Fabric MCP server

Connect Fabric to Claude, ChatGPT, Cursor, Claude Code, Codex, Gemini, GitHub Copilot and any other MCP client, for your whole team. Metorial adds security, governance, and tracing, and gives everyone one Magic MCP URL to connect.

What you can do with the Fabric MCP server

Ask your agent in plain language. Each of these maps to a real tool on the server.

  • Use the docs workload api spec tool in Fabric
  • Use the docs platform api spec tool in Fabric
  • Use the docs workloads tool in Fabric
  • Use the one lake download file tool in Fabric
  • Use the one lake list tables tool in Fabric
  • Use the data factory create dataflow tool in Fabric

Supported Tools

docs_workload_api_spec

Docs Workload API Spec

Official upstream MCP name: docs_workload-api-spec. Return compact API-spec metadata for a Fabric workload as a downloadable file.

docs_platform_api_spec

Docs Platform API Spec

Official upstream MCP name: docs_platform-api-spec. Return compact Fabric platform API metadata, scopes, pagination, and LRO conventions as a downloadable file.

docs_workloads

Docs Workloads

Official upstream MCP name: docs_workloads. List Microsoft Fabric workloads known to the docs resource index and prepare the compact resource for download.

onelake_download_file

OneLake Download File

Official upstream MCP name: onelake_download_file. Download a OneLake file and prepare a downloadable file.

onelake_list_tables

OneLake List Tables

Official upstream MCP name: onelake_list_tables. List Iceberg tables in a OneLake namespace.

datafactory_create_dataflow

Data Factory Create Dataflow

Official upstream MCP name: datafactory_create-dataflow. Create a Dataflow in a Fabric workspace.

onelake_get_table

OneLake Get Table

Official upstream MCP name: onelake_get_table. Get metadata for a OneLake Iceberg table.

onelake_list_items

OneLake List Items

Official upstream MCP name: onelake_list_items. List OneLake items for a Fabric workspace using the OneLake API endpoint.

onelake_list_files

OneLake List Files

Official upstream MCP name: onelake_list_files. List files under a Fabric item through the OneLake DFS-compatible endpoint.

onelake_delete_file

OneLake Delete File

Official upstream MCP name: onelake_delete_file. Delete a file from OneLake.

onelake_list_table_namespaces

OneLake List Table Namespaces

Official upstream MCP name: onelake_list_table_namespaces. List Iceberg table namespaces for a Fabric item.

datafactory_get_pipeline

Data Factory Get Pipeline

Official upstream MCP name: datafactory_get-pipeline. Get a Data Pipeline by ID from a Fabric workspace.

core_create_item

Core Create Item

Official upstream MCP name: core_create-item. Create a Microsoft Fabric item in a workspace using Fabric REST.

datafactory_list_pipelines

Data Factory List Pipelines

Official upstream MCP name: datafactory_list-pipelines. List Data Pipelines in a Fabric workspace.

onelake_create_directory

OneLake Create Directory

Official upstream MCP name: onelake_create_directory. Create a directory in OneLake.

docs_item_definitions

Docs Item Definitions

Official upstream MCP name: docs_item-definitions. Return Fabric item definition shape and item-type notes as a downloadable file.

onelake_get_table_namespace

OneLake Get Table Namespace

Official upstream MCP name: onelake_get_table_namespace. Get metadata for a OneLake Iceberg table namespace.

onelake_get_table_config

OneLake Get Table Config

Official upstream MCP name: onelake_get_table_config. Get OneLake Iceberg table REST catalog configuration for a Fabric item.

docs_best_practices

Docs Best Practices

Official upstream MCP name: docs_best-practices. Return compact Microsoft Fabric implementation best practices as a downloadable file.

datafactory_list_dataflows

Data Factory List Dataflows

Official upstream MCP name: datafactory_list-dataflows. List Dataflows in a Fabric workspace.

datafactory_execute_query

Data Factory Execute Query

Official upstream MCP name: datafactory_execute-query. Execute a Dataflow query and prepare downloadable Arrow stream results when Fabric returns query data.

onelake_delete_directory

OneLake Delete Directory

Official upstream MCP name: onelake_delete_directory. Delete a directory from OneLake.

docs_api_examples

Docs API Examples

Official upstream MCP name: docs_api-examples. Return compact Fabric API examples and source links as a downloadable file.

datafactory_create_pipeline

Data Factory Create Pipeline

Official upstream MCP name: datafactory_create-pipeline. Create a Data Pipeline in a Fabric workspace.

onelake_list_workspaces

OneLake List Workspaces

Official upstream MCP name: onelake_list_workspaces. List OneLake workspaces visible to the connected Microsoft Fabric user.

onelake_list_items_dfs

OneLake List Items DFS

Official upstream MCP name: onelake_list_items_dfs. List workspace paths through the OneLake DFS-compatible endpoint.

datafactory_run_pipeline

Data Factory Run Pipeline

Official upstream MCP name: datafactory_run-pipeline. Start an on-demand Data Pipeline job in Fabric.

onelake_upload_file

OneLake Upload File

Official upstream MCP name: onelake_upload_file. Upload inline text or base64 content into a OneLake file.

core_list_workspaces

Core List Workspaces

Discover accessible Fabric workspaces and their IDs using the Fabric REST API.

core_cancel_item_job

Core Cancel Item Job

Request cancellation of a running Fabric item job. Use core_get_item_job to confirm its eventual state; discover workspace and item IDs with core_list_workspaces and core_list_items.

core_list_items

Core List Items

Discover Fabric items in a workspace. Call core_list_workspaces first to select a workspace.

core_get_item_job

Core Get Item Job

Check an item job started by datafactory_run_pipeline. Respect Retry-After before polling; discover workspace and item IDs with core_list_workspaces and core_list_items.

core_delete_item

Core Delete Item

Delete a Fabric item. Discover IDs with core_list_workspaces and core_list_items. Fabric uses soft deletion for supported item types unless hardDelete is true.

core_update_item

Core Update Item

Update a Fabric item display name or description. Discover IDs with core_list_workspaces and core_list_items.

core_get_item

Core Get Item

Read a Fabric item. Discover workspace and item IDs with core_list_workspaces and core_list_items.

core_get_operation_state

Core Get Operation State

Check a Fabric long-running operation using the x-ms-operation-id returned by creation or query execution. Respect Retry-After before polling.

Connect Fabric to your AI client

Every client uses the same Magic MCP URL, and so does any other MCP client. Add it once and sign in with SSO.

  1. Enable Fabric in Metorial. In your Metorial portal, enable the Fabric MCP server and sign in with the account that owns the data. Access stays governed by your team policies.
  2. Add a custom connector. Open Customize, then Connectors. Select Add, then Custom, then Web.
  3. Paste your Metorial MCP URL. Name it Metorial, paste your Magic MCP URL (<your-magic-mcp-url>) and continue.
  4. Sign in. Select Add and sign in to load Fabric tools.

Run Fabric through the Metorial gateway

One governed layer for every app your agents reach, not a separate connector per tool.

  • Give Fabric and every other app to your whole team through one MCP gateway, behind your SSO