NiCE Cognigy Plugin

The NiCE Cognigy Plugin connects your client to the Cognigy.AI REST API. You can create, test, and improve LLM-based AI Agents without leaving your development environment. The plugin includes a version-matched server engine, skills, agents, and scripts. The server engine runs as a Model Context Protocol (MCP) server, exposing Cognigy.AI capabilities to your client.

Key Benefits

Comprehensive API coverage. 16 tools cover the Cognigy.AI API. They automate everything from creating an AI Agent to deploying it on voice and web channels.
Fast setup and iteration. Create an AI Agent, Flow, AI Agent Node, and REST Endpoint in a single call. Then talk to the AI Agent, refine it, and repeat with a built-in self-improvement loop.
Guidance built in. Skills load automatically when your request matches. Dedicated agents run the full build-and-test and voice go-live loops for you.
Reliable and safe operations. Rate limiting, Zod input validation, and standardized RFC 7807 error responses keep operations safe.

Prerequisites

A Cognigy.AI API key. To create one, go to User Menu > My Profile > API Keys > Create New.
A Cognigy.AI API base URL. For example, for the trial environment, use https://api-trial.cognigy.ai.
A supported client: Claude Code, Codex, or Claude Desktop.
Node.js 20 or later.

How to Set Up

Claude Code
Codex
Claude Desktop
Manual and CI

Run the installer in your terminal. It checks for Node.js and prompts you to select your client. It also asks for your Cognigy.AI API base URL and API key. Then it wires the credentials automatically.macOS and Linux:

bash <(curl -fsSL https://raw.githubusercontent.com/Cognigy/cognigy-plugin/main/install.sh)

Windows (PowerShell, run as Administrator):

irm https://raw.githubusercontent.com/Cognigy/cognigy-plugin/main/install.ps1 | iex

If you already have Node.js 20 or later, you can skip the bootstrap and run the installer directly:

npx -y -p @cognigy/plugin-engine@latest cognigy-setup

Restart Claude Code after setup completes. You now have the tools, skills, and agents.

The first Claude Code session downloads the engine. If the tools don’t appear, run /mcp and reconnect, or restart the client. On Windows, fully quit Claude Code. End every Claude process in Task Manager because a normal close can leave it running in the background. Then reopen the client.

Claude Code leaves auto-updates off for third-party marketplaces by default. Turn them on so future fixes reach you automatically. For more information, see Get Plugin Updates.

For Codex, add the server manually to your Codex configuration file at ~/.codex/config.toml:

[mcp_servers.cognigy]
command = "npx"
args = ["-y", "-p", "@cognigy/plugin-engine@latest", "cognigy-mcp"]

[mcp_servers.cognigy.env]
COGNIGY_API_BASE_URL = "your-api-base-url"
COGNIGY_API_KEY = "your-api-key"

Replace the values with your Cognigy.AI API base URL and API key. Restart Codex to load the tools. This setup gives Codex the plugin tools. Skills and agents load in Codex.

Setting up Claude Desktop takes two steps. First, run the installer to wire the tools. Then add the plugin in the app to get the skills and agents.

Run the installer for your platform, as shown in the Claude Code tab. Select Claude Desktop when prompted. This wires the connector that serves the tools.
In Claude Desktop, select Customize in the left-side menu.
Next to Personal plugins, select +, hover over Add, and select Add marketplace.
In the URL field, enter Cognigy/cognigy-plugin, select the result, and select Sync.
Install the Cognigy plugin by selecting +. Then select Continue on the local MCP warning.

Leave the plugin’s own platform connector unconnected. The Cognigy connector wired by the installer already serves the tools.

Manual install (Claude Code). Instead of running the installer, use these commands:

/plugin marketplace add Cognigy/cognigy-plugin
/plugin install cognigy@cognigy-plugin

Then wire your credentials:

npx -y -p @cognigy/plugin-engine@latest cognigy-setup --client claude-code

Scripting and CI. Skip the prompts with flags:

npx -y -p @cognigy/plugin-engine@latest cognigy-setup \
  --client claude-code --client claude-desktop \
  --api-base-url https://api-trial.cognigy.ai --api-key <key>

Configuration

The installer from How to Set Up collects your Cognigy.AI API base URL and API key. It saves them securely for each client you selected, such as the system keychain for Claude Code. The engine then reads them as environment variables. The following optional variables let you override the defaults.

Variable	Required	Default	Description
`COGNIGY_API_BASE_URL`	Yes	None	Your Cognigy.AI API base URL.
`COGNIGY_API_KEY`	Yes	None	Your Cognigy.AI API key.
`LOG_LEVEL`	No	`info`	One of `debug`, `info`, `warn`, `error`.
`RATE_LIMIT_MAX_REQUESTS`	No	`100`	Maximum requests per window.
`RATE_LIMIT_WINDOW_MS`	No	`60000`	Rate limit window in milliseconds.

Available Tools

The plugin provides the following tools to automate Cognigy.AI workflows. Each tool has a type of Read or Write, indicating whether it reads data from Cognigy.AI or writes data to it.

