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 β Chat with agents, manage conversations, read history
- Admin Tools β List, inspect, and manage deployed agents
- Setup Tools β Create complete agents in a single call with
setup_agent - Resource CRUD β Full create/read/update/delete for rules, workflows, LLM configs, connectors
- Diagnostic Tools β Health checks, configuration inspection, environment diagnostics
- Schedule Management β Manage periodic agent tasks and triggers
- OpenAPI 3.1 β Auto-generated OpenAPI spec. Paste any external OpenAPI spec into EDDI β get a fully deployed API-calling agent
Open Standards β Not Proprietary APIs
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. Beyond MCP, EDDI implements A2A (Agent-to-Agent Protocol) for cross-platform agent communication, OpenAPI 3.1 for native spec generation and consumption, OAuth 2.0 / OIDC via Keycloak, and SSE for real-time streaming β all open standards, zero vendor lock-in.