For AI agents: a documentation index is available at the root level at /llms.txt and /llms-full.txt. Append /llms.txt to any URL for a page-level index, or .md for the markdown version of any page.
  • Getting Started
    • Welcome
    • Contributing
  • Concepts
    • Columns
    • Seed Datasets
    • Agent Rollout Ingestion
    • Custom Columns
    • Validators
    • Processors
    • Person Sampling
    • Traces
      • Overview
      • MCP Providers
      • Tool Configs
      • Enabling Tools
      • CLI Configuration
      • Safety & Limits
    • Architecture & Performance
    • Deployment Options
    • Security
  • Tutorials
    • Overview
    • The Basics
    • Structured Outputs, Jinja Expressions, and Conditional Generation
    • Seeding with an External Dataset
    • Providing Images as Context
    • Generating Images
    • Image-to-Image Editing
  • Recipes
    • Recipe Cards
  • Plugins
    • Overview
    • Example Plugin
    • FileSystemSeedReader Plugins
    • Discover
  • Code Reference
    • Overview
  • Dev Notes
    • Overview
    • Push Datasets to Hugging Face Hub
    • Text-to-SQL for Nemotron Super
    • Async All the Way Down
    • Owning the Model Stack
    • Data Designer Got Skills
NVIDIANVIDIA
Developer-friendly docs for your API
Privacy Policy | Manage My Privacy | Do Not Sell or Share My Data | Terms of Service | Accessibility | Corporate Policies | Product Security | Contact

Copyright © 2026, NVIDIA Corporation.

LogoLogoNeMo Data Designer
On this page
  • Quick Start
  • Guides
  • Example
  • Code Reference
ConceptsTool Use & MCP

Tool Use & MCP

||View as Markdown|
Previous

Message Traces

Next

MCP Providers

Tool use lets LLM columns call external tools during generation (e.g., lookups, calculations, retrieval, domain services). Data Designer supports tool use via the Model Context Protocol (MCP), which standardizes how tools are discovered and invoked.

Quick Start

  1. Configure an MCP provider (Local or Remote)
  2. Create a ToolConfig referencing your provider
  3. Add tool_alias to your LLM column
1import data_designer.config as dd
2from data_designer.interface import DataDesigner
3
4# 1. Configure provider
5
6## Local Stdio provider
7mcp_provider = dd.LocalStdioMCPProvider(
8 name="demo-mcp",
9 command="python",
10 args=["-m", "my_mcp_server"],
11)
12
13## Remote provider
14# mcp_provider = dd.MCPProvider(
15# name="remote-mcp",
16# endpoint="https://mcp.example.invalid/sse",
17# api_key="REMOTE_MCP_API_KEY",
18# )
19
20data_designer = DataDesigner(mcp_providers=[mcp_provider])
21
22# 2. Create tool config
23tool_config = dd.ToolConfig(
24 tool_alias="my-tools",
25 providers=["demo-mcp"],
26)
27
28builder = dd.DataDesignerConfigBuilder(tool_configs=[tool_config])
29
30# 3. Use tools in column
31builder.add_column(
32 dd.LLMTextColumnConfig(
33 name="answer",
34 prompt="Use tools to answer: {{ question }}",
35 model_alias="nvidia-text",
36 tool_alias="my-tools",
37 )
38)

Guides

GuideDescription
MCP ProvidersConfigure local subprocess or remote SSE providers
Tool ConfigurationsDefine tool permissions and limits
Enabling Tools on ColumnsUse tools in LLM generation
Configure via CLIInteractive CLI configuration
Message TracesCapture full conversation history
Safety & LimitsAllowlists, budgets, timeouts

Example

See the PDF Q&A Recipe for a complete working example.

Code Reference

For internal architecture and API documentation, see MCP Code Reference.