Tool	Type	Description
`create_ai_agent`	Write	Create a complete AI Agent with an auto-provisioned Flow, AI Agent Node, and REST Endpoint.
`update_ai_agent`	Write	Update the persona, guardrails, and job configuration (role, procedures, LLM, temperature).
`setup_llm`	Write	Create an LLM resource (GPT-4, Claude, Mistral, and others) with automatic connection validation.
`talk_to_agent`	Write	Send a message to an AI Agent and get its response.
`list_resources`	Read	List Projects, AI Agents, Flows, Endpoints, LLMs, Knowledge Stores, and more.
`get_resource`	Read	Get detailed information about a single resource.
`delete_resource`	Write	Permanently delete a resource.
`manage_knowledge`	Write	Create Knowledge Stores, add sources (URL, text, file), and list chunks for RAG.
`create_tool`	Write	Add a tool (HTTP, knowledge, email, MCP) to an AI Agent Node.
`update_tool`	Write	Update an existing tool Node’s configuration.
`manage_webchat`	Write	Create or configure a Webchat v3 Endpoint for website deployment.
`manage_flow_nodes`	Write	Create, update, delete, or list Flow Nodes for conversation logic.
`manage_packages`	Write	List exportable resources, and upload, inspect, import, export, and download Cognigy.AI Package zip files.
`manage_voice_gateway`	Write	Create or configure a Voice Gateway Endpoint with WebRTC for browser-based voice interaction.
`manage_settings`	Write	Manage Project-level settings, including voice preview and Knowledge AI configuration.
`audit_voice_agent`	Write	Audit a voice agent against the Go-Live Checklist. It reports by default and applies safe fixes on demand.

Security

API keys are passed through environment variables and are never logged.
All inputs are validated with Zod schemas before reaching the API.
Rate limiting protects the API from excessive or abusive requests.

Privacy

The NiCE Cognigy plugin sends requests only to the Cognigy.AI API base URL that you configure. The plugin doesn’t collect, store, or share any data. All data stays between your client and your Cognigy.AI instance. For more information, see the Cognigy Privacy Policy.

How to Use

Once the plugin is installed, you can interact with Cognigy.AI using natural language prompts in your client. The following examples show prompts for common workflows and the tools the client runs in response.

Create an AI Agent

Ask your client to create an AI Agent in a Cognigy.AI Project:

Create a Cognigy AI Agent called "Support Bot" in Project <projectId>.
Give it a helpful customer support persona, set up an LLM,
and return the endpoint URL so I can test it.

This workflow uses the setup_llm tool to create the LLM resource. It then uses the create_ai_agent tool to provision the AI Agent, Flow, and REST Endpoint.

Test and Improve the Agent

Send a message to the AI Agent, refine its instructions, and compare responses:

Talk to my Support Bot at <endpointUrl> and ask "How do I reset my password?".
Then update the job description to make the response more concise and actionable.
Talk to it again and compare the responses.

This workflow uses a self-improvement loop: talk_to_agent, then evaluate, then update_ai_agent, then talk_to_agent again.

Add a Knowledge Store

Attach a Knowledge Store so the AI Agent can search approved content when answering questions:

Create a Knowledge Store in Project <projectId>, add the URL
https://docs.example.com/faq as a source, then attach it to my Support Bot
so the AI Agent can reference it to answer questions.

This workflow uses the manage_knowledge tool to create the store and ingest the source. It then uses create_tool to attach the store as a knowledge search tool on the AI Agent Node.

Deploy to Voice

Configure voice preview and create a browser-based Voice Gateway Endpoint:

Set the voice preview provider for Project <projectId> to Microsoft, then create
a Voice Gateway endpoint for flow <flowId> named "Support Voice" and give me the
WebRTC demo URL I can open in the browser.

This workflow uses manage_settings with the set_voice_preview operation to configure speech. It then uses manage_voice_gateway to provision a Voice Gateway Endpoint with a WebRTC demo URL.

Export and Import Packages

Upload a Package, preview the import, and import it into a Project:

Upload the package at /absolute/path/to/support-bot.zip into Project <projectId>,
show me the import preview, then import it using the default selections.

You can also drag and drop files into some clients to upload them.

This workflow uses the manage_packages tool with the operations upload_and_inspect and then import.

Review Existing Resources

List resources to inspect Projects, AI Agents, or conversations:

List all my Cognigy.AI Projects and show which AI Agents exist in each one.

This workflow uses the list_resources tool with the resource types project and agent. You can also ask for recent conversations and summarize the returned data.

Get Plugin Updates

Claude Desktop updates the engine on every launch. Claude Code updates only when marketplace auto-updates are enabled. Third-party marketplaces default to off. To turn auto-updates on, go to /plugin > Marketplaces > cognigy-plugin, or run /plugin update cognigy@cognigy-plugin. The installer also works as a manager. Run the same cognigy-setup command with a subcommand:

npx -y -p @cognigy/plugin-engine@latest cognigy-setup status      # Show what's installed and the latest available version
npx -y -p @cognigy/plugin-engine@latest cognigy-setup update      # Pull the latest version (Claude Code)
npx -y -p @cognigy/plugin-engine@latest cognigy-setup uninstall   # Remove the plugin and connector (add --purge to also clear ~/.cognigy-plugin)

Overview

AI Agents

Human Escalation

Platform Features

For Developers

Administration and Installation

Key Benefits

Prerequisites

How to Set Up

Configuration

Available Tools

Security

Privacy

How to Use

Get Plugin Updates

More Information

​Key Benefits

​Prerequisites

​How to Set Up

​Configuration

​Available Tools

​Security

​Privacy

​How to Use

​Get Plugin Updates

​More Information

Key Benefits

Prerequisites

How to Set Up

Configuration

Available Tools

Security

Privacy

How to Use

Get Plugin Updates

More Information