MCP SERVERQuestion a Genesys Cloud contact centre in plain language: queue volumes, call quality, sentiment, detected topics and full conversation transcripts.
LABSCO SUMMARY
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.
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 credentials — npx -y @makingchatbots/genesys-cloud-mcp-server, then supply credentials
USE CASES
Search queues by name pattern, then compare conversation volumes across them over a date range.
Pull the voice conversations for the window, then read the lowest Mean Opinion Score recorded on each.
Take a sample of conversations from a queue, then fetch a time-aligned transcript with speaker labels.
Sample conversation IDs for the queue and score sentiment across them in one call.
Read the topics Speech and Text Analytics detected on a conversation.
List the OAuth clients with their roles and divisions, then check one client's request volume by endpoint.
Counted once with only startup setup. Other versions, modes or optional credentials may expose a different list.
conversation_sentimentRetrieves sentiment analysis scores for one or more conversations. Sentiment is evaluated based on customer phrases, categorized as positive, neutral, or negative. The result includes both a numeric sentiment score (-100 to 100) and an interpreted sentiment label.
conversation_topicsRetrieves Speech and Text Analytics topics detected for a specific conversation. Topics represent business-level intents (e.g. cancellation, billing enquiry) inferred from recognised phrases in the customer-agent interaction.
conversation_transcriptRetrieves a structured transcript of the conversation, including speaker labels, utterance timestamps, and sentiment annotations where available. The transcript is formatted as a time-aligned list of utterances attributed to each participant (e.g., customer or agent)
oauth_client_usageRetrieves the usage of an OAuth Client for a given period. It returns the total number of requests and a breakdown of Platform API endpoints used by the client.
oauth_clientsRetrieves a list of all OAuth clients, including their associated roles and divisions. This tool is useful for auditing and managing OAuth clients in the Genesys Cloud organization.
query_queue_volumesReturns a breakdown of how many conversations occurred in each specified queue between two dates. Useful for comparing workload across queues. MAX 300 queue IDs.
sample_conversations_by_queueRetrieves conversation analytics for a specific queue between two dates, returning a representative sample of conversation IDs. Useful for reporting, investigation, or summarisation.
search_queuesSearches for routing queues based on their name, allowing for wildcard searches. Returns a paginated list of matching queues, including their Name, ID, Description (if available), and Member Count (if available). Also provides pagination details like current page, page size, total results found, and total pages available. Useful for finding specific queue IDs, checking queue configurations, or listing available queues.
search_voice_conversationsSearches for voice conversations within a specified time window, optionally filtering by phone number. Returns a paginated list of conversation IDs and call duration for use in further analysis or tool calls.
voice_call_qualityRetrieves voice call quality metrics for one or more conversations by ID. This tool specifically focuses on voice interactions and returns the minimum Mean Opinion Score (MOS) observed in each conversation as structured JSON. MOS is a measure of perceived audio quality based on factors such as jitter, latency, packet loss, and codec. Use the following legend to interpret MOS values:
BEFORE YOU INSTALL
10 tools when we connected. Tools are called by snake_case ids such as search_queues, not the Title Case names in the feature table. Each needs a Genesys Cloud permission, for example routing:queue:view, so an under-scoped OAuth client fails. All ten only read.
CONTEXT COST
Rated by the size of the 10 tool definitions that ride along on every turn, not by how many there are
INSTALLATION
npx -y @makingchatbots/genesys-cloud-mcp-serverDownload the .mcpb file from the latest release, then Claude Desktop → Settings > Extensions → open the .mcpb file → configure the Region and OAuth Client
{
"mcpServers": {
"genesys-cloud": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@makingchatbots/genesys-cloud-mcp-server"
],
"env": {
"GENESYSCLOUD_REGION": "<YOUR_GENESYSCLOUD_REGION>",
"GENESYSCLOUD_OAUTHCLIENT_ID": "<YOUR_GENESYSCLOUD_OAUTHCLIENT_ID>",
"GENESYSCLOUD_OAUTHCLIENT_SECRET": "<YOUR_GENESYSCLOUD_OAUTHCLIENT_SECRET>"
}
}
}
}{
"mcpServers": {
"genesysCloud": {
"command": "npx",
"args": [
"-y",
"@makingchatbots/genesys-cloud-mcp-server"
],
"env": {
"GENESYSCLOUD_REGION": "${GENESYSCLOUD_REGION}",
"GENESYSCLOUD_OAUTHCLIENT_ID": "${GENESYSCLOUD_OAUTHCLIENT_ID}",
"GENESYSCLOUD_OAUTHCLIENT_SECRET": "${GENESYSCLOUD_OAUTHCLIENT_SECRET}"
}
}
}
}MCP servers
sapph1re
echelon-ai-labs
reminia
effytech