MCP server overview¶
The Model Context Protocol (MCP) is an open standard that lets AI agents, large language models (LLMs), and coding assistants discover and interact with external tools, data sources, and services through a consistent interface. Instead of embedding tool logic inside every agent or client, you deploy an MCP server that hosts tools centrally. Clients connect to that server at runtime to list and invoke tools without custom integration code per client.
DataRobot provides several MCP server options—from a managed platform service to templates you deploy yourself—so you can expose DataRobot capabilities and custom logic to agentic workflows, IDEs, and chat clients.
How MCP works¶
MCP uses a client-server model:
- The client—the reasoning engine or assistant that plans tasks. Examples include a LangGraph agent in the DataRobot Agentic Starter template, or an IDE assistant in Cursor, Claude Desktop, or VS Code.
- The MCP server—a web service that hosts tool logic, resources, and prompts. The server executes tasks such as calling the DataRobot API, running predictions, or querying external systems.
- The protocol—a standard interface for discovery and invocation. Clients ask the server which tools are available and send structured requests to run them.
flowchart LR
Client["MCP client<br/>(agent, IDE, chat app)"]
Server["MCP server<br/>(tools, resources, prompts)"]
DR["DataRobot platform<br/>and external APIs"]
Client <-->|"MCP protocol"| Server
Server --> DR
Why use an MCP server?¶
Using an MCP server to provide tools offers several advantages over embedding tools directly in agent code or deploying each tool separately:
- Centralized tool management—define and host tools in one place that multiple agents or clients can share.
- Standardized interface—tools follow the MCP protocol, so they work across MCP-compatible frameworks and clients.
- Dynamic discovery—clients list available tools at runtime; you can add or change tools on the server without redeploying every client.
- Separation of concerns—scale and update the tool server independently from your agents and applications.
For tool integration patterns inside agentic workflows, see Integrate tools using an MCP server. For connecting IDEs and chat clients, see Connect agentic coding environments to MCP servers.
DataRobot MCP server types¶
DataRobot supports two main MCP server options. The right choice depends on whether you need a managed platform endpoint or a fully customizable server. Agents built with the Agentic Starter template can connect to either; see Connect Agentic Starter agents.
| Option | Deployment | Best for |
|---|---|---|
| DataRobot Global MCP | Automatically available on your DataRobot instance. | Quick access to platform tools without deploying your own server. |
| Standalone MCP server | Local development or DataRobot deployment via the MCP template. | Full control, custom tools, integrations, and dynamic tool registration. |
DataRobot Global MCP¶
The DataRobot Global MCP is a persistently deployed MCP server that DataRobot automatically provisions on your instance. Agentic workflows and MCP clients can connect to it using a fixed platform endpoint without deploying a separate MCP application.
Endpoint:
https://{DATAROBOT_URL}/api/v2/genai/globalmcp/mcp
Key characteristics:
- Managed service—no separate MCP deployment to create or maintain.
- Platform-native access—connect from agentic workflows or coding environments using your DataRobot API key.
- Predictive AI tools (initial release)—the Global MCP currently exposes DataRobot predictive AI tools; additional tool categories are planned for future releases.
Global MCP tool availability
The DataRobot Global MCP currently supports tools for predictive AI. This limitation will be removed in a future release.
Authentication: Requests require a DataRobot API key passed as a Bearer token. Obtain your key from the user menu under API keys and tools. See API key management.
When to use it:
- You want immediate access to DataRobot predictive tools from Cursor, Claude Desktop, VS Code, or an agentic workflow.
- You do not need custom tools, third-party integrations, or deployment-specific configuration.
- Your environment provides the Global MCP endpoint (available in recent DataRobot releases).
For client configuration examples, see Using the DataRobot Global MCP.
Standalone MCP server¶
The DataRobot MCP template (datarobot-mcp-template) is an App Framework template that deploys a FastMCP-based MCP server as a DataRobot custom model application. You can run it locally for development or deploy it to DataRobot for production.
