为 AI Agent 准备的金融智能工具 —— 精心整理，而非原始数据。
Toolstem 是一个 MCP（模型上下文协议）服务器，它将原始金融市场数据转化为供 AI Agent 使用的精选合成情报。与仅仅暴露供应商 REST API 的透传包装器不同，每个 Toolstem 工具都会整合多个数据源、推导信号并预先计算 Agent 本来需要自己处理的数学指标。
一次调用。一个 Agent 友好的 JSON 响应。无需解析嵌套数组，无需跨端点拼接，无需处理空值检查的样板代码。
大多数金融 MCP 服务器为每个 API 端点暴露一个工具 —— 这迫使你的 Agent 进行 4-5 次顺序调用、编写胶水代码并分析原始数据结构。Toolstem 的构建方式不同：
并行数据获取 —— 每个工具都会同时向多个源发起请求。
推导信号 —— 从原始数字计算出人类可读的建议，如 UNDERVALUED（低估）、STRONG（强劲）、ACCELERATING（加速）。
预计算数学指标 —— CAGR（复合年均增长率）、同比（YoY）增长、利润率趋势、距离 52 周高/低点的距离、自由现金流（FCF）收益率等已包含在响应中。
扁平、可预测的模式 —— 没有深度嵌套的供应商特性泄露到 Agent 的提示词中。
优雅降级 —— 如果某个上游端点失败，响应的其余部分仍会返回，失败项以 null 填充。
Related MCP server: TickerAPI
get_stock_snapshot全面的股票概览，将报价、概况、DCF 估值和评级整合为单一响应。
输入：
{
"symbol": "AAPL"
}示例输出（已截断）：
{
"symbol": "AAPL",
"company_name": "Apple Inc.",
"sector": "Technology",
"industry": "Consumer Electronics",
"exchange": "NASDAQ",
"price": {
"current": 178.52,
"change": 2.34,
"change_percent": 1.33,
"day_high": 179.80,
"day_low": 175.10,
"year_high": 199.62,
"year_low": 130.20,
"distance_from_52w_high_percent": -10.57,
"distance_from_52w_low_percent": 37.11
},
"valuation": {
"market_cap": 2780000000000,
"market_cap_readable": "$2.78T",
"pe_ratio": 29.5,
"dcf_value": 195.20,
"dcf_upside_percent": 9.35,
"dcf_signal": "FAIRLY VALUED"
},
"rating": {
"score": 4,
"recommendation": "Buy",
"dcf_score": 5,
"roe_score": 4,
"roa_score": 4,
"de_score": 5,
"pe_score": 3
},
"fundamentals_summary": {
"beta": 1.28,
"avg_volume": 55000000,
"employees": 164000,
"ipo_date": "1980-12-12",
"description": "Apple Inc. designs, manufactures..."
},
"meta": {
"source": "Toolstem via Financial Modeling Prep",
"timestamp": "2026-04-17T18:30:00Z",
"data_delay": "End of day"
}
}推导字段（原始 API 中不存在）：
dcf_signal —— 如果 DCF 上行空间 > 10% 则为 UNDERVALUED，如果 < -10% 则为 OVERVALUED，否则为 FAIRLY VALUED。
market_cap_readable —— 人类友好的格式，如 $2.78T、$450.2B、$12.5M。
distance_from_52w_high_percent / distance_from_52w_low_percent —— 预计算的区间位置。
get_company_metrics深入的基本面分析 —— 盈利能力、财务健康状况、现金流、增长和每股指标 —— 由 5 个财务报表端点合成。
输入：
{
"symbol": "AAPL",
"period": "annual"
}period 接受 annual（默认）或 quarter。
示例输出（已截断）：
{
"symbol": "AAPL",
"period": "annual",
"latest_period_date": "2025-09-30",
"profitability": {
"revenue": 394328000000,
"revenue_readable": "$394.3B",
"revenue_growth_yoy": 7.8,
"net_income": 96995000000,
"net_income_readable": "$97.0B",
"gross_margin": 46.2,
"operating_margin": 31.5,
"net_margin": 24.6,
"roe": 160.5,
"roa": 28.3,
"roic": 56.2,
"margin_trend": "EXPANDING"
},
"financial_health": {
"total_debt": 111000000000,
"total_cash": 65000000000,
"net_debt": 46000000000,
"debt_to_equity": 1.87,
"current_ratio": 1.07,
"interest_coverage": 41.2,
"health_signal": "STRONG"
},
"cash_flow": {
"operating_cash_flow": 118000000000,
"free_cash_flow": 104000000000,
"free_cash_flow_readable": "$104.0B",
"fcf_margin": 26.4,
"capex": 14000000000,
