FSS Pension

Provides real-time pension data via MCP using FSS OpenAPI for product search, fee analysis, rankings, and statistics.

html

0

GitHub Stars

html

Language

7 months ago

First Indexed

3 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "ddoriboo-pension-mcp": {
      "command": "python",
      "args": [
        "fss_pension_server.py"
      ],
      "env": {
        "OPENAI_API_KEY": "YOUR_OPENAI_API_KEY",
        "FSS_SERVICE_KEY": "YOUR_API_KEY"
      }
    }
  }
}

You can run the Pension MCP Server to access real-time pension data from FSS OpenAPI and expose it through the MCP protocol to AI models and clients. This server lets you search pension products, compare fees, view company rankings, and access pension statistics, enabling AI-assisted advice workflows.

How to use

You use an MCP client to connect to the Pension MCP Server and issue predefined operations such as listing pension products, searching by filters, or retrieving statistics. The server runs locally (or remotely) and receives commands via the MCP protocol, returning structured results that your client can render or feed into AI workflows. After starting the MCP server, you can configure your client to provide the FSS service key so the server can access the FSS OpenAPI data in real time.

Typical usage patterns include: 1) loading the list of pension products, 2) filtering results by product type or fee level, 3) obtaining the lowest-fee products for cost-conscious comparisons, 4) fetching company performance rankings, and 5) pulling current pension statistics for dashboards. These capabilities feed AI-assisted consultations and real-time market views in your applications.

How to install

Prerequisites: Python 3.11 is required to run the MCP Server. You should also have pip available to install dependencies.

Install and run the MCP Server locally with the following steps.

cd fss_pension_mcp_server
pip install -r requirements.txt

# Environment variable for FSS API access
export FSS_SERVICE_KEY="your_fss_api_key"

# Start the MCP server
python fss_pension_server.py

Additional setup and notes

For the Web Service, you will also need an OpenAI API key if you want AI-based pension consultations. The web service relies on the same FSS data source and can be deployed together or separately as needed.

If you plan to deploy to Railway, ensure you provide the necessary environment variables (FSS_SERVICE_KEY and OPENAI_API_KEY) in the deployment configuration and point the web service at its entry script.

After installation, you can open the web app in your browser at http://localhost:8000 to access the AI-assisted pension consultation UI.

Configuration and security

Set environment variables to provide access credentials for the FSS OpenAPI and, if you use AI features, for OpenAI. The MCP server reads FSS_SERVICE_KEY at startup to authorize data access.

Keep your API keys secure and do not commit them to version control. Use a local environment file or a secret management system in production.

Troubleshooting and tips

If the server fails to start, verify that Python 3.11 is installed and that all dependencies in requirements.txt install successfully. Check that the FSS_SERVICE_KEY is set correctly and that network access to the FSS OpenAPI is available.

Available tools

get_pension_products

Retrieve the list of pension products available via the MCP server.

search_products

Search pension products using filters and criteria.

get_low_fee_products

Analyze and return the lowest-fee pension products.

get_company_ranking

Provide company-by-company performance rankings for pension offerings.

get_pension_statistics

Return pension-related statistics from the data source.

GET /api/market-summary

Web service endpoint to fetch current market summary based on FSS data.

POST /api/ai-chat-with-profile

AI-assisted chat with a pension profile for personalized guidance.

POST /api/ai-recommendation

Personalized pension product recommendations based on user data.

POST /api/retirement-scenario

Analyze and output retirement scenarios using input assumptions.