Endpoints:
| Environment | URL |
|---|---|
| Local (default) | http://localhost:8080/mcp |
| DataRobot deployment | https://{DATAROBOT_URL}/api/v2/deployments/{DEPLOYMENT_ID}/directAccess/mcp |
Key characteristics:
- Comprehensive built-in tools—pre-built tools for DataRobot platform operations, third-party integrations, and web search.
- Dynamic tool registration—automatically expose tagged DataRobot deployments as MCP tools.
- Custom tool authoring—add domain-specific tools using FastMCP decorators and Python type hints.
- Repeatable instances—apply the component multiple times in one project under different names for separate MCP backends.
- OpenTelemetry tracing—optional observability for tool calls in production.
Built-in tool categories include:
- DataRobot platform—catalog and datasets, modeling and projects, deployments, batch and real-time predictions, vector databases, use cases, and documentation lookup.
- Data connectors—Confluence, Jira, Google Drive, and Microsoft 365 (OAuth configuration required).
- Web search—Perplexity and Tavily (API keys required).
Supported built-in MCP tools¶
The standalone DataRobot MCP template currently supports the following built-in tools.
Tool inventory source
This list is based on the current datarobot-mcp-template codebase. Tool availability can vary by feature flags and credentials (OAuth providers, Perplexity/Tavily API keys, and DataRobot API access).
DataRobot - Catalog (datasets and datastores):
catalog_upload_dataset,catalog_list_datasets,catalog_get_preview,catalog_list_datastores,catalog_browse_datastorecatalog_query_datastore,catalog_check_timeseries_eligibility,catalog_analyze_dataset,catalog_suggest_ml_problems,catalog_get_eda_insights
DataRobot - Modeling (projects and models):
models_get_bestmodel,modeling_score_dataset,modeling_list_models,modeling_get_modeldetails,modeling_list_projectsmodeling_get_project_dataset,modeling_start_autopilot,modeling_get_model_roc,modeling_get_model_feature_impact,modeling_get_model_lift_chart
DataRobot - Deployments:
deployment_get_list,deployment_get_model_info,deployment_create_deployment,deployment_get_prediction_history,deployment_get_infodeployment_generate_prediction_sample,deployment_validate_prediction_data,deployment_get_features
DataRobot - Predictions:
predict_batch_predictions_from_dataset,predict_batch_predictions_from_partition,predict_get_batch_job_statuspredict_get_batch_results,predict_score_catalog_realtime,predict_score_inline_realtime
DataRobot - Vector databases, use cases, and docs:
vdb_list,vdb_query,datarobot_usecases_list,usecases_list_assets,datarobot_docs_fetch_page
Data connectors - Confluence:
confluence_get_page,confluence_create_page,confluence_add_comment,confluence_search_space,confluence_update_page
Data connectors - Jira:
jira_search_issues,jira_get_issue,jira_create_issue,jira_update_issue,jira_transition_issue
Data connectors - Google Drive:
gdrive_find_contents,gdrive_read_and_export_content,gdrive_create_file,gdrive_update_metadata,gdrive_manage_access
Data connectors - Microsoft 365:
microsoft_graph_search_content,microsoft_graph_share_item,microsoft_graph_create_file,microsoft_graph_update_metadata
Web search tools:
perplexity_search,perplexity_sonar,tavily_search_web,tavily_extract_text,tavily_list_links,tavily_crawl_site
When to use it:
EXTERNAL_MCP_URL(withEXTERNAL_MCP_HEADERS) for the Global MCP or any other MCP endpoint.MCP_DEPLOYMENT_IDorMCP_WORKLOAD_IDfor a standalone MCP server deployed in DataRobot.- You need custom tools, integration with collaboration platforms, or full control over the tool surface.
- Multiple agents or MCP clients should share one tool backend.
- You want to turn DataRobot deployments into tools automatically via dynamic tool registration.
For deployment and development, see the MCP Server application template and the MCP template repository.
