- CONFIG
- NLP
- AUDIT
- HUMAN
Short answer
How can I check my pipeline health and NLP settings?
Your AI client pulls component settings and lists all available enrichments directly from watsonx Discovery. You get a clear view of your active NLP layers and project configurations without digging through the console.
Where every issue lands.
Pipeline monitoring outcomes
The AI organizes your discovery data into these specific views.
CONFIG
Component settings
The AI uses get_component_settings to pull specific parameters for your project parts. You see exactly how each piece is configured.
NLP
Active enrichments
The AI runs list_available_enrichments to show you which NLP tools are ready for your data. You can verify which processing steps are active.
AUDIT
Configuration gaps
The AI compares your current settings against your intended setup. You'll find where enrichments might be missing or misconfigured.
HUMAN
Manual adjustments
The AI identifies settings that require your direct intervention. You'll know exactly which parameters you need to change in the watsonx Discovery console.
The workflow
What your AI does when the request arrives.
The AI acts as a bridge between your chat interface and your discovery datasets.
Fetch settings
The AI pulls the specific configuration details for your project components.
get_component_settingsList enrichments
The AI scans your environment to see which NLP enrichment options are available.
list_available_enrichmentsAnalyze status
The AI compares the fetched settings against your questions to find discrepancies.
get_component_settingslist_available_enrichmentsReport findings
The AI presents a summary of your pipeline health and active NLP layers.
get_component_settings
Try it
Copy these to start.
Use these prompts to begin monitoring your pipelines.
Starting points
Swap the bracketed text with your actual project or component names.
watsonx Discovery Connector
You're all set. Choose your MCP client and follow the setup instructions.
https://edge.vinkius.com/vk_preview_MOvCoAeU4n0XLtoAj5AMd7HKRadaRJgAFtxeD6Bh/mcpClaude Desktop
Follow the steps below to connect in seconds.
- 1In Claude Desktop, open Settings → Connectors.
- 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
- 3Click Add and start a new chat — watsonx Discovery capabilities are ready to use.
{
"mcpServers": {
"watsonx-discovery-mcp": {
"url": "https://edge.vinkius.com/vk_preview_MOvCoAeU4n0XLtoAj5AMd7HKRadaRJgAFtxeD6Bh/mcp"
}
}
}Show me the settings for the [component name] component.
Which NLP enrichments are currently available in my discovery instance?
Check the settings for [component name] and tell me if any enrichments are missing.
List all available enrichments for my current dataset.
Claude
ChatGPT
Cursor
VS Code
Windsurf
Claude Code
JetBrains
Cline
Start here
Connect watsonx Discovery once, then ask.
One connection links your AI client to your data. Your credentials stay encrypted, and you can find the full setup guide on the Connector page.
Connect watsonx Discovery to your AIFAQ
How this task behaves
- 01
Can the AI change my component settings?
No. The AI can only read settings using get_component_settings. You must make any changes manually in watsonx Discovery.
- 02
Can the AI add new NLP enrichments?
No. The AI can only list what is available. It cannot trigger the creation or activation of new enrichments.
- 03
Does the AI see my raw data?
The AI only accesses the specific component settings and enrichment lists requested through the tools.
- 04
Can I use this to troubleshoot pipeline failures?
Yes, by checking if the correct enrichments are active and if the component settings match your requirements.
- 05
How often does the AI refresh the component settings?
The AI fetches fresh data from watsonx Discovery every time you ask a question using the tools.
More questions about watsonx Discovery? The Connector page answers them. See everything the watsonx Discovery Connector can do
Connect watsonx Discovery to Claude, Cursor, ChatGPT & more