"dividends_paid": 15000000000,
"buybacks": 89000000000,
"fcf_yield": 3.7
},
"growth_3yr": {
"revenue_cagr": 8.2,
"net_income_cagr": 10.1,
"fcf_cagr": 9.5,
"growth_signal": "ACCELERATING"
},
"per_share": {
"eps": 6.42,
"book_value_per_share": 3.99,
"fcf_per_share": 6.89,
"dividend_per_share": 0.96,
"payout_ratio": 14.9
},
"meta": {
"source": "Toolstem via Financial Modeling Prep",
"timestamp": "2026-04-17T18:30:00Z",
"periods_analyzed": 3,
"data_delay": "End of day"
}
}推导字段：
margin_trend —— 基于净利润率序列方向的 EXPANDING（扩张）、STABLE（稳定）或 CONTRACTING（收缩）。
health_signal —— 根据债务权益比、流动比率和利息保障倍数得出的 STRONG（强劲）、ADEQUATE（充足）或 WEAK（疲软）。
growth_signal —— 基于同比（YoY）增长轨迹的 ACCELERATING（加速）、STEADY（平稳）或 DECELERATING（减速）。
revenue_cagr、net_income_cagr、fcf_cagr —— 分析窗口内的复合年均增长率。
fcf_margin、fcf_yield —— 由现金流 + 收入 + 市值预计算得出。
npm install -g toolstem-mcp-server作为 stdio 服务器运行：
FMP_API_KEY=your_key_here toolstem-mcp-server作为 HTTP（流式 HTTP 传输）服务器运行：
FMP_API_KEY=your_key_here PORT=3000 toolstem-mcp-server --http添加到你的 claude_desktop_config.json 中：
{
"mcpServers": {
"toolstem": {
"command": "npx",
"args": ["-y", "toolstem-mcp-server"],
"env": {
"FMP_API_KEY": "your_fmp_api_key"
}
}
}
}Toolstem 发布在 Smithery 上，可一键安装到支持的 MCP 客户端中。
作为 toolstem-financial-data Actor 在 Apify Store 上提供。通过输入从你的 Apify 工作流中调用它：
{
"tool": "get_stock_snapshot",
"symbol": "AAPL"
}或
{
"tool": "get_company_metrics",
"symbol": "AAPL",
"period": "annual"
}结果会被推送到默认数据集。该 Actor 通过 Apify 的按事件付费模型对每次工具调用进行收费。
构建并运行 HTTP 传输：
npm install
npm run build
FMP_API_KEY=your_key npm run start:http你的 MCP 客户端随后可以连接到 POST http://your-host:3000/mcp。
变量 | 必需 | 描述 |
| 是 | Financial Modeling Prep API 密钥。请在 financialmodelingprep.com 获取。 |
| 否 | HTTP 传输端口。默认为 |
npm install
npm run dev # stdio, hot reload via tsx
npm run build # TypeScript -> dist/
npm start # run built stdio server
npm run start:http # run built HTTP serversrc/
├── index.ts # MCP server entry (stdio + Streamable HTTP)
├── actor.ts # Apify Actor entry
├── services/
│ └── fmp.ts # Financial Modeling Prep API client
├── tools/
│ ├── get-stock-snapshot.ts
│ └── get-company-metrics.ts
└── utils/
└── formatting.ts # Market cap formatting, CAGR, trend signals所有 FMP 端点都被封装在一个 FmpClient 类中。工具实现通过 Promise.all 并行扇出到多个客户端方法，然后合成合并后的结果。
MIT —— 参见 LICENSE。
Toolstem —— 为 Agent 原生经济提供的精选金融智能。
Side-by-side comparison of 2-5 companies across price, valuation (P/E, P/B, P/S, EV/EBITDA, DCF), profitability (margins, ROE, ROA, ROIC), financial health (D/E, current ratio, interest coverage), growth (revenue and earnings YoY), dividends, and analyst ratings. Returns derived rankings showing which company leads each dimension — lowest_pe, highest_margin, strongest_balance_sheet, best_growth, most_undervalued, highest_rated. Use this for investment comparisons, competitive analysis, or evaluating alternatives in the same sector.
