包括 npm 和 npx）：
brew install node这将安装最新版本的 Node.js、npm 和 npx。
验证安装：
node -v
npm -v
npx -v下载 Node.js 安装程序：
前往https://nodejs.org/并下载适用于 Windows 的 LTS 版本。
运行安装程序并按照提示操作。这将安装 Node.js、npm 和 npx。
**验证安装：**打开命令提示符并运行：
node -v
npm -v
npx -v如果您看到所有三个的版本号，则可以继续下面的安装步骤。
要为 Claude Desktop 配置 Octagon MCP：
打开 Claude 桌面
前往“设置”>“开发者”>“编辑配置”
将以下内容添加到您的claude_desktop_config.json中（将your-octagon-api-key替换为您的 Octagon API 密钥）：
{
"mcpServers": {
"octagon-mcp-server": {
"command": "npx",
"args": ["-y", "octagon-mcp@latest"],
"env": {
"OCTAGON_API_KEY": "YOUR_API_KEY_HERE"
}
}
}
}重新启动 Claude 以使更改生效
配置 Cursor Desktop 🖥️ 注意：需要 Cursor 版本 0.45.6+
要在 Cursor 中配置 Octagon MCP：
打开游标设置
前往“功能”>“MCP 服务器”
点击“+ 添加新的 MCP 服务器”
输入以下内容：
名称：“octagon-mcp”（或您喜欢的名称）
类型：“命令”
命令： env OCTAGON_API_KEY=your-octagon-api-key npx -y octagon-mcp
如果您使用的是 Windows 并且遇到问题，请尝试
cmd /c "set OCTAGON_API_KEY=your-octagon-api-key && npx -y octagon-mcp"
将your-octagon-api-key替换为您的 Octagon API 密钥。
添加后，刷新 MCP 服务器列表即可查看新工具。Composer Agent 会在适当时自动使用 Octagon MCP，但您可以通过描述您的投资研究需求来明确请求。通过 Command+L (Mac) 访问 Composer，选择提交按钮旁边的“代理”，然后输入您的查询。
将其添加到您的./codeium/windsurf/model_config.json ：
{
"mcpServers": {
"octagon-mcp-server": {
"command": "npx",
"args": ["-y", "octagon-mcp@latest"],
"env": {
"OCTAGON_API_KEY": "YOUR_API_KEY_HERE"
}
}
}
}env OCTAGON_API_KEY=your_octagon_api_key npx -y octagon-mcpnpm install -g octagon-mcp有关使用 Octagon 代理的全面文档，请访问我们的官方文档： https://docs.octagonagents.com
文档包括：
详细 API 参考
代理特定查询指南
示例和用例
投资研究的最佳实践
每个工具都使用一个接受自然语言查询的prompt参数。请在提示中包含所有相关详细信息。
从 SEC 文件中提取信息。
例子：
What was Apple's gross margin percentage from their latest 10-Q filing?分析收益电话会议记录。
例子：
What did NVIDIA's CEO say about AI chip demand in their latest earnings call?检索财务指标和比率。
例子：
Calculate the price-to-earnings ratio for Tesla over the last 4 quarters访问股票市场数据。
例子：
How has Apple's stock performed compared to the S&P 500 over the last 6 months?研究私人公司信息。
例子：
What is the employee count and funding history for Anthropic?研究初创企业融资轮次和风险投资。
例子：
What was OpenAI's latest funding round size, valuation, and key investors?研究并购和IPO交易。
例子：
What was the acquisition price when Microsoft acquired GitHub?用于查找投资者信息的专门数据库代理。
例子：
What is the latest investment criteria of Insight Partners?用于分析私人债务、借款人和贷款人的专门数据库代理。
例子：
List all the debt activities from borrower American Tower从任何公共网站提取数据。
例子：
Extract property prices and square footage data from zillow.com/san-francisco-ca/对任何主题进行全面研究。
例子：
Research the financial impact of Apple's privacy changes on digital advertising companies' revenue and margins“亚马逊 2023 年第四季度的收入和净收入是多少？”
“分析特斯拉过去3年的研发支出趋势。”
“NVIDIA 首席执行官在最近的财报电话会议上对 AI 芯片需求提供了什么指导？”
“比较前五大半导体公司的市盈率、市销率和企业价值/息税折旧摊销前利润比率。”
“Anthropic 的最新一轮融资规模、估值和主要投资者是多少？”
“从 zillow.com/san-francisco-ca/ 提取所有数据字段”
“研究苹果隐私变化对数字广告公司收入和利润的财务影响”
“汇编 2024 年第四季度贷款机构 ING 集团的所有债务活动”
“过去 12 个月，Andreessen Horowitz 对人工智能初创公司进行了多少投资？”
API 密钥问题：确保您的 Octagon API 密钥在环境或配置文件中正确设置。
连接问题：确保与 Octagon API 的连接正常工作。
速率限制：如果遇到速率限制错误，请减少请求的频率。
env OCTAGON_API_KEY=your_octagon_api_key npx -y octagon-mcpnpm install -g octagon-mcp麻省理工学院
⭐ 如果您发现它有用，请为该 repo 加星标！
[COMPREHENSIVE MARKET INTELLIGENCE] Orchestrates all agents for comprehensive market intelligence analysis. Capabilities: Combines insights from SEC filings, earnings calls, financial metrics, stock data, institutional holdings, private company research, funding analysis, M&A transactions, investor intelligence, and debt analysis to provide holistic market intelligence. Best for: Complex research requiring multiple data sources and comprehensive analysis across public and private markets. Example queries: 'Retrieve year-over-year growth in key income-statement items for AAPL, limited to 5 records and filtered by period FY', 'Analyze the latest 10-K filing for AAPL and extract key financial metrics and risk factors', 'Retrieve the daily closing prices for AAPL over the last 30 days', 'Analyze AAPL's latest earnings call transcript and extract key insights about future guidance', 'Provide a comprehensive overview of Stripe, including its business model and key metrics', 'Retrieve the funding history for Stripe, including all rounds and investors'.
