One AI Chat to Rule Them All: Connecting Enterprise Tools with MCP
summary
Demonstrates an on‑prem AI integration using the Model Context Protocol (open‑sourced by Anthropic Nov 2024 and donated to the Linux Foundation with OpenAI/Google/Microsoft endorsements). Uses Ollama + Open WebUI + mcpo proxy as the local stack and deploys MCP servers for Mattermost→Atlassian Jira and Obsidian. The running demo fetches channel messages, summarizes discussion, and creates two Jira tickets successfully; Obsidian note creation is implemented but intermittently fails in the live demo.
AI-written summary · about
chapters (8)
- 0:00Connecting AI with enterprise tools
- 1:25Limitations of traditional AI integrations
- 2:30Model Context Protocol
- 4:56MCP for structured tool access
- 6:39Live demo: Mattermost and Jira
- 11:59Enhancing interactions with visuals
- 13:29Future possibilities and adoption
- 15:17Live demo: Obsidian integration
related talks
37mLetting AI Interface with Your App with MCPs
36mPutting AI Agents to Work: A New Era of Open Source Connectivity with MCP
33mThe Model Context Protocol: Connecting AI to Everything
30mComposable AI: Building Next-Gen AI Agents with MCP
29mEmpowering Your Product with Agentic AI
20mLetting AI Interface with your App with MCP
54mFrom Single-Shot LLMs to Intelligent Agents: Building Scalable AI Systems with Spring AI and MCP
21mIntegrate Your APIs into the New AI Marketplace