Genesys Flow MCP
Connects to Genesys Cloud to list IVR routes and retrieve IVR flow configurations, generating readable Markdown documentation covering business and technical details, prompts, and integrations.
README
Genesys Flow MCP
Local MCP server that connects to Genesys Cloud, lists IVR routes, retrieves an IVR's configured open-hours flow, and produces readable Markdown documentation.
The generated document is structured for both business and technical readers:
- Route — IVR name, ID, state, DNIS (when available), and configured flow.
- Business Focus — the flow purpose and customer menu routing.
- Technical Focus — flow settings, variables, prompts/TTS, tasks, menus, and decision paths.
- Integrations and Routing Dependencies — Data Actions, Bot Flows, and ACD queues.
Prerequisites
- Node.js 18 or later
- A Genesys Cloud OAuth client using the Client Credentials grant
- Permissions to read Architect IVRs and flows in the relevant Genesys Cloud organisation
Install and configure
Install dependencies:
cd <path-to-genesys-flow-mcp>
npm install
Create a .env file in the project root:
GENESYS_CLIENT_ID=your-client-id
GENESYS_CLIENT_SECERET=your-client-secret
GENESYS_REGION=ie
Important:
GENESYS_CLIENT_SECERETis intentionally spelled this way because it matches the current source code. Do not rename it toSECRETunless you also updatesrc/config/env.ts.
Set GENESYS_REGION to your Genesys Cloud region suffix, for example ie for mypurecloud.ie.
Run locally
For development:
npm run dev
For the compiled server used by desktop clients:
npm run build
npm start
The server uses the MCP stdio transport. It is started by the MCP client; it does not expose a browser URL or HTTP port.
Test with MCP Inspector
Use the MCP Inspector to test the server directly before connecting it to Claude Desktop:
cd <path-to-genesys-flow-mcp>
npm run inspect
The Inspector opens a local browser interface. In it:
-
Connect to the server using the default stdio configuration.
-
Open the Tools tab.
-
Run
get_ivrsto confirm Genesys authentication and route retrieval. -
Run
get_flow_by_namewith an IVR name, for example:{ "name": "testt call" } -
Check that the response starts with the Route section and includes the configured flow, prompts, and integrations.
Available tools
get_ivrs
Returns the Genesys Cloud routing/IVR list.
Example request:
List the available Genesys IVRs.
get_flow_by_name
Looks up an IVR by name, retrieves its configured open-hours flow, and returns Markdown documentation.
Input:
{
"name": "testt call"
}
Example request:
Use get_flow_by_name for the IVR named "testt call".
If the IVR is not found, or it has no open-hours flow, the tool returns an error describing the problem.
What the generated documentation includes
The documentation follows the relationship below:
Genesys IVR Route
↓
Configured Open-Hours Flow
├── Business Focus: customer routing and menu choices
└── Technical Focus: prompts, variables, tasks, menus, integrations
Integration detection covers the common Architect dependencies below:
| Architect element | Documented as |
|---|---|
DataAction |
Data Action / Web Services Data Action |
CallBotFlowAction |
Bot Flow, including name and flow ID |
TransferPureMatchAction |
ACD Queue |
All TTS prompts found in tasks and menu greetings are included in the technical flow walk.
Test with Claude Desktop
-
Build the project:
cd <path-to-genesys-flow-mcp> npm run build -
In Claude Desktop, open:
File → Settings → Developer → Edit Config -
Add the following at the top level of the opened JSON file. Preserve any existing settings such as
preferences.{ "mcpServers": { "genesys-flow": { "command": "node", "args": [ "<path-to-genesys-flow-mcp>\\dist\\index.js" ], "env": { "GENESYS_CLIENT_ID": "your-client-id", "GENESYS_CLIENT_SECERET": "your-client-secret", "GENESYS_REGION": "ie" } } } }Replace
<path-to-genesys-flow-mcp>with the full path to your local project folder. If the file already contains properties, addmcpServersalongside them and ensure the preceding property ends with a comma. -
Fully quit and reopen Claude Desktop.
-
Start a new chat and ask:
What Genesys tools are available?Then test the documentation:
Use get_flow_by_name for the IVR named "testt call" and document its route, configured flow, prompts, and integrations.
Do not commit or share the Claude Desktop config if it contains your client secret. For a local test on a personal device, passing the credentials through the MCP env block is acceptable. Use a dedicated OAuth client with the minimum required Genesys permissions.
Build check
Run the TypeScript build check after code changes:
npm run build
Project structure
src/
├── config/ Environment variable validation
├── mcp/ MCP server and tool registration
├── services/ Genesys authentication, API access, and documentation generation
├── tools/ MCP tool handlers
└── types/ Genesys Cloud response types
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.