Skip to main content
Glama
deenesjakoruzh
geddamsatish

FinanceExpert

by geddamsatish
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

mcp-stock-server (FinanceExpert)

Небольшой сервер Model Context Protocol, созданный с помощью FastMCP. Он предоставляет рыночные данные Yahoo Finance (через yfinance), чтобы ассистенты могли получать котировки, историю в формате CSV и текстовые графики цен в формате Unicode.

Требования

  • Python 3.11+

  • uv (рекомендуется) или другой способ установки зависимостей из pyproject.toml

Related MCP server: Yahoo Finance MCP Server

Настройка

cd mcp-stock-server
uv sync

Запуск (stdio)

Сервер использует протокол MCP через stdio (по умолчанию для mcp.run()):

uv run python server.py

Добавление в качестве MCP-сервера (Cursor)

  1. Откройте Cursor Settings → MCP (или отредактируйте ваш JSON-конфиг MCP — обычно это ~/.cursor/mcp.json в macOS/Linux).

  2. Зарегистрируйте stdio-сервер, рабочим каталогом которого является этот репозиторий, а команда запускает server.py.

Вариант А — uv run (рекомендуется)

Замените /absolute/path/to/mcp-stock-server на реальный путь, по которому вы клонировали репозиторий.

{
  "mcpServers": {
    "FinanceExpert": {
      "command": "uv",
      "args": ["run", "python", "server.py"],
      "cwd": "/absolute/path/to/mcp-stock-server"
    }
  }
}

После uv sync используются зафиксированные зависимости из uv.lock.

Вариант Б — Python из виртуального окружения проекта

Используйте этот вариант, если не хотите вызывать uv из MCP-клиента:

{
  "mcpServers": {
    "FinanceExpert": {
      "command": "/absolute/path/to/mcp-stock-server/.venv/bin/python",
      "args": ["server.py"],
      "cwd": "/absolute/path/to/mcp-stock-server"
    }
  }
}

Сначала создайте venv (из корня репозитория): uv sync (устанавливает зависимости в .venv).

  1. Сохраните конфигурацию и перезапустите Cursor (или перезагрузите MCP). В панели MCP вы должны увидеть FinanceExpert с инструментами get_stock_analysis, get_historical_prices и get_stock_price_chart.

Другие MCP-клиенты (например, Claude Code, редакторы с поддержкой MCP) используют тот же принцип: command + args + cwd для stdio-сервера.

Инструменты

Инструмент

Описание

get_stock_analysis

Сводка: текущая цена, 50-дневное среднее, рекомендация аналитиков (из Ticker.info).

get_historical_prices

Столбец close (цена закрытия) в формате CSV за последние days календарных дней (period=f"{days}d"). По умолчанию days=30.

get_stock_price_chart

ASCII/Unicode-график: заливка области, ось цен, даты начала/конца на временной оси и 8-ступенчатый спарклайн.

Параметры get_stock_price_chart

  • ticker — Тикер, например INTU, AAPL.

  • days — Используется, если period не указан: диапазон Yahoo Nd (календарные дни). По умолчанию 30.

  • period — Необязательная строка периода Yahoo; если задана, переопределяет days. Примеры: 10y, 5y, 1y, 6mo, ytd, max.

Примеры:

  • Последний месяц сессий (по календарным дням): days=30

  • Последние десять календарных лет (окно Yahoo): period="10y"

Рыночные данные поступают от Yahoo через yfinance; семантика соответствует yfinance history(period=...).

Отказ от ответственности

Котировки и история предоставляются только для ознакомления и не являются инвестиционным советом. Данные Yahoo могут задерживаться или содержать ошибки; для принятия решений проверяйте информацию независимо.

Available Tools

3 tools
get_historical_pricesC

Fetches historical closing prices for chart generation.

ParametersJSON Schema
NameRequiredDescriptionDefault
tickerYes
daysNo

Output Schema

ParametersJSON Schema
NameRequiredDescription
resultYes

TDQS

C2.9/5.0
Behavior2/5

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

No annotations are provided, so description must disclose behavioral traits. It does not mention whether data is cached, any limits on 'days' parameter, or output format beyond 'closing prices'. No contradiction with annotations.

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?

Description is one concise sentence, front-loaded with purpose. No fluff, but could be longer for completeness.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given an output schema exists, return values are covered. However, no guidance on parameter ranges or timezone for days, and no usage context for how this relates to chart generation. Incomplete for a tool with zero annotations.

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

Parameters3/5

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

Schema description coverage is 0%, so description should compensate. It adds no detail about 'ticker' or 'days' beyond their names. Baseline is 3 due to absence of param info in description.

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 fetches historical closing prices for chart generation, specifying the action (fetch), resource (historical prices), and purpose (chart generation). However, it does not differentiate from sibling tools like get_stock_price_chart or get_stock_analysis.

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 siblings. It does not mention prerequisites, alternatives, or contexts where this tool is preferred.

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

get_stock_analysisA

Fetches real-time stock price, 50-day average, and analyst recommendations.

