Solutif Genesys Cloud MCP Server
# Solutif Genesys Cloud MCP Server
Solutif's MCP server for Genesys Cloud Platform API operations and analytics.
## Tools
| Tool | Description |
|---|---|
| [`create_queue`](docs/tools.md#create-queue) | Creates a queue after checking for a duplicate name |
| [`search_queues`](docs/tools.md#search-queues) | Searches queues by name |
| [`query_queue_volumes`](docs/tools.md#query-queue-volumes) | Retrieves queue conversation volumes |
| [`sample_conversations_by_queue`](docs/tools.md#sample-conversations-by-queue) | Samples conversations from a queue |
| [`voice_call_quality`](docs/tools.md#voice-call-quality) | Retrieves voice quality metrics |
| [`conversation_sentiment`](docs/tools.md#conversation-sentiment) | Retrieves conversation sentiment |
| [`conversation_topics`](docs/tools.md#conversation-topics) | Retrieves conversation topics |
| [`search_voice_conversations`](docs/tools.md#search-voice-conversations) | Searches voice conversations |
| [`conversation_transcript`](docs/tools.md#conversation-transcript) | Retrieves a conversation transcript |
| [`oauth_clients`](docs/tools.md#oauth-clients) | Lists OAuth clients |
| [`oauth_client_usage`](docs/tools.md#oauth-client-usage) | Retrieves OAuth client usage |
## Local setup
```bash
npm install
npm run build
```
Configure your MCP client to run the local build:
```json
{
"mcpServers": {
"solutif-genesys-cloud": {
"command": "node",
"args": ["/absolute/path/to/genesys-cloud-mcp-server/dist/index.js"],
"env": {
"GENESYSCLOUD_REGION": "<REGION>",
"GENESYSCLOUD_OAUTHCLIENT_ID": "<OAUTH_CLIENT_ID>",
"GENESYSCLOUD_OAUTHCLIENT_SECRET": "<OAUTH_CLIENT_SECRET>"
}
}
}
}
```
The server is read-only by default. To expose `create_queue`, add:
```json
"GENESYSCLOUD_ENABLE_QUEUE_CREATION": "true"
```
The OAuth client then needs `routing:queue:add` and `routing:queue:view`. Keep `create_queue` out of the MCP client's auto-approved tools so every write requires user approval.
## MCP Bundle
```bash
npm run package:mcpb
```
Install the generated `genesys-cloud-mcp-server.mcpb` in Claude Desktop. Queue creation is disabled by default and can be enabled in the extension settings.
## Development
```bash
npm run lint:check
npm run build
npm test -- --run
```
Based on the MIT-licensed [MakingChatbots Genesys Cloud MCP Server](https://github.com/MakingChatbots/genesys-cloud-mcp-server).
TDQS
Scored across 10 tools
Most tools have clearly distinct outputs: transcript, sentiment scores, topics, voice quality, queue volumes, and OAuth usage are separable. A minor overlap exists between conversation_transcript (which can include sentiment annotations) and conversation_sentiment, and between the two conversation-ID discovery tools, but descriptions are enough to resolve this.
The set mixes verb-led names like search_queues and query_queue_volumes with noun-phrase names like conversation_transcript, voice_call_quality, and oauth_clients. The naming is readable and mostly snake_case, but the absent verb pattern prevents strong consistency.
Ten tools is a well-scoped size for a Genesys Cloud server covering conversation analytics, queue interrogation, and OAuth auditing. Each tool has a distinct responsibility and none feel redundant.
Conversation-centric workflows are well covered: discovery, sampling, transcript, sentiment, topics, and call quality are all present. Minor gaps like the lack of non-voice conversation search and OAuth client management actions prevent a perfect score.