AI-Native Control Plane
The Model Context Protocol (MCP) is an open standard that allows AI assistants to interact with external tools. EDDI implements a comprehensive MCP server with 42 tools spanning every aspect of the platform.
Tool Categories
- Conversation Tools — Chat with agents, manage conversations, read history
- Admin Tools — List, inspect, and manage deployed agents
- Setup Tools — Create complete agents in a single call with
setup_agent - Resource CRUD — Full create/read/update/delete for rules, workflows, LLM configs, connectors
- Diagnostic Tools — Health checks, configuration inspection, environment diagnostics
- Schedule Management — Manage periodic agent tasks and triggers
MCP Client Support
EDDI agents can also consume external MCP tools during conversations. Configure MCP server endpoints, and agents auto-discover and invoke tools based on conversation context — powered by LangChain4j's MCP client integration.