Mifos MCP - Model Context Protocol (MCP)

Mifos MCP - Model Context Protocol (MCP)

Enabling AI agents to access and operate on financial data in the Mifos X ecosystem using Model Context Protocol.

17
Stars
12
Forks
17
Watchers
4
Issues
Mifos MCP provides a Model Context Protocol (MCP) interface tailored for the Mifos X ecosystem, empowering AI agents to interact with financial data and perform operations within the platform. It offers a Java (Quarkus) implementation, with easy configurability via environment variables and native executable support. Developers can test and debug deployments with the MCP Inspector, and detailed instructions ensure smooth setup and integration. Comprehensive examples demonstrate practical banking and financial automation workflows.

Key Features

Java (Quarkus) based MCP server implementation
Seamless integration with the Mifos X/Fineract platform
Environment variable configuration for secure connections
Support for native executable builds
Compatible with MCP Inspector for debugging and testing
Sample prompts and real-world usage videos
Multi-platform agent support via STDIO or SSE
Authentication and multi-tenant support
Backoffice and client management operations
Scalable for various banking workflows

Use Cases

Automated client registration and KYC processing
Opening, activating, and managing client profiles
Creating and managing loan products
Loan application, approval, disbursement, and repayment workflows
Adding and updating customer addresses and references
Backoffice automation using AI-driven agents
Integrating AI-powered tools into financial operations
Real-time testing and debugging of MCP endpoints
Secure, tenant-aware API integrations for banking systems
Extending financial service workflows with intelligent automation

README

Mifos MCP - Model Context Protocol (MCP)

This project provides Model Context Protocol (MCP) for the Mifos X Ecosystem, enabling AI agents to access financial data and operations. Implementations is available in Java (Quarkus).


MCP Developer Tools

Use the MCP Inspector to test and debug your server:

bash
npx @modelcontextprotocol/inspector

This starts a local web UI to connect to your MCP server via STDIO or SSE.


Getting Started

1. Choose Your Implementation

Java (Quarkus)

Prerequisites: JDK 21+, Maven

Steps:

  1. Configure environment variables in your shell or IDE:
    bash
    export MIFOSX_BASE_URL="https://your-fineract-instance"
    export MIFOSX_BASIC_AUTH_TOKEN="your_api_token"
    export MIFOS_TENANT_ID="default"
    
  2. Run via JBang (for quick execution):
    bash
    jbang --quiet org.mifos.community.ai:mcp-server:1.0.0-SNAPSHOT:runner
    
  3. (Optional) Build a native executable:
    bash
    ./mvnw package -Dnative
    ./target/mcp-server-1.0.0-SNAPSHOT-runner
    

Configuration

All implementations require the following environment variables:

Variable Description
FINERACT_BASE_URL Base URL of your Fineract instance
FINERACT_BASIC_AUTH_TOKEN API authentication token
FINERACT_TENANT_ID Tenant identifier (default: default)

Note: Java uses MIFOSX_ prefixed variables (e.g., MIFOSX_BASE_URL).


Building Native Executables (Java Only)

For Java (Quarkus), create a native executable:

bash
./mvnw package -Dnative -Dquarkus.native.container-build=true
./target/mcp-server-1.0.0-SNAPSHOT-runner

Testing with MCP Inspector

  1. Start your MCP server (Python/Java/Node.js).
  2. Run the inspector:
    bash
    npx @modelcontextprotocol/inspector
    
  3. Connect to the server using the STDIO transport.

Examples - Backoffice Agent

Video URL Title Prompt
https://youtu.be/MDQKRoz5GKw?si=69X77C58nFhy6Ioh Join and Try the Mifos MCP. Go to https://ai.mifos.community N/A
https://youtu.be/y5MR3j8EGM4?si=zXTurBNql4xF5CGY Create Client Create the client using first name: OCTAVIO, last name: PAZ, email address: octaviopaz@mifos.org, mobile number: 5518098299 and external id: OCPZ99
https://youtu.be/qJsC25cd-1g?si=qQzX8DeOe0_2qhfr Activate Client Activate the client OCTAVIO PAZ
https://youtu.be/X1g_nVDsRnM?si=K7vsAN7gOLEC2OG0 Add Address to Client Add the address to the client OCTAVIO PAZ. Fields: address type: HOME, address: PLAZA DE LORETO, neighborhood: DOCTOR ALFONZO, number: NUMBER 10, city: CDMX, country: MÉXICO, postal code: 54440, state province: CDMX.
https://youtu.be/xeL9_sycwA8?si=AtV6F4WhTvcDspSp Add Personal Reference to Client Add the family member to the client OCTAVIO PAZ. First name: Maria, middle name: Elena, last name: Ramírez, age: 27, relationship: Sister, gender: FEMALE, date of birth: 15 March 1998, qualification: Bachelor’s Degree, is dependent, profession: STUDENT, marital status: SINGLE.
https://youtu.be/IKGMeAJBAOk?si=N27rE64dn7qxmMBk Create a Loan Product Create a default loan product named "SILVER" with short name "ST01", principal 10000, 5 repayments, nominal interest rate 10.0%, repayment frequency 2 MONTHS, currency USD.
https://youtu.be/5EdgUyLyP0w?si=L0UdYjXlyYF6faL5 Create Loan Application Apply for an individual loan account for the client OCTAVIO PAZ using loan product SILVER.
https://youtu.be/2ioN_8z_uaY?si=ZTB5rCrgS2jTpC4- Approve Loan Application Approve the loan account
https://youtu.be/dDebmrn4lB0?si=0GTf4asCBHnsu27f Disbursement of Loan Disburse the loan account using payment type Money Transfer.
https://youtu.be/N3wnyJCh_Ik?si=gSy5LrJdFF2kfzHd Make Loan Repayment Make a repayment for loan account 6 using Money Transfer. Set the amount to 6687.59, the date to 06 AUGUST 2025, and use external ID RT33. Add the note “FYI” and include payment account number 100, check number 101, routing code 102, receipt number 103, and bank number 1
https://youtu.be/bOuTj97hyqU?si=9bpno4Kp0II1IfPY Create Savings Product Create a default savings product with the name "WALLET", short name "TSWL", description "WALLET PRODUCT", and currency code "USD".
https://youtu.be/l-Z7LlE3AnM?si=yQM4lloJL8Hu6yv8 Create a Savings Account Application Apply for a savings account for the client OCTAVIO PAZ using savings product WALLET and external ID STP1.
https://youtu.be/Q5ExlhalG8U?si=TwbsUZX30G3JeNJy Approve Savings Application Approve the savings account and include the note: "MY FIRST APPROVAL".
https://youtu.be/DJgUiRYK-rE?si=YatfVgOgpbP4wV91 Activate Savings Account Activate the savings account
https://youtu.be/Od7KFqktUtI?si=gPJNlLOB_7D74QdS Make a Deposit Transaction Create a savings transaction for client with the account number 1. It's a DEPOSIT of 5000 using Money Transfer. The note should be "Monthly saving".
https://youtu.be/9OL6N5wKG7c?si=R50RjTK6GI_ODuUs Make a Withdrawal Transaction Create a savings transaction for client with the account number 1. It's a WITHDRAWAL of 2000 using Money Transfer. Add the note "Emergency expense".