| Name | Required | Description | Default |
|---|---|---|---|
| symbols | Yes | 2-5 stock ticker symbols to compare (e.g., ["AAPL", "MSFT", "GOOGL"]) |
| Name | Required | Description |
|---|---|---|
| symbols_compared | Yes | |
| comparison_date | Yes | |
| companies | Yes | |
| rankings | Yes | |
| meta | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, destructiveHint=false, idempotentHint=true, openWorldHint=true. The description aligns fully, detailing the read-only operation and output format (derived rankings). No contradictions, and the description adds significant behavioral context (categories of metrics, derived rankings) beyond annotations.
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?
Three sentences: first states core purpose, second lists all metric categories, third gives use cases. Front-loaded, no filler, every sentence adds value.
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 the tool's complexity (many metrics and derived rankings) and the presence of an output schema, the description is complete. It covers input constraints (2-5 symbols), output nature (derived rankings), and typical use cases. No gaps for an agent to misuse.
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% (the symbols parameter has a detailed description including example). The tool description restates '2-5 companies' but adds no new semantics beyond the schema. Baseline 3 applies.
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 explicitly states the tool performs side-by-side comparison of 2-5 companies across price, valuation, profitability, financial health, growth, dividends, and analyst ratings. It also lists derived rankings (lowest_pe, etc.). This clearly distinguishes from siblings get_company_metrics (likely single company) and get_stock_snapshot (likely a quick overview).
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 explicit use cases: 'Use this for investment comparisons, competitive analysis, or evaluating alternatives in the same sector.' It does not explicitly state when not to use or name alternatives, but the context is clear and actionable.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Deep financial analysis including profitability, financial health, cash flow, growth (3-year CAGR), and per-share metrics. Synthesizes key metrics, financial ratios, income statement, balance sheet, and cash flow statement into one agent-ready response with derived signals: margin_trend (EXPANDING/STABLE/CONTRACTING), health_signal (STRONG/ADEQUATE/WEAK), and growth_signal (ACCELERATING/STEADY/DECELERATING). Use this for fundamental analysis, financial health checks, or when you need to understand a company's trajectory.
| Name | Required | Description | Default |
|---|---|---|---|
| symbol | Yes | Stock ticker symbol (e.g., AAPL, MSFT, TSLA) | |
| period | No | Reporting period. Defaults to annual. | annual |
| Name | Required | Description |
|---|---|---|
| symbol | Yes | |
| period | Yes | |
| latest_period_date | Yes | |
| profitability | Yes | |
| financial_health | Yes | |
| cash_flow | Yes | |
| growth_3yr | Yes | |
| per_share | Yes | |
| meta | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, destructiveHint=false, idempotentHint=true, covering safety. The description adds value by explaining derived signals and output structure, but doesn't disclose additional behavioral traits beyond what annotations provide.
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?
Two sentences, front-loaded with key content. Each sentence contributes: first lists included metrics, second explains output and use cases. No unnecessary words.
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 the presence of an output schema (handling return values), complete schema coverage, and annotations covering safety, the description provides sufficient context about purpose, usage, and derived signals. It is thorough for a tool of this complexity.
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%, so the schema already documents both parameters adequately. The description does not add extra parameter detail beyond what is in the schema, aligning with the baseline of 3.
