The work has a consistent shape: search for the queue or the conversations first, then hand those IDs to the analytics tools. Permissions are granted per tool rather than all at once, so scope the OAuth client to cover the tools you actually intend to call.
An MCP server over the Genesys Cloud Platform API, built for reporting and investigation: it finds the queues and conversations first, then pulls the analytics attached to them.
- Queue search by name with wildcards, returning IDs, descriptions and member counts, paginated up to 500 per page
- Workload comparison across up to 300 queues at once for a date range
- A representative sample of conversation IDs for one queue between two dates, meant as the starting point for deeper calls
- Voice conversation search in a time window, optionally filtered by phone number, returning IDs and call durations
- Voice quality per conversation as the minimum Mean Opinion Score observed in it
- Customer sentiment as both a numeric score from -100 to 100 and an interpreted label
- Speech and Text Analytics topics for a conversation — the business intents detected in it, such as cancellation or billing enquiry
- A time-aligned transcript with speaker labels and, where available, sentiment annotations
- An audit view of the org's OAuth clients with their roles and divisions, plus one client's request volume broken down by Platform API endpoint
A Genesys Cloud OAuth client, with the permissions for the tools you plan to use assigned to it — the tool reference names them per tool, for example routing:queue:view for queue search and analytics:conversationDetail:view for queue volumes. Three environment variables carry it: GENESYSCLOUD_REGION, GENESYSCLOUD_OAUTHCLIENT_ID and GENESYSCLOUD_OAUTHCLIENT_SECRET. It is a stdio server — run it with npx -y @makingchatbots/genesys-cloud-mcp-server, or install the .mcpb bundle from the releases page in Claude Desktop.
One command plus a key — npx -y @makingchatbots/genesys-cloud-mcp-server, then supply credentials