Genesys Cloud MCP Server exposes Genesys Cloud Platform API tools for queue, conversation, quality, sentiment, topic, transcript, and OAuth client analysis via MCP clients.
Search routing queues by name with wildcards and pagination.
Query queue conversation volumes and member counts by queue IDs and date range.
Sample representative conversation IDs for a queue between dates.
Retrieve voice call quality metrics, including minimum MOS.
Retrieve conversation sentiment scores and interpreted labels.
Retrieve detected Speech and Text Analytics conversation topics.
Search voice conversations by date range and optional phone number.
Retrieve structured conversation transcripts with speakers, timestamps, and sentiment where available.
List OAuth clients and retrieve OAuth client usage for a specified period.
Run as a stdio MCP server configured with Genesys Cloud region and OAuth client credentials.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Genesys Cloud MCP Server show me conversation volumes for queue 'customer_support' yesterday"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
A Model Context Protocol (MCP) server for Genesys Cloud's Platform API.
Tool | Description |
Searches for queues by their name (supports wildcards) | |
Retrieves conversation volumes and member count by Queue IDs | |
Retrieves a representative sample of Conversation IDs for a Queue ID | |
Retrieves voice call quality metrics for one or more conversations by ID | |
Retrieves the sentiment for one or more conversations by ID | |
Retrieves the topics for a conversation by ID | |
Searches voice conversations by optional criteria | |
Retrieves conversation transcript | |
Retrieves a list of all the OAuth clients | |
Retrieves OAuth client usage for given period |
Related MCP server: Genesys Cloud MCP Server
This MCP Server provides an MCP Bundle (.mcpb file) along with each release, which is a single-click installable package for Claude Desktop. To use it:
Download the .mcpb file from the latest release
In Claude Desktop navigate to Settings > Extensions.
Open the .mcpb file with Claude
Configure the Region and OAuth Client for the extension
The extension will now be available in your conversations.
Add this to your claude_desktop_config.json:
{
"mcpServers": {
"genesys-cloud": {
"type": "stdio",
"command": "npx",
"args": ["-y", "@makingchatbots/genesys-cloud-mcp-server"],
"env": {
"GENESYSCLOUD_REGION": "<PUT REGION HERE>",
"GENESYSCLOUD_OAUTHCLIENT_ID": "<PUT OAUTHCLIENT ID HERE>",
"GENESYSCLOUD_OAUTHCLIENT_SECRET": "<PUT OAUTHCLIENT SECRET HERE>"
}
}
}
}Add below to your .gemini/settings.json file. You can read more about the setup from the official guide.
{
"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}"
}
}
}
}This currently only supports a stdio server. To configure authentication you'll need to:
Create an OAuth Client in Genesys Cloud
Assign the permissions to it for the tools you want to be used
Provide the following environment variables when referencing the server:
GENESYSCLOUD_REGION
GENESYSCLOUD_OAUTHCLIENT_ID
GENESYSCLOUD_OAUTHCLIENT_SECRET
nvm use
npm install
npm run devThis is part of personal project to create a conversational Business Insights tool. It is a practical way for me to learn MCP servers, and how best to represent Genesys Cloud's Platform APIs in a way that can be easily consumed by LLMs.
There will be a lot of changes, and I will be sure to share my learnings in my newsletter.
Retrieves 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.
Inputs: conversationIds (required).
Retrieves 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.
Inputs: conversationId (required).
Retrieves 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)
Inputs: conversationId (required).
Retrieves 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.
Inputs: no named parameters.
Retrieves 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.
Inputs: oauthClientId (required), startDate (required), endDate (required).
Returns a breakdown of how many conversations occurred in each specified queue between two dates. Useful for comparing workload across queues. MAX 300 queue IDs.
Inputs: queueIds (required), startDate (required), endDate (required).
Retrieves conversation analytics for a specific queue between two dates, returning a representative sample of conversation IDs. Useful for reporting, investigation, or summarisation.
Inputs: queueId (required), startDate (required), endDate (required).
Searches 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.
Inputs: name (required), pageNumber, pageSize.
Searches 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.
Inputs: startDate (required), endDate (required), phoneNumber, pageNumber, +1 more.
Retrieves 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:
• Poor: MOS < 3.5 • Acceptable: 3.5 ≤ MOS < 4.3 • Excellent: MOS ≥ 4.3
Inputs: conversationIds (required).
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Scored across 10 tools
Most tools target clearly distinct outputs: queue search, conversation search, transcripts, sentiment, topics, call quality, and OAuth data. The main ambiguity is between sample_conversations_by_queue and query_queue_volumes, both of which aggregate conversations by queue, though their descriptions do clarify that one returns IDs and the other returns counts.
All names are snake_case and readable, but conventions are mixed: four tools start with action verbs (search_queues, sample_conversations_by_queue, query_queue_volumes, search_voice_conversations) while the remaining six start with resource nouns (conversation_topics, oauth_clients, etc.). The conversation_* group is consistent, but there is no single predictable pattern across the set.
With 10 tools, the set is well within the ideal range and each tool serves a distinct part of the Genesys Cloud surface: queue lookup, conversation search, analytics, transcripts, quality, and OAuth auditing. No tool feels redundant or unnecessary.
The set supports a coherent read/analytics workflow: find queues, search or sample conversations, then retrieve transcripts, topics, sentiment, and call quality for conversation IDs. Gaps such as non-voice conversation search and OAuth client management exist, but they appear to be outside the intended analytics/audit scope.
Manage CallKaro voice agents, phone numbers, call queues, and place single or batch AI calls.
CX ops: read conversations, calls and QA evaluations from Zendesk, Freshdesk, Five9 and more.
Manage AI assistants, history, calls, campaigns, contacts, knowledge, messaging, and automations.
Reporting, callback operations, queue settings and Custom IVR flows for RingCentral call queues.
