# @cognigy/plugin-engine [Health: Active]

**Category:** 🗣️ Conversational AI  
**Repository:** https://github.com/Cognigy/cognigy-plugin  
**GitHub Stars:** 18  
**npm Downloads (last month):** 2452  
**Views:** 0  
**Installs:** 0  
**Upvotes:** 0  
**Directory Page:** https://allmcps.com/mcp/cognigy-plugin-engine

## Description
MCP server engine for the NiCE Cognigy Plugin (Claude Code, Codex, and more)

## Tools
Capabilities this server exposes over MCP:

- **create_ai_agent** — Create a complete AI Agent with auto-provisioned flow, job node, and REST endpoint
- **update_ai_agent** — Update persona, guardrails, job config (role, procedures, LLM, temperature)
- **setup_llm** — Create an LLM resource (GPT-4, Claude, Mistral, etc.) with automatic connection validation
- **talk_to_agent** — Send a message to an AI Agent and get its response (uses Endpoint Test Mode, so it is not counted as billable)
- **list_resources** — List projects, agents, flows, endpoints, LLMs, knowledge stores, and more
- **get_resource** — Get detailed information about a single resource
- **delete_resource** — Permanently delete a resource
- **manage_knowledge** — Create knowledge stores, add sources (URL, text, file), list chunks for RAG
- **create_tool** — Add a tool (HTTP, knowledge, email, MCP, A2A) to an agent's job node
- **update_tool** — Update an existing tool node's configuration
- **manage_webchat** — Create or configure a Webchat v3 endpoint for website deployment
- **manage_flow_nodes** — Create, update, delete, or list flow nodes for conversation logic
- **manage_packages** — List exportable resources, upload, inspect, import, export, and download Cognigy package zip files
- **manage_voice_gateway** — Create or configure a Voice Gateway endpoint with WebRTC for browser-based voice interaction
- **manage_a2a_server** — Deploy a Flow as an A2A (Agent2Agent) server endpoint that other agents can discover and call
- **manage_settings** — Manage project-level settings including voice preview and Knowledge AI configuration
- **audit_voice_agent** — Audit a voice agent against the Go-Live Checklist; reports by default, applies safe fixes on demand
- **manage_snapshots** — Create and restore project Snapshots so agent changes can be rolled back

## Claude Desktop Quick Installation
Install path detected from listing signals. Uses `npx` (confidence: high):

```json
"mcpServers": {
  "plugin-engine": {
    "command": "npx",
    "args": ["-y","-p","@cognigy/plugin-engine@latest","cognigy-setup"],
    "env": {
      "COGNIGY_API_BASE_URL": "",
      "COGNIGY_API_KEY": ""
    }
  }
}
```

**Requires environment variables:** `COGNIGY_API_BASE_URL`, `COGNIGY_API_KEY` — the values above are empty placeholders; fill in real credentials before running (see the repository for what each one is for).

## Documentation

## What @cognigy/plugin-engine does

The @cognigy/plugin-engine MCP server connects an AI assistant to the Cognigy.AI REST API and exposes workflows for building and operating conversational agents. It belongs in the Conversational AI category and covers more than basic agent creation: projects can be configured with LLM resources, knowledge stores, tools, webchat endpoints, voice endpoints, and A2A server endpoints.

The main agent workflow can create an agent together with a flow, an AI Agent job node, and a REST endpoint. After creation, an assistant can change the agent persona, guardrails, job role, procedures, selected LLM, and temperature. The `talk_to_agent` tool sends test messages through Endpoint Test Mode, which the supplied documentation says is not billable.

Other tools provide resource discovery and administration. They can list Cognigy resources, retrieve one resource in detail, delete resources, manage flow nodes, create or update tools, and create or configure deployment endpoints. Snapshot support provides a way to save and restore project changes.

## How it works

The @cognigy/plugin-engine MCP server packages the Cognigy API operations as MCP tools. An AI client invokes a tool with structured input, and the engine validates requests before calling Cognigy. The implementation includes Zod input validation, rate limiting, and RFC 7807-style error responses.

Knowledge workflows can create stores and add URL, text, or file sources, then list chunks for retrieval-augmented generation. Tool management supports HTTP, knowledge, email, MCP, and A2A tool types. Voice workflows can create Voice Gateway endpoints with WebRTC, while webchat workflows target Webchat v3 endpoints for website deployment. A flow can also be exposed as an A2A endpoint for discovery and calls from other agents.

The package includes skills and agents in clients that support them. These provide workflow guidance for activities such as agent building, knowledge configuration, voice readiness checks, webchat, packages, settings, tools, and troubleshooting. It also bundles the official Cognigy documentation MCP server for documentation lookup.

## Setup and configuration

Installation is handled through the `cognigy-setup` installer. Node.js 20 or newer is required. The installer accepts a Cognigy API base URL and API key, then installs or configures the plugin for the selected client. A noninteractive setup can pass client and credential values as command-line flags.

The @cognigy/plugin-engine MCP server requires `COGNIGY_API_BASE_URL` and `COGNIGY_API_KEY` when launched with environment configuration. The installer can instead store credentials in `~/.cognigy-plugin/config.json`; environment values take precedence, and the file is used as a fallback when a required value is unavailable. `LOG_LEVEL`, `RATE_LIMIT_MAX_REQUESTS`, and `RATE_LIMIT_WINDOW_MS` are optional overrides.

The README documents support for Claude Code, Claude Desktop, ChatGPT with Codex, Antigravity, Cursor, and other Agent Plugins-compatible hosts such as Kiro and VS Code with Copilot. Cursor has its own setup path and asks for credentials in its plugin configuration.

## Limitations and notes

The supplied material does not describe a standalone Cognigy account or project provisioning process, so users need access to a Cognigy.AI environment and valid API credentials. Deleting a resource is permanent. Endpoint Test Mode avoids billing for the documented agent conversation test, but that statement does not apply broadly to every Cognigy operation.

Client behavior differs. Some clients install the plugin automatically, while others require an in-app or host-level installation step. Auto-update behavior also depends on the client. The engine falls back when credentials are absent from a supported environment configuration, but an unexpanded `${...}` placeholder is treated as missing rather than as a usable key.

_Full upstream README: https://allmcps.com/mcp/cognigy-plugin-engine/readme_