Skip to main content
Glama
VoxLink-org

Finance Tools MCP

by VoxLink-org
README.md
# finance-tools-mcp: A Financial Analysis MCP Server
> https://github.com/VoxLink-org/finance-tools-mcp

## Overview

The **finance-tools-mcp** is a Model Context Protocol (MCP) server designed to provide comprehensive financial insights and analysis capabilities to Large Language Models (LLMs). Modified from [investor-agent](https://github.com/ferdousbhai/investor-agent), it integrates with various data sources and analytical libraries to offer a suite of tools for detailed financial research and analysis.

<a href="https://glama.ai/mcp/servers/@VoxLink-org/finance-tools-mcp">
  <img width="380" height="200" src="https://glama.ai/mcp/servers/@VoxLink-org/finance-tools-mcp/badge" alt="Finance Tools MCP server" />
</a>

## Prerequisites

*   **Python:** 3.10 or higher is required.
*   **Package Manager:** [uv](https://docs.astral.sh/uv/) is the recommended package installer and resolver for this project.

## Installation

First, install `uv` if you haven't already:

```bash
curl -LsSf https://astral.sh/uv/install.sh | sh
```

Ensure `uv` is in your system's PATH. You might need to restart your terminal or add `~/.cargo/bin` to your PATH.

Then, you can run the `finance-tools-mcp` MCP server using `uvx` (which executes a package without explicitly installing it into your environment):

```bash
uvx finance-tools-mcp
```

To run the server with a FRED API key (for enhanced macroeconomic data access), set it as an environment variable:

```bash
FRED_API_KEY=YOUR_API_KEY uvx finance-tools-mcp
```

You can also run the server using Server-Sent Events (SSE) transport, which might be preferred by some MCP clients:

```bash
uvx finance-tools-mcp --transport sse
```

Or with both the FRED API key and SSE transport:

```bash
FRED_API_KEY=YOUR_API_KEY uvx finance-tools-mcp --transport sse
```

## Usage with MCP Clients

To integrate **finance-tools-mcp** with an MCP client (for example, Claude Desktop), add the following configuration to your `claude_desktop_config.json`:

```json
{
  "mcpServers": {
    "investor": {
        "command": "path/to/uvx/command/uvx",
        "args": ["finance-tools-mcp"],
    }
  }
}
```

## Debugging

You can leverage the MCP inspector to debug the server:

```bash
npx @modelcontextprotocol/inspector uvx finance-tools-mcp
```

or

```bash
npx @modelcontextprotocol/inspector uv --directory  ./ run finance-tools-mcp
```

For log monitoring, check the following directories:

*   macOS: `~/Library/Logs/Claude/mcp*.log`
*   Windows: `%APPDATA%\Claude\logs\mcp*.log`

## Development

For local development and testing:

1.  Use the MCP inspector as described in the [Debugging](#debugging) section.
2.  Test using Claude Desktop with this configuration:

```json
{
  "mcpServers": {
    "investor": {
      "command": "path/to/uv/command/uv",
      "args": ["--directory", "path/to/finance-tools-mcp", "run", "finance-tools-mcp"],
    }
  }
}
```

TDQS

B3.2/5.0

Scored across 17 tools

Disambiguation3/5

Most tools have distinct purposes, but there is some overlap that could cause confusion. For example, get_historical_fng_tool and analyze_fng_trend both deal with Fear & Greed Index data, and get_ticker_data includes news while get_ticker_news_tool is specifically for news. However, descriptions help clarify differences, such as analyze_fng_trend focusing on trend analysis versus get_historical_fng_tool for raw data retrieval.

Naming Consistency4/5

The naming follows a consistent snake_case pattern with a verb_noun structure for most tools, like get_price_history and search_fred_series. There are minor deviations, such as calculate being a single verb and cnbc_news_feed using a noun_verb_noun pattern, but overall, the naming is predictable and readable.

Tool Count4/5

With 17 tools, the count is slightly high but reasonable for a finance domain that covers diverse areas like market data, news, sentiment, and analysis. It provides comprehensive coverage without being overwhelmingly large, though it borders on the heavy side for typical MCP server scopes.

Completeness4/5

The tool set offers broad coverage for financial analysis, including data retrieval (e.g., price history, financial statements), sentiment indicators, news feeds, and specialized tools like options analysis. Minor gaps exist, such as no explicit tools for portfolio management or trading actions, but agents can work around this with the available tools for core financial workflows.

Maintenance

ActivityInactive
ResponsivenessNo issues