watsonx Discovery MCP Server for AutoGen 6 tools — connect in under 2 minutes
Microsoft AutoGen enables multi-agent conversations where agents negotiate, delegate, and execute tasks collaboratively. Add watsonx Discovery as an MCP tool provider through the Vinkius and every agent in the group can access live data and take action.
ASK AI ABOUT THIS MCP SERVER
Vinkius supports streamable HTTP and SSE.
import asyncio
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.tools.mcp import McpWorkbench
async def main():
# Your Vinkius token — get it at cloud.vinkius.com
async with McpWorkbench(
server_params={"url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"},
transport="streamable_http",
) as workbench:
tools = await workbench.list_tools()
agent = AssistantAgent(
name="watsonx_discovery_agent",
tools=tools,
system_message=(
"You help users with watsonx Discovery. "
"6 tools available."
),
)
print(f"Agent ready with {len(tools)} tools")
asyncio.run(main())
* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure
About watsonx Discovery MCP Server
Connect your IBM watsonx Discovery account to any AI agent and harness the power of cognitive search and NLP-driven text analytics through natural conversation.
AutoGen enables multi-agent conversations where agents negotiate, delegate, and collaboratively use watsonx Discovery tools. Connect 6 tools through the Vinkius and assign role-based access — a data analyst queries while a reviewer validates, with optional human-in-the-loop approval for sensitive operations.
What you can do
- Cognitive Search — Perform natural language or Discovery Query Language (DQL) queries against your data collections for high-quality semantic search
- Data Discovery — Browse and list all data collections within your project to retrieve collection and document IDs
- Document Analysis — Retrieve comprehensive metadata, ingestion status, and technical details for specific indexed documents
- NLP Enrichments — List and monitor available enrichments (NLP models) like Sentiment, Entities, and Keywords being applied to your data
- Component Health — Verify project-level configurations, ingestion notices, and health settings for all project components
- Semantic Insights — Surface relevant information and hidden patterns from massive unstructured datasets through simple chat commands
The watsonx Discovery MCP Server exposes 6 tools through the Vinkius. Connect it to AutoGen in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.
How to Connect watsonx Discovery to AutoGen via MCP
Follow these steps to integrate the watsonx Discovery MCP Server with AutoGen.
Install AutoGen
Run pip install "autogen-ext[mcp]"
Replace the token
Replace [YOUR_TOKEN_HERE] with your Vinkius token
Integrate into workflow
Use the agent in your AutoGen multi-agent orchestration
Explore tools
The workbench discovers 6 tools from watsonx Discovery automatically
Why Use AutoGen with the watsonx Discovery MCP Server
AutoGen provides unique advantages when paired with watsonx Discovery through the Model Context Protocol.
Multi-agent conversations: multiple AutoGen agents discuss, delegate, and collaboratively use watsonx Discovery tools to solve complex tasks
Role-based architecture lets you assign watsonx Discovery tool access to specific agents — a data analyst queries while a reviewer validates
Human-in-the-loop support: agents can pause for human approval before executing sensitive watsonx Discovery tool calls
Code execution sandbox: AutoGen agents can write and run code that processes watsonx Discovery tool responses in an isolated environment
watsonx Discovery + AutoGen Use Cases
Practical scenarios where AutoGen combined with the watsonx Discovery MCP Server delivers measurable value.
Collaborative analysis: one agent queries watsonx Discovery while another validates results and a third generates the final report
Automated review pipelines: a researcher agent fetches data from watsonx Discovery, a critic agent evaluates quality, and a writer produces the output
Interactive planning: agents negotiate task allocation using watsonx Discovery data to make informed decisions about resource distribution
Code generation with live data: an AutoGen coder agent writes scripts that process watsonx Discovery responses in a sandboxed execution environment
watsonx Discovery MCP Tools for AutoGen (6)
These 6 tools become available when you connect watsonx Discovery to AutoGen via MCP:
get_component_settings
Retrieves the configuration and health settings for project components
get_document_details
Retrieves metadata and status for a specific indexed document
list_available_enrichments
g., Sentiment, Entities) are being applied to documents. Lists all enrichments (NLP models) configured for the project
list_collection_documents
Lists all documents indexed within a specific collection
list_discovery_collections
Lists all data collections within the current watsonx Discovery project
query_discovery_content
Provide a collection ID and the query text. Performs a natural language or DQL query against a discovery collection
Example Prompts for watsonx Discovery in AutoGen
Ready-to-use prompts you can give your AutoGen agent to start working with watsonx Discovery immediately.
"List all my Discovery collections."
"Search the 'Legal Documents' collection for 'contract termination clauses'."
"What enrichments are currently active in my project?"
Troubleshooting watsonx Discovery MCP Server with AutoGen
Common issues when connecting watsonx Discovery to AutoGen through the Vinkius, and how to resolve them.
McpWorkbench not found
pip install "autogen-ext[mcp]"watsonx Discovery + AutoGen FAQ
Common questions about integrating watsonx Discovery MCP Server with AutoGen.
How does AutoGen connect to MCP servers?
Can different agents have different MCP tool access?
Does AutoGen support human approval for tool calls?
Connect watsonx Discovery with your favorite client
Step-by-step setup guides for every MCP-compatible client and framework:
Anthropic's native desktop app for Claude with built-in MCP support.
AI-first code editor with integrated LLM-powered coding assistance.
GitHub Copilot in VS Code with Agent mode and MCP support.
Purpose-built IDE for agentic AI coding workflows.
Autonomous AI coding agent that runs inside VS Code.
Anthropic's agentic CLI for terminal-first development.
Python SDK for building production-grade OpenAI agent workflows.
Google's framework for building production AI agents.
Type-safe agent development for Python with first-class MCP support.
TypeScript toolkit for building AI-powered web applications.
TypeScript-native agent framework for modern web stacks.
Python framework for orchestrating collaborative AI agent crews.
Leading Python framework for composable LLM applications.
Data-aware AI agent framework for structured and unstructured sources.
Microsoft's framework for multi-agent collaborative conversations.
Connect watsonx Discovery to AutoGen
Get your token, paste the configuration, and start using 6 tools in under 2 minutes. No API key management needed.