ParametersJSON Schema
NameRequiredDescriptionDefault
tickerYes

Output Schema

ParametersJSON Schema
NameRequiredDescription
resultYes

TDQS

A3.5/5.0
Behavior3/5

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

No annotations are provided, so the description carries full burden. It indicates the tool fetches data (non-destructive), but does not disclose any potential latency, rate limits, or data freshness. The output schema exists but is not referenced; description could hint at what fields are returned beyond what's in schema.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise at one sentence, front-loading the key output fields. Every phrase adds value, with no waste.

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 has one simple parameter and an output schema, the description could be more complete by adding a note about the ticker format or data source. It is adequate but lacks some contextual details like time zone or data provider.

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

Parameters3/5

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

Schema description coverage is 0% (no description for the parameter), so the description must compensate. It does not explain what the ticker parameter expects (e.g., format, examples). However, the parameter has no enums and is simple, so the gap is small. Baseline 3 is appropriate.

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 it fetches real-time stock price, 50-day average, and analyst recommendations. The verb 'fetches' and the specific resources are well-defined, but it does not distinguish itself from sibling tools like get_historical_prices or get_stock_price_chart.

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

Usage Guidelines3/5

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

The description implies usage for obtaining current price, average, and recommendations, but provides no explicit guidance on when to use this tool versus alternatives. For instance, it does not mention that get_historical_prices might be for historical data or get_stock_price_chart for chart data.

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

get_stock_price_chartA

Plain-text Unicode chart. Pass period (e.g. 10y, 5y, 1y) for calendar ranges, or use days alone.

ParametersJSON Schema
NameRequiredDescriptionDefault
tickerYes
daysNo
periodNo

Output Schema

ParametersJSON Schema
NameRequiredDescription
resultYes

TDQS

A3.6/5.0
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. It discloses the output format (plain-text Unicode chart) and the two ways to specify time range, but does not mention rate limits, data latency, or whether it requires authentication. The behavior is partially transparent.

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 two sentences, no waste. It front-loads the key purpose and follows with parameter guidance. Efficient.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool has an output schema, the description does not need to detail return structure. It covers the main purpose, parameter usage, and output format. For a simple chart tool with 3 parameters, this is reasonably complete.

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

Parameters3/5

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

Schema description coverage is 0%, so the description must compensate. It explains 'period' and 'days' parameters by specifying their relationship (period for calendar ranges, days alone). However, it does not describe the 'ticker' parameter or the exact format of 'period'. This adds some meaning but not comprehensive.

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 specifies a verb-resource-action: it creates a plain-text Unicode chart for a stock. It is distinct from 'get_historical_prices' and 'get_stock_analysis' as it focuses on chart output, though it does not explicitly differentiate from those siblings.

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

Usage Guidelines4/5

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

The description gives clear guidance on how to specify the time range: use period for calendar ranges or days alone. However, it does not explain when to prefer this tool over its siblings (e.g., when you need a visual chart vs. raw prices or analysis).

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. 3 tool updatesv0.1.0
    • First observedget_historical_prices
    • First observedget_stock_analysis
    • First observedget_stock_price_chart
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

A3.5/5.0

Scored across 3 tools

Disambiguation4/5

Tools are mostly distinct: get_historical_prices provides raw data for charts, get_stock_analysis gives real-time price and fundamentals, and get_stock_price_chart returns a visual chart. However, get_historical_prices and get_stock_price_chart both relate to historical data, causing slight overlap.

Naming Consistency5/5

All tools use a consistent get_verb_noun pattern (get_historical_prices, get_stock_analysis, get_stock_price_chart). Naming is clear and predictable.

Tool Count5/5

With 3 tools covering historical data, real-time analysis, and charting, the set is appropriately scoped for a finance assistant. No tool feels unnecessary.

Completeness3/5

The tools cover basic stock data retrieval and charting but lack fundamental operations like search, comparison, or portfolio management. Gaps exist for a fully comprehensive finance tool.

Maintenance

ActivityInactive
ResponsivenessNo issues

Resources

Related MCP Connectors

Related MCP Servers

  • Yahoo Finance MCP Server

    a05031113
    F
    license
    Not graded
    quality
    D
    maintenance
    Enables querying Yahoo Finance data including stock prices, historical data, financial statements, dividends, news, analyst recommendations, and company information through the yfinance library.
    -

  • Yahoo Finance MCP Server

    peidaqi
    A
    license
    Not graded
    quality
    D
    maintenance
    Enables LLMs to retrieve stock market data and financial information from Yahoo Finance using the yfinance Python library. Supports querying stock prices, historical data, and other financial metrics through natural language.
    MIT

  • yahoo-finance-mcp

    Alex2Yang97
    A
    license
    A
    quality
    D
    maintenance
    Enables retrieval of comprehensive financial data from Yahoo Finance, including stock prices, company info, financial statements, options, and news, for stock analysis and market research.
    9
    355
    MIT

  • yahoo-finance-mcp

    nrempel
    A
    license
    A
    quality
    C
    maintenance
    Provides access to Yahoo Finance data including real-time stock quotes, historical prices, financial statements, company info, symbol search, and news.
    6
    44 npm
    1
    MIT