Skip to main content
Glama

OpenBanking MCP Server

by NBWolfer
GitHub
Python
OverviewInspectNewEndpointsSchemaRelated ServersReviewsScore
Need Help?View Source CodeReport Issue

OpenBanking MCP Server

An MCP (Model Context Protocol) server that integrates with local Ollama LLMs for OpenBanking applications.

Features

  • Multiple LLM Agents: Support for 4 different specialized agents

  • Ollama Integration: Local LLM model support

  • Tool System: Comprehensive toolset for various operations

  • OpenBanking Focus: Specialized tools for banking and financial data

Architecture

This MCP server follows the architecture shown in the diagram:

  • MCP Host communicates with MCP Server

  • 4 Specialized Agents (Agent 1-4) with LLM/Model capabilities

  • Tool system for specific operations

  • Banking Services/API integration

Agents

  1. Agent 1 - Market Analyst: Market data analysis and volatile situations

  2. Agent 2 - Portfolio Manager: Portfolio management and strategy finding

  3. Agent 3 - Risk Analyst: Risk analysis for users

  4. Agent 4 - Explainability Agent: LLM for explainability and SWOT analysis

Project Structure

mcpOpenbankingMCPServer/ ├── src/ │ ├── __init__.py │ ├── main.py # Main server entry point │ ├── agents/ │ │ ├── __init__.py │ │ └── agent_manager.py # Agent management system │ ├── tools/ │ │ ├── __init__.py │ │ ├── tool_registry.py # Tool registration and management │ │ ├── portfolio_tools.py # Portfolio analysis tools │ │ ├── market_tools.py # Market data tools │ │ ├── risk_tools.py # Risk assessment tools │ │ ├── strategy_tools.py # Strategy recommendation tools │ │ └── analysis_tools.py # SWOT and explanation tools │ ├── config/ │ │ ├── __init__.py │ │ └── config.py # Configuration management │ └── utils/ │ ├── __init__.py │ └── utils.py # Utility functions ├── config/ │ └── config.yaml # Server configuration ├── requirements.txt # Python dependencies ├── startup.py # Python startup script ├── start_server.ps1 # PowerShell startup script ├── start_server.bat # Batch file for Windows ├── demo.py # Demo examples ├── test_server.py # Test script └── README.md # This file

Prerequisites

  1. Python 3.8+ with conda environment

  2. Ollama installed and running locally

  3. Conda environment named openbanking-backend

Setup

1. Create Conda Environment (if not exists)

conda create -n openbanking-backend python=3.11 conda activate openbanking-backend

2. Install Dependencies

pip install -r requirements.txt

3. Install and Start Ollama

Download and install Ollama from https://ollama.ai

# Pull a model (example with Llama 3.2) ollama pull llama3.2:latest # Start Ollama server ollama serve

4. Configure the Server

Edit config/config.yaml to customize:

  • Ollama connection settings

  • Agent configurations

  • Model assignments

  • Tool settings

Running the Server

Option 1: Using PowerShell Script (Recommended for Windows)

.\start_server.ps1

Option 2: Using Python Startup Script

python startup.py

Option 3: Direct Execution

conda activate openbanking-backend python src/main.py

Option 4: Development Mode

python src/main.py --dev

Tools Available

Portfolio Analysis

  • analyze_portfolio: Comprehensive portfolio analysis

  • portfolio_optimization: Portfolio allocation optimization

Market Analysis

  • market_analysis: Current market conditions analysis

  • volatility_analysis: Market volatility assessment

Risk Assessment

  • assess_risk: User-specific risk assessment

  • risk_simulation: Scenario-based risk simulation

Strategy Recommendations

  • recommend_strategy: Investment strategy recommendations

Analysis & Explainability

  • swot_analysis: SWOT analysis for any subject

  • explain_concept: Explain financial concepts simply

  • reverse_simulation: Reverse engineering analysis

Usage Examples

Run Demo

python demo.py

Test the Server

python test_server.py

Configuration

The server uses config/config.yaml for configuration. Key sections:

# Ollama connection ollama: host: "localhost" port: 11434 timeout: 30 # Agents configuration agents: - name: "market_analyst" model: "gemma3:4b" role: "Market Data Analyst" # ... more config # Tools configuration tools: - name: "portfolio_analysis" enabled: true

Troubleshooting

Common Issues

  1. Ollama Connection Failed

    • Ensure Ollama is installed and running (ollama serve)

    • Check if the default port 11434 is available

    • Verify models are pulled (ollama list)

  2. Conda Environment Issues

    • Make sure openbanking-backend environment exists

    • Activate the environment before running

    • Install dependencies in the correct environment

  3. Import Errors

    • Ensure all dependencies are installed

    • Check Python path and working directory

Logs

Check the console output for detailed error messages and debugging information.

Development

Adding New Tools

  1. Create tool class in src/tools/

  2. Add tool registration in tool_registry.py

  3. Update configuration if needed

Adding New Agents

  1. Add agent configuration in config/config.yaml

  2. Implement custom agent logic if needed

  3. Test with demo scripts

License

MIT License

This server cannot be installed

-
security - not tested
F
license - not found
-
quality - not tested

How are these scores calculated?

An MCP server that integrates with local Ollama LLMs to provide financial analysis through four specialized agents (Market Analyst, Portfolio Manager, Risk Analyst, and Explainability Agent) with comprehensive banking tools.

  1. Features
    1. Architecture
      1. Agents
        1. Project Structure
          1. Prerequisites
            1. Setup
              1. 1. Create Conda Environment (if not exists)
              2. 2. Install Dependencies
              3. 3. Install and Start Ollama
              4. 4. Configure the Server
            2. Running the Server
              1. Option 1: Using PowerShell Script (Recommended for Windows)
              2. Option 2: Using Python Startup Script
              3. Option 3: Direct Execution
              4. Option 4: Development Mode
            3. Tools Available
              1. Portfolio Analysis
              2. Market Analysis
              3. Risk Assessment
              4. Strategy Recommendations
              5. Analysis & Explainability
            4. Usage Examples
              1. Run Demo
              2. Test the Server
            5. Configuration
              1. Troubleshooting
                1. Common Issues
                2. Logs
              2. Development
                1. Adding New Tools
                2. Adding New Agents
              3. License

                Related MCP Servers

                • MCP Ollama Server

                  emgeee
                  A
                  security
                  A
                  license
                  A
                  quality
                  MCP Ollama server integrates Ollama models with MCP clients, allowing users to list models, get detailed information, and interact with them through questions.
                  Last updated -
                  3
                  27
                  MIT License
                  • Apple

                • Multi-Model Advisor

                  YuChenSSR
                  A
                  security
                  A
                  license
                  A
                  quality
                  An MCP server that queries multiple Ollama models and combines their responses, providing diverse AI perspectives on a single question for more comprehensive answers.
                  Last updated -
                  2
                  65
                  MIT License
                  • Apple

                • Ollama MCP Server

                  NewAITees
                  -
                  security
                  F
                  license
                  -
                  quality
                  A server that enables seamless integration between local Ollama LLM instances and MCP-compatible applications, providing advanced task decomposition, evaluation, and workflow management capabilities.
                  Last updated -
                  6
                  • Apple

                • Just Prompt

                  disler
                  A
                  security
                  F
                  license
                  A
                  quality
                  A lightweight MCP server that provides a unified interface to various LLM providers including OpenAI, Anthropic, Google Gemini, Groq, DeepSeek, and Ollama.
                  Last updated -
                  6
                  649

                View all related MCP servers

                New MCP Servers

                MCP directory API

                We provide all the information about MCP servers via our MCP API.

                curl -X GET 'https://glama.ai/api/mcp/v1/servers/NBWolfer/mcpOpenbankingMCPServer'

                If you have feedback or need assistance with the MCP directory API, please join our Discord server