Contact


Key Features:

  • MCP-compliant with STDIO/SSE transports
  • Environment-agnostic configuration

Star History

Star History Chart

Repository Owner

openMF
openMF

Organization

Repository Details

Language Java
Default Branch main
Size 629 KB
Contributors 7
License Mozilla Public License 2.0
MCP Verified Nov 12, 2025

Programming Languages

Java
100%

Tags

Topics

agentic agentic-ai ai backoffice banking corebanking financialinclusion fintech llm loan savings

Join Our Newsletter

Stay updated with the latest AI tools, news, and offers by subscribing to our weekly newsletter.

We respect your privacy. Unsubscribe at any time.

Related MCPs

Discover similar Model Context Protocol servers

  • QuantConnect MCP Server

    QuantConnect MCP Server

    Official bridge for secure AI access to QuantConnect's algorithmic trading cloud platform

    QuantConnect MCP Server enables artificial intelligence systems such as Claude and OpenAI to interface with QuantConnect's cloud platform through an official, secure, and dockerized implementation of the Model Context Protocol (MCP). It facilitates automated project management, strategy writing, backtesting, and live deployment by exposing a comprehensive suite of API tools for users with valid access credentials. As the maintained official version, it ensures security, easy deployment, and cross-platform compatibility for advanced algorithmic trading automation.

    • 50
    • MCP
    • QuantConnect/mcp-server
  • Authenticator App MCP Server

    Authenticator App MCP Server

    Secure MCP server for AI-assisted access to 2FA codes and passwords.

    Authenticator App MCP Server provides a secure Model Context Protocol (MCP) server enabling AI agents to interact with authentication credentials, such as 2FA codes and passwords. It facilitates automated login processes for AI assistants while maintaining robust security by requiring access tokens and integrating with the Authenticator App desktop client. This solution streamlines the management of user credentials across multiple platforms and websites, ensuring seamless and secure credential retrieval by AI agents.

    • 27
    • MCP
    • firstorderai/authenticator_mcp
  • MCP XRPL Server

    MCP XRPL Server

    Unified Model Context Protocol server for seamless AI-driven interaction with the XRP Ledger.

    MCP XRPL Server provides a comprehensive Model Context Protocol implementation for the XRP Ledger, enabling AI agents to access blockchain services seamlessly across MainNet, TestNet, and DevNet. It offers an extensive suite of features including account management, token transfers, NFT operations, DIDs, AMM operations, and oracle interactions, all via a standardized MCP interface. The server supports context-driven interactions, making XRPL functionality readily accessible for AI-powered agents.

    • 5
    • MCP
    • RomThpt/mcp-xrpl
  • FinData MCP Server

    FinData MCP Server

    Open-source MCP server for LLM access to professional financial data.

    FinData MCP Server offers standardized financial data access to large language models by implementing the Model Context Protocol. It supports multiple data providers such as Tushare and Wind, and enables retrieval of both market and macroeconomic data via Stdio or SSE transports. The server is configurable and integrates into AI systems, providing tools for market, fundamental, and financial data queries.

    • 45
    • MCP
    • zlinzzzz/finData-mcp-server
  • MXCP

    MXCP

    Enterprise-Grade Model Context Protocol Framework for AI Applications

    MXCP is an enterprise-ready framework that implements the Model Context Protocol (MCP) for building secure, production-grade AI application servers. It introduces a structured methodology focused on data modeling, robust service design, policy enforcement, and comprehensive testing, integrated with strong security and audit capabilities. The framework enables rapid development and deployment of AI tools, supporting both SQL and Python environments, with built-in telemetry and drift detection for reliability and compliance.

    • 49
    • MCP
    • raw-labs/mxcp
  • kibitz

    kibitz

    The coding agent for professionals with MCP integration.

    kibitz is a coding agent that supports advanced AI collaboration by enabling seamless integration with Model Context Protocol (MCP) servers via WebSockets. It allows users to configure Anthropic API keys, system prompts, and custom context providers for each project, enhancing contextual understanding for coding tasks. The platform is designed for developers and professionals seeking tailored AI-driven coding workflows and provides flexible project-specific configuration.

    • 104
    • MCP
    • nick1udwig/kibitz
  • Didn't find tool you were looking for?

    Be as detailed as possible for better results