Which integrations are available for this server?

Allows for the creation and management of tasks on the GitHub platform as part of a multi-platform task orchestration system. Integrates with n8n to trigger automated workflows and orchestrate complex tasks directly from the agent. Enables the creation of tasks and management of interactions within the Slack platform. Utilizes Supabase and its pgvector extension for semantic search (RAG) and persistent storage of conversation context.

How do I use Jarvis MCP Server?

1. Click on "Install Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Jarvis MCP Server search my memory for our last discussion about the product roadmap" That's it! The server will respond to your query, and you can continue using it as needed. Here is a step-by-step guide with screenshots.

🚀 Jarvis MCP Server

Production-Ready HTTP MCP Server für Claude Desktop Integration

Verbindet Claude ↔ n8n ↔ Supabase für autonome Jarvis-Agenteneichung.

✨ Features

✅ Semantic Search – conversation_search via Supabase pgvector (RAG)
✅ Memory Management – Persistente Speicherung aller Interactions
✅ Workflow Orchestration – n8n-Integration für Task-Automatisierung
✅ Task Creation – Multi-Platform (Monday.com, GitHub, Slack)
✅ Agent Monitoring – Status & Health Checks
✅ Production Ready – Zero-Downtime Deployment

📚 Verfügbare MCP-Tools

`conversation_search`

Semantic Search in Jarvis Knowledge Base (RAG via pgvector)

`save_context`

Speichere Claude-Jarvis Interaktionen für Future Retrieval

`trigger_workflow`

Starte n8n Workflows direkt

`create_task`

Erstelle Tasks über Multiple Plattformen

`get_agent_status`

Agenten-Monitoring & Health Checks

🚀 Replit Deployment

GitHub Connection (in Replit Settings)
Set Secrets (siehe .env.example)
Run – Auto-Deploy

🔌 Claude Desktop Config

{
  "mcpServers": {
    "jarvis": {
      "command": "curl",
      "args": ["-X", "POST", "https://YOUR-REPLIT-URL/mcp/tools/call"],
      "env": {
        "MCP_SERVER_URL": "https://YOUR-REPLIT-URL"
      }
    }
  }
}