HomeBlogAPI ManagementMCP & Agent AI: The ultimate context-based communication platform for banks

MCP & Agent AI: The ultimate context-based communication platform for banks

This site is also available in: Deutsch (German)

In today’s article, we look at how banks can implement a context-based communication platform based on the MCP principle. We summarize key requirements, market solutions and open source frameworks and compare them with LeapXpert (Swisscom) and Agentforce (Salesforce) as examples.


1 Introduction: Why MCP and Agent AI are crucial for banks

Banks are under pressure to establish AI-driven, context-based communication platforms that work seamlessly across countries and channels. With Model Context Protocol (MCP) and Agent AI, existing APIs and integrations can be transformed into intelligent, agent-enabled services for next-best-action, automated summaries and real-time consent-based data processing.


2 Central requirements for an MCP-capable communication platform

  1. Agent-based communication & Agent AI

    • AI agents (e.g. chatbots, virtual assistants) use context data for precise answers and actions.

  2. Context-controlled workflows

    • Dynamic process control via DMN decision rules (e.g. channel selection, offer creation).

  3. API orientation & MCP

    • Exposure of all backend systems via REST/GraphQL APIs as MCP server.

  4. Cross-channel collaboration

    • Standardized message and agent control via chat apps, e-mail, SMS, voice, video.

  5. AI functions for banks

    • Next-best-action, automatic summaries, sentiment analysis.

  6. Consent management

    • Strict adherence to consent in every customer interaction.


3. market overview: Commercial MCP & Agent AI platforms

SolutionCore functionsBanking focus
MuleSoft MCP Support (Beta)APIs & integrations as MCP server, standardized agent-to-tool protocol, secure scalingEnables AI agents next-best-action & real-time context
LeapXpertCompliance chat in messaging apps, archiving, consent handlingSpecialized chat compliance
SymphonySecure multi-channel communication, bot/API connection, AI summariesTrading & Wealth Management
UnbluOmnichannel (chat, video, co-browsing), secure messenger, AI co-pilotBanks & insurers
QwilCloud messenger with end-to-end encryption, file/screen sharingBanks, wealth management, law firms
Infobip (CPaaS)SMS, WhatsApp, email, voice, chatbot builder, campaign workflowsTransaction notifications across all sectors
Agentforce (Salesforce)Unified CRM platform, autonomous workflow managementSales and service teams in banks

4. open source frameworks for MCP & Agent AI

FrameworkFunctionsBanking use
RasaNLU, context-driven stories, multi-channel connectors, on-prem optionChatbots, virtual assistants with agent AI function
CIBSevenBPMN engine, DMN decision rules, banking connectors, on-prem performanceOrchestration of complex workflows & next-best-action
MuleSoft AnypointMCP connector, API management, integration templatesSeamless exposure of all systems as MCP servers for AI agents

5. example architecture: MCP & Agent AI in banking operations

  1. Data Hub / Data Lake

    • Saves customer profiles, consent records, event logs.

    • Provides context data (last contact, open opportunities) via REST/GraphQL.

  2. CIBSeven BPMN & DMN

    • Orchestrates “customer interaction” and “next-best-action” processes.

  3. Service APIs

    • Consent service: Checks consent before interaction.

    • CRM service: Writes after-call summaries & NBX recommendations to the CRM.

    • NBX engine: Machine learning-based action suggestions.

    • MuleSoft MCP Server: Exposes MuleSoft APIs & integrations as MCP for Agent AI.

  4. Messaging gateway

    • Delivery via LeapXpert, Infobip, Unblu, Qwil.

  5. Rasa Agent AI

    • Uses Rasa NLU/Stories for initial contact, forwards complex requests to agents.

  6. Monitoring & Audit

    • Complete logging of all process instances, decisions, API calls in CIBSeven Cockpit.


6 Conclusion: Flexibility & future-proofing thanks to MCP & Agent AI

With Model Context Protocol (MCP) and Agent AI, banks are creating a modular, context-driven and AI-enabled communication platform. The building block approach – from MuleSoft MCP and LeapXpert to Rasa and CIBSeven – allows next-best-action, compliance and omnichannel workflows to be optimally linked. So financial institutions are fit for the AI-native future!


Leave a Reply

Your email address will not be published. Required fields are marked *