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 it provides deep financial analysis and synthesizes key metrics, ratios, and statements into an agent-ready response. It distinguishes from siblings (compare_companies and get_stock_snapshot) by emphasizing depth and derived signals.
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?
Explicitly recommends use for fundamental analysis, financial health checks, or understanding a company's trajectory. While it doesn't directly mention alternatives, sibling tool names and the focus on depth imply when not to use.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get a comprehensive stock snapshot including real-time price, valuation metrics, DCF analysis, and analyst ratings for any publicly traded company. Returns curated, agent-ready data synthesized from multiple sources in a single call — includes derived signals like dcf_signal (UNDERVALUED/FAIRLY VALUED/OVERVALUED), human-readable market cap, and 52-week range distance. Use this when you need a quick overview of a stock before digging into financials.
| Name | Required | Description | Default |
|---|---|---|---|
| symbol | Yes | Stock ticker symbol (e.g., AAPL, MSFT, TSLA) |
| Name | Required | Description |
|---|---|---|
| symbol | Yes | |
| company_name | Yes | |
| sector | Yes | |
| industry | Yes | |
| exchange | Yes | |
| price | Yes | |
| valuation | Yes | |
| rating | Yes | |
| fundamentals_summary | Yes | |
| meta | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already indicate readOnlyHint=true, destructiveHint=false, idempotentHint=true, and openWorldHint=true. The description adds behavioral context by explaining the tool synthesizes data from multiple sources, returns derived signals (dcf_signal), and provides curated agent-ready data. This adds value beyond the annotations.
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 concise, consisting of three focused sentences. The first sentence states the main purpose, the second lists key output components, and the third provides usage guidance. No redundant or irrelevant information.
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 the tool's simplicity (one parameter), presence of output schema, and rich annotations, the description sufficiently covers the tool's functionality, output highlights, and usage context. It explains derived signals and the nature of the data, making it complete for an agent to understand and invoke correctly.
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 the single required parameter 'symbol' (ticker). The description does not add additional semantic information about the parameter beyond what the schema already provides. With full schema coverage, a 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 provides a comprehensive stock snapshot including real-time price, valuation metrics, DCF analysis, and analyst ratings. It distinguishes from siblings by noting it is a quick overview before diving into financials, differentiating from get_company_metrics and compare_companies.
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 explicitly says 'Use this when you need a quick overview of a stock before digging into financials,' providing clear context for when to use the tool. It implies but does not explicitly state when not to use it or mention alternatives beyond the sibling context.
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.
v1.2.9screen_stocksv1.1.0compare_companiesscreen_stocksv1.0.0get_company_metricsget_stock_snapshotScored across 3 tools
The three tools are largely distinct: snapshot gives a quick overview, company_metrics provides deep financials, and compare_companies does side-by-side analysis. However, get_stock_snapshot and get_company_metrics both include valuation and financial data, so an agent could occasionally hesitate on which to call first.
All tool names follow a clear verb_noun pattern: get_stock_snapshot, get_company_metrics, compare_companies. The verb changes appropriately for the action, and there is no mixing of styles or vague naming.
Three tools is on the lean side but fits a focused stock-analysis server: overview, deep dive, and comparison. Each tool earns its place and the count feels sufficient rather than bloated.
The surface covers the core workflow: quick overview, fundamental analysis, and comparative screening. Minor gaps exist (e.g., no historical price data or explicit ticker search), but agents can accomplish most typical investment-analysis tasks without dead ends.
SEC filings and financial data for AI agents: 59 tools for statements, valuation and supply chains.
Real SEC, 13F, insider, congress & macro data your AI agent can cite. Hosted MCP, 24 tools.
13-model stock valuation engine for AI agents - fair values for 5,900+ US stocks, updated daily.
Realtime financial context for AI agents: what changed, who is affected, and what to watch next. One suite covering news, events, guidance, filing changes, sentiment, stakeholders, and alerts. Information-efficient responses with evidence for every result. First-class point-in-time safety for backtests. Pairs well with web search and a market-data API. All data is our own.
