FinBrain MCP

by ahmetsbilgin

334 downloads

Not rated

GitHub

About

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

Details

Author: ahmetsbilgin
Downloads: 334
Categories: Database, Finance, Other

- 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)

Setting up with Highlight

This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:

Download and install Highlight from highlightai.com/download
Navigate to the plugins tab and select "Add Custom Plugin"
Configure the plugin with the settings below

Plugin Name FinBrain MCP

Command (node, npx, python, etc.)

Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
Enable "Start Automatically" if you want the plugin to start when Highlight launches

Setting up with Cursor

Open Cursor's settings
Navigate to the MCP section
Click "Add new Global MCP server"
Copy and paste the configuration below based on your operating system

JSON

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

JSON

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

JSON

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

Setting up with Claude Desktop

Open Claude Desktop's settings
Go to the Integrations tab
Click "Add MCP Server"
Use the configuration below based on your operating system

Note: Make sure Claude Desktop is running before attempting to connect.

JSON

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

JSON

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

JSON

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

Setting up with Windsurf

Open Windsurf's preferences
Go to the Integrations section
Click "Add MCP Integration"
Use the configuration below based on your operating system

JSON

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

JSON

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

JSON

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

Setting up with Cline

Open Cline's settings
Navigate to the Integrations section
Click "Add MCP Server"
Copy and paste the configuration below based on your operating system

Note: Make sure to restart Cline after adding the configuration.

JSON

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

JSON

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

JSON

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

Setting up with Goose

Open Goose's preferences
Go to the Integrations tab
Select "MCP Servers"
Click "Add New Server"
Use the configuration below based on your operating system

JSON

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

JSON

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

JSON

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

From the repository

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.

Claude Desktop / Cursor

Paste into your MCP client config file to install this server.

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

McpServers

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

FinBrain MCP

> Requires Python 3.10+ A Model Context Protocol (MCP) server that exposes FinBrain datasets to AI clients (Claude Desktop, VS Code MCP extensions, etc.) via simple tools. Backed by the official finbrain-python SDK. - Package name: finbrain-mcp - CLI entrypoint: finbrain-mcp - Documentation: finbrain.tech/integrations/mcp ----------

Features

AI-Powered Price Predictions

Access FinBrain's machine learning price forecasts with daily (10-day) and monthly (12-month) horizons. Includes mean predictions with 95% confidence intervals.

News Sentiment Analysis

Track aggregated sentiment scores derived from financial news coverage. Monitor how market sentiment shifts over time for any ticker.

Alternative Data

- LinkedIn Metrics — Employee count and follower trends as company health indicators - App Store Ratings — Mobile app performance data for consumer-facing companies - Options Flow — Put/call ratios and volume to gauge market positioning

Institutional & Insider Activity

- US Congress Trades — Stock transactions disclosed by House representatives and Senators - Insider Transactions — SEC Form 4 filings showing executive buys and sells - Analyst Ratings — Wall Street coverage and price target changes ----------

What you get

- ⚡️ Local MCP server (no proxying) using your own FinBrain API key - 🧰 Tools (JSON by default, CSV optional) with paging - health - available_markets, available_tickers - predictions_by_market, 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 - 🧹 Consistent, model-friendly shapes (we normalize raw API responses) - 🔑 Multiple ways to provide your API key: env var, file ----------

Install

Option A — Standard install (pip)

```bash

No reviews yet — be the first

Use Google, GitHub, or an email account so ratings stay tied to real people.

Email sign in

No reviews posted yet.

About

Details

Jump to

Setting up with Highlight

From the repository

Claude Desktop / Cursor

McpServers

FinBrain MCP&nbsp;

Features

AI-Powered Price Predictions

News Sentiment Analysis

Alternative Data

Institutional & Insider Activity

What you get

Install

Option A — Standard install (pip)

Install

More like this

Sequential Thinking

Redis

Filesystem

EverArt

Google Drive

Sqlite

FinBrain MCP