Skip to main content

MCP Server for Corpus Tracker - Financial Portfolio Assistant

Project description

Corpus MCP Server

A Model Context Protocol (MCP) server for the Corpus Tracker application. This server allows AI assistants (like Claude) to securely interact with your financial portfolio, enabling them to fetch holdings, analyze net worth, and manage transactions.

Features

  • Portfolio Analytics: Fetch net worth, asset allocation, and top holdings.
  • Asset Management: List, add, and remove Gold and Stock holdings.
  • Finance Tracking: Log income and expenses, view transaction history, and analyze cash flow.
  • Secure Authentication: Uses API Key authentication to communicate with your Corpus Tracker backend.

Available Tools

Profile & Management

  • get_my_profile: Get the current user's profile and settings.
  • list_corpora: List all corpora (profiles) the user belongs to.

Analytics

  • get_portfolio_summary: Get aggregated net worth, asset breakdown, and liabilities.
  • get_top_holdings(limit): Get top holdings by value.

Gold Holdings

  • list_gold_holdings: List all gold holdings.
  • add_gold_holding(weight_grams, purchase_price, purchase_date): Add a new gold holding.
  • delete_gold_holding(holding_id): Delete a gold holding by ID.

Stock Holdings

  • list_stock_holdings: List all stock holdings.
  • add_stock_holding(symbol, quantity, avg_price): Add a new stock holding.
  • update_stock_holding(holding_id, symbol, quantity, avg_price): Update an existing stock holding.
  • delete_stock_holding(holding_id): Delete a stock holding by ID.

Financial Transactions

  • list_transactions(start_date, end_date, category, type, limit): List transactions with filters.
  • add_transaction(type, amount, category, description, date): Add a new income or expense transaction.
  • delete_transaction(txn_id): Delete a transaction by ID.
  • get_cashflow_trend(days): Get income vs expense trend for the last N days.

Installation

pip install corpus-mcp

Configuration

The server requires two environment variables to connect to your backend:

  • API_URL: The URL of your Corpus Tracker backend API (e.g., https://my-corpus.vercel.app/api/v1).
  • API_KEY: Your personal API Key generated from the Corpus Tracker settings.

Usage

Running Standalone

You can run the server directly:

# Set environment variables
export API_URL="https://my-corpus.vercel.app/api/v1"
export API_KEY="sk_..."

# Run the server
corpus-mcp

Using with Claude Desktop

Add the following configuration to your claude_desktop_config.json:

{
  "mcpServers": {
    "corpus-tracker": {
      "command": "uvx",
      "args": [
        "corpus-mcp"
      ],
      "env": {
        "API_URL": "https://my-corpus.vercel.app/api/v1",
        "API_KEY": "your_api_key_here"
      }
    }
  }
}

Development

To install dependencies and run locally:

# Install dependencies
pip install .

# Run dev server
corpus-mcp

License

MIT

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

corpus_mcp-0.1.1.tar.gz (47.8 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

corpus_mcp-0.1.1-py3-none-any.whl (5.3 kB view details)

Uploaded Python 3

File details

Details for the file corpus_mcp-0.1.1.tar.gz.

File metadata

  • Download URL: corpus_mcp-0.1.1.tar.gz
  • Upload date:
  • Size: 47.8 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: uv/0.7.19

File hashes

Hashes for corpus_mcp-0.1.1.tar.gz
Algorithm Hash digest
SHA256 22ce4a85f224b98bd208e20fc7e929f1027aa31e96b1e2655bdc206103d5afaa
MD5 4ea83a26366b3c6d011622d70428fcb3
BLAKE2b-256 8f4aa263ca826681f5a3dfb3379f1919d419ac61c683c7b916bbbd0d821da957

See more details on using hashes here.

File details

Details for the file corpus_mcp-0.1.1-py3-none-any.whl.

File metadata

  • Download URL: corpus_mcp-0.1.1-py3-none-any.whl
  • Upload date:
  • Size: 5.3 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: uv/0.7.19

File hashes

Hashes for corpus_mcp-0.1.1-py3-none-any.whl
Algorithm Hash digest
SHA256 68eb63a612dbdaf672a7de70c5912e181f0235da37d547b014e43a8c2deafa46
MD5 0b656567b40e05032347131dea443e7d
BLAKE2b-256 0422cbd90a68d147f87ccde4e80001e5a88dc931f983f1e4cf3504655f7de8e4

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page