Connect Agentic Starter agents¶
The DataRobot Agentic Starter template doesn’t include an MCP server. Instead, the agent acts as an MCP client. At runtime, mcp_tools_context connects to the MCP server set in the project’s .env file and passes its tools to the LangGraph workflow. This happens in custompy_adaptor for DRUM and in register.py for DRAgent.
In .env, set the variable that matches where your MCP server runs:
- EXTERNAL_MCP_URL (with EXTERNAL_MCP_HEADERS) for the Global MCP or any other MCP endpoint.
- MCP_DEPLOYMENT_ID or MCP_WORKLOAD_ID for a standalone MCP server deployed in DataRobot.
- MCP_SERVER_PORT for an MCP server running on your machine.
If none of these are set, the agent runs without MCP tools. For precedence rules and examples, see Configure MCP server connection.
Apps created from earlier template versions
Earlier versions of the Agentic Starter template included an MCP server in mcp_server/, served locally on port 9000. Updating to a current version removes that server. To keep its tools, move them to the Global MCP or a standalone MCP server, as described in MCP migration guide.
Endpoint reference¶
Use the following patterns when configuring agents or MCP clients. Always use the exact URL from your deployment output when available.
| MCP server type | Context | Base URL |
|---|---|---|
| Global MCP | Platform | https://{DATAROBOT_URL}/api/v2/genai/globalmcp/mcp |
| Standalone MCP template | Local | http://localhost:8080/mcp |
| Standalone MCP template | Deployed | https://{DATAROBOT_URL}/api/v2/deployments/{DEPLOYMENT_ID}/directAccess/mcp |
Finding deployed endpoints
For the MCP template, run task infra:info or check deployment output for MCP_SERVER_MCP_ENDPOINT.
Authentication¶
Remote MCP connections to DataRobot typically require:
Authorization: Bearer <DATAROBOT_API_TOKEN>—DataRobot API key for authentication.x-datarobot-api-token: <DATAROBOT_API_TOKEN>—Required for tool execution on many standalone MCP server deployments.
The Global MCP generally requires the Bearer token only. See Connect agentic coding environments to MCP servers for per-client configuration examples.
Choose an MCP server¶
Use this guidance to select the right option:
- Start with the Global MCP if you need quick access to DataRobot predictive tools from an IDE or agent and your instance provides the endpoint.
- Use the standalone MCP template if you need custom tools, third-party integrations (Jira, Confluence, Google Drive, Microsoft 365), web search, dynamic deployment registration, or a dedicated tool server shared across multiple applications.
An Agentic Starter agent connects to one MCP server at a time, allowing you to use different servers per environment. For example, set a standalone MCP server running locally (MCP_SERVER_PORT) during development and a deployed standalone server or the Global MCP for the deployed agent.
MCP vs. direct tool integration¶
DataRobot also supports integrating tools directly into agents without an MCP server (for example, via ToolClient and direct tool deployments). MCP is preferable when you want centralized tool management, protocol-standard compatibility, and runtime tool discovery.
| Consideration | MCP server | Direct tool deployment |
|---|---|---|
| Tool management | Centralized in one server. | Each tool deployed separately. |
| Protocol | MCP standard. | DataRobot-specific. |
| Tool discovery | Automatic at runtime. | Manual per tool. |
| Dynamic updates | Update server without redeploying agents. | Often requires agent redeployment. |
| Client compatibility | Any MCP-compatible client. | DataRobot agent framework. |
For direct tool integration, see Add tools to agents.
Next steps¶
| Topic | Description |
|---|---|
| Integrate tools using an MCP server | Connect MCP tools to LangGraph and other agentic workflows. |
| Connect agentic coding environments to MCP servers | Configure Cursor, Claude Desktop, and VS Code for Global MCP and standalone servers. |
| MCP Server application template | Overview of the standalone MCP template and key features. |
| DataRobot MCP template repository | Source, component setup, and in-repo developer documentation. |
| DataRobot Agentic Starter template | Full agentic application that connects to MCP servers as a client. |
| Model Context Protocol | Official MCP specification. |