Edit

Share via

Fabric Pro-Dev MCP Server tools reference

Fabric Pro-Dev MCP Server exposes tools organized into three categories: API documentation & best practices for offline development guidance, OneLake data operations for working with files and tables in OneLake, and Core Fabric operations for creating Fabric items.

Note

Tool names and availability may change between releases. Verify available tools via your AI agent's tool list or the GitHub repository.

API documentation & best practices

These tools provide your AI agent with Fabric API specifications, item schemas, and guidance — all served locally without connecting to live Fabric environments. Use them to generate code, understand API shapes, and follow recommended patterns.

Tool Description
docs_workloads Lists Fabric workload types that have public API specifications available
docs_workload-api-spec Retrieves the complete OpenAPI specification for a specific Fabric workload
docs_platform-api-spec Retrieves the OpenAPI specification for core Fabric platform APIs
docs_item-definitions Retrieves JSON schema definitions for items in a Fabric workload API
docs_best-practices Retrieves best practice documentation and guidance for a specific topic
docs_api-examples Retrieves example API request/response files for a specific workload

Example prompts:

  • "What are the available Fabric workload types I can work with?"
  • "Show me the OpenAPI operations for 'notebook' and give a sample creation body"
  • "Get the platform-level API specifications for Microsoft Fabric"
  • "Create a Lakehouse resource definition with a schema that enforces a string column and a datetime column"
  • "Show me the JSON schema for a Data Pipeline item definition"
  • "Show me best practices for handling API throttling in Fabric"
  • "Get example request/response payloads for creating a Notebook"
  • "What are the pagination patterns for Fabric REST APIs?"

OneLake data operations

These tools connect to your Fabric environment to interact with OneLake storage — listing workspaces and items, managing files and directories, and querying table metadata.

Tool Description
onelake_list_workspaces Lists available Microsoft Fabric workspaces
onelake_list_items Lists workspace items with high-level metadata
onelake_list_items_dfs Lists Fabric items via the DFS endpoint
onelake_list_files Lists files using the hierarchical file-list endpoint
onelake_download_file Downloads a OneLake file
onelake_upload_file Uploads a file to OneLake storage
onelake_delete_file Deletes a file from OneLake storage
onelake_create_directory Creates a directory via the DFS endpoint
onelake_delete_directory Deletes a directory (optionally recursive)
onelake_get_table_config Retrieves table API configuration for a workspace item
onelake_list_table_namespaces Lists table namespaces (schemas) exposed through the table API
onelake_get_table_namespace Retrieves metadata for a specific namespace
onelake_list_tables Lists tables published within a namespace
onelake_get_table Retrieves the definition for a specific table

Important

Unlike the documentation tools above, OneLake tools connect to your live Fabric environment and require authentication.

Core Fabric operations

These tools call Fabric REST APIs to create and manage Fabric items.

Tool Description
core_create-item Creates new Fabric items (Lakehouses, Notebooks, Pipelines, etc.)

Example workflows

These workflows show how to combine tools from different categories:

Explore API specs and generate code

  1. "What Fabric workload types are available?" — uses docs_workloads
  2. "Show me the OpenAPI operations for 'notebook'" — uses docs_workload-api-spec
  3. "Generate a Python script to create a notebook using the Fabric API" — agent uses the spec context

Work with OneLake data

  1. "List my Fabric workspaces" — uses onelake_list_workspaces
  2. "Show me the files in my Sales lakehouse" — uses onelake_list_files
  3. "Download the config.json file" — uses onelake_download_file
  4. "Upload my updated config.json" — uses onelake_upload_file

Scaffold a new Fabric item

  1. "Show me the JSON schema for a Lakehouse item definition" — uses docs_item-definitions
  2. "What are best practices for Lakehouse design?" — uses docs_best-practices
  3. "Create a new Lakehouse called CustomerData in my dev workspace" — uses core_create-item

Troubleshooting

For common issues and solutions, see the Troubleshooting Guide in the GitHub repository.

Related content

  • Last updated on