广告合作
MCP.so
登录

FinBrain MCP Server

@ahmetsbilgin

代码仓库

基本信息

分类

其他

传输方式

stdio

作者

ahmetsbilgin

提交者

Ahmet Bilgin

关于 FinBrain MCP Server

Access institutional-grade alternative financial data directly in your LLM workflows.

#finance#quant#alternativedata

FinBrain MCP Server 配置

使用下面的配置,将此服务器添加到你的 MCP 客户端。

{
  "mcpServers": {
    "finbrain-mcp": {
      "command": "python",
      "args": [
        "-m",
        "venv",
        ".venv"
      ]
    }
  }
}

FinBrain MCP Server 工具

工具列表暂未提供

当前收录暂时没有可展示的工具列表，不代表服务没有工具。请查阅项目文档了解支持的能力。

工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。

概览

What is FinBrain MCP?

FinBrain MCP is a Model Context Protocol server that exposes FinBrain datasets to AI clients like Claude Desktop and VS Code MCP extensions. It provides tools for financial data including price predictions, news sentiment, alternative data, and institutional/insider activity. Requires Python 3.10+ and a FinBrain API key.

How to use FinBrain MCP?

Install via pip install --upgrade finbrain-mcp, configure your FinBrain API key in the MCP client’s config (Claude Desktop or VS Code), then ask natural-language questions. The client launches the server automatically; no manual start needed.

Key features of FinBrain MCP

  • AI-powered price predictions with 10-day and 12-month horizons
  • News sentiment analysis with aggregated scores per ticker
  • Alternative data: LinkedIn metrics, App Store ratings, Options flow
  • Institutional activity: US Congress trades, insider transactions, analyst ratings
  • Tools return JSON by default, CSV on request, with paging support
  • Local MCP server using your own API key (no cloud proxying)

Use cases of FinBrain MCP

  • Get daily or monthly price forecasts for any ticker
  • Track aggregate news sentiment and market mood shifts
  • Monitor insider transactions and congressional stock trades
  • Fetch analyst ratings and price target changes
  • Retrieve alternative indicators like LinkedIn follower trends and put/call ratios

常见问题

1

What are the runtime requirements for FinBrain MCP?

Python 3.10+ is required. Install the package via pip; a FinBrain API key is mandatory.

2

How do I provide my FinBrain API key?

Set `FINBRAIN_API_KEY` in the MCP client’s `env` block (recommended) or as an environment variable. Restart the client after setting the env var.

3

What endpoints are available?

Tools include `predictions_by_ticker`, `news_sentiment_by_ticker`, `app_ratings_by_ticker`, `analyst_ratings_by_ticker`, `house_trades_by_ticker`, `senate_trades_by_ticker`, `insider_transactions_by_ticker`, `linkedin_metrics_by_ticker`, `options_put_call`, and basic ones like `health`, `available_markets`, and `available_tickers`.

4

Can I get CSV output instead of JSON?

Yes – simply say “as CSV” in your request, and the tool will return CSV formatted data.

5

Is data proxied or stored locally?

The MCP server runs locally and directly accesses FinBrain’s API with your own key. No proxying; data is fetched live from FinBrain’s cloud.

评论

其他 分类下的更多 MCP 服务器

🚀 Model Context Protocol (MCP) Curriculum for Beginners

microsoft

This open-source curriculum introduces the fundamentals of Model Context Protocol (MCP) through real-world, cross-language examples in .NET, Java, TypeScript, JavaScript, Rust and Python. Designed for developers, it focuses on practical techniques for building modular, scalable,

16.7K

Hindsight

vectorize-io

Hindsight: Agent Memory That Learns

50.4K

Health by Dr Brad

Dr Brad Stanfield

Health by Dr Brad works out a health plan from your own results: which screening is due at your age, and evidence-based suggestions, each with the reason and the published guideline or study behind it. Your record is one

Codelf

unbug

A search tool helps dev to solve the naming things problem.

14.2K

Yuppsy

Yuppsy MCP: build and publish real estate websites from your AI assistant. Yuppsy lets your AI assistant create live websites for real estate agents and individual property listings. You don't need a designer or any code

广告合作