| Name | Required | Description | Default |
|---|---|---|---|
| prompt | Yes | Your natural language query or request for the agent |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden. While it mentions the tool 'orchestrates all agents' and lists data sources, it doesn't disclose critical behavioral traits like whether this is a read-only operation, potential rate limits, authentication requirements, response format, or error handling. The description focuses on capabilities rather than operational behavior.
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?
The description is front-loaded with purpose and capabilities, but becomes verbose with the lengthy list of data sources and multiple example queries. While all content is relevant, the example section could be more concise. The structure is logical but could be more efficiently organized.
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?
Given this is a complex orchestration tool with no annotations and no output schema, the description is insufficient. It doesn't explain what the tool returns, how results are structured, error conditions, or operational constraints. The example queries help but don't compensate for the lack of behavioral and output documentation needed for effective agent use.
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?
Schema description coverage is 100% with the single 'prompt' parameter well-documented as 'Your natural language query or request for the agent.' The description adds value through example queries that illustrate what constitutes a good prompt, but doesn't provide additional parameter-specific guidance beyond what the schema already states.
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?
The description clearly states the tool 'orchestrates all agents for comprehensive market intelligence analysis' and lists specific capabilities like SEC filings, earnings calls, financial metrics, etc. It distinguishes from siblings by emphasizing comprehensive multi-source analysis, though it doesn't explicitly name the sibling tools for comparison.
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?
The description provides clear context with 'Best for: Complex research requiring multiple data sources and comprehensive analysis across public and private markets.' It includes example queries that illustrate appropriate use cases. However, it doesn't explicitly state when NOT to use this tool or directly compare it to the sibling tools by name.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
[PUBLIC & PRIVATE MARKET INTELLIGENCE] A comprehensive agent that can utilize multiple sources for deep research analysis. Capabilities: Aggregate research across multiple data sources, synthesize information, and provide comprehensive investment research. Best for: Investment research questions requiring up-to-date aggregated information from the web. Example queries: 'Research the financial impact of Apple's privacy changes on digital advertising companies' revenue and margins', 'Analyze the competitive landscape in the cloud computing sector, focusing on AWS, Azure, and Google Cloud margin and growth trends', 'Investigate the factors driving electric vehicle adoption and their impact on battery supplier financials'.
| Name | Required | Description | Default |
|---|---|---|---|
| prompt | Yes | Your natural language query or request for the agent |
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 mentions capabilities like aggregation and synthesis, but lacks critical behavioral details such as rate limits, authentication requirements, data freshness guarantees, or potential costs. The description doesn't contradict annotations (since none exist), but provides insufficient operational context for a tool performing complex research.
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?
The description is moderately structured with capability lists, usage guidance, and examples, but could be more front-loaded. Some sentences like 'Capabilities: Aggregate research across multiple data sources, synthesize information, and provide comprehensive investment research' could be more efficiently integrated. The bracketed '[PUBLIC & PRIVATE MARKET INTELLIGENCE]' adds little value and disrupts flow.
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?
For a complex research tool with no annotations and no output schema, the description is incomplete. It doesn't explain what format the research results will take, whether they include citations or sources, how comprehensive the aggregation is, or any limitations on research scope. The examples help but don't compensate for missing behavioral and output context that an agent would need to use this tool effectively.
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?
The input schema has 100% description coverage for its single parameter ('prompt'), which is well-documented as 'Your natural language query or request for the agent'. The description adds value by providing example queries that illustrate appropriate prompt content, but doesn't add significant semantic information beyond what the schema already provides. With high schema coverage, the baseline score of 3 is appropriate.
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?
The description clearly states the tool's purpose as a comprehensive research agent that aggregates, synthesizes, and provides investment research using multiple data sources. It specifies the verb ('utilize multiple sources for deep research analysis') and resource ('investment research questions'), but doesn't explicitly differentiate from sibling tools like 'octagon-agent' or 'octagon-scraper-agent' beyond mentioning its comprehensive nature.
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?
The description provides clear context for when to use this tool: 'Best for: Investment research questions requiring up-to-date aggregated information from the web' and includes example queries. However, it doesn't explicitly state when NOT to use it or mention alternatives like the sibling tools, leaving some ambiguity about tool selection.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
[PUBLIC & PRIVATE MARKET INTELLIGENCE] Specialized agent for financial data extraction from investor websites. Capabilities: Extract structured financial data from investor relations websites, tables, and online financial sources. Best for: Gathering financial data from websites that don't have accessible APIs. Example queries: 'Extract all data fields from zillow.com/san-francisco-ca/', 'Extract all data fields from www.carvana.com/cars/'.
| Name | Required | Description | Default |
|---|---|---|---|
| prompt | Yes | Your natural language query or request for the agent |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full burden but provides minimal behavioral disclosure. It mentions 'financial data extraction' but doesn't describe rate limits, authentication needs, error handling, or what happens when extraction fails. The description doesn't contradict annotations since none exist, but it's insufficient for a tool performing web scraping operations.
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?
The description is reasonably concise with three focused sentences: purpose statement, capabilities, usage guidance, and examples. The bracketed '[PUBLIC & PRIVATE MARKET INTELLIGENCE]' adds some noise, but overall the structure is clear and front-loaded with the core purpose.
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?
For a web scraping tool with no annotations and no output schema, the description is incomplete. It doesn't explain what structured data format to expect, error conditions, rate limits, or authentication requirements. The examples help but don't compensate for missing behavioral and output information critical for an AI agent.
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?
The description doesn't mention the 'prompt' parameter at all, though schema description coverage is 100% with the parameter well-documented as 'Your natural language query or request for the agent'. The description's example queries imply what the prompt should contain, but adds minimal value beyond what the schema already provides.
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?
The description clearly states the tool's purpose as 'financial data extraction from investor websites' with specific capabilities like extracting structured data from tables and online financial sources. It distinguishes from siblings by specifying 'financial data' focus, though not explicitly contrasting with 'octagon-agent' or 'octagon-deep-research-agent'.
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?
The description provides clear context for when to use this tool: 'Best for: Gathering financial data from websites that don't have accessible APIs.' It gives two example queries showing practical applications. However, it doesn't explicitly state when NOT to use it or mention alternatives among sibling tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v1.0.0octagon-agentoctagon-companies-agentoctagon-deals-agentoctagon-debts-agentoctagon-financials-agentoctagon-funding-agentoctagon-investors-agentoctagon-sec-agentoctagon-stock-data-agentoctagon-transcripts-agentoctagon-companies-agentoctagon-deals-agentoctagon-debts-agentoctagon-deep-research-agentoctagon-financials-agentoctagon-funding-agentoctagon-investors-agentoctagon-scraper-agentoctagon-sec-agentoctagon-stock-data-agentoctagon-transcripts-agentScored across 3 tools
The tools have overlapping purposes, causing significant ambiguity. All three tools are described as providing comprehensive market intelligence, with octagon-agent and octagon-deep-research-agent both focusing on aggregated research across multiple sources, making it unclear when to choose one over the other. The descriptions do not clearly delineate distinct boundaries, leading to potential misselection.
The tool names follow a highly consistent pattern with the prefix 'octagon-' followed by a descriptive suffix ('agent', 'deep-research-agent', 'scraper-agent'). This uniform naming convention makes the tools easily identifiable and predictable, with no deviations in style or structure.
With only 3 tools, the count feels thin for the broad scope of 'comprehensive market intelligence' covering public and private markets. While the tools aim to cover multiple data sources and analyses, the limited number may not adequately support the complex workflows implied by the descriptions, bordering on under-scoped for the domain.
There are significant gaps in the tool surface for market intelligence. The tools focus on aggregation and scraping but lack dedicated operations for specific actions like updating data, deleting records, or managing user queries, which are essential for a complete CRUD lifecycle. This incompleteness could lead to agent failures in handling varied tasks.
Market data, financial statements, valuation, research, and news for investment workflows.
Company and market intelligence, news, enrichment, and agentic workflows for dealmakers.
Live market data, financial analysis, and portfolio research tools across 10,000+ tickers.
Private company data, entity-resolved news, targeted lists, and alternative signals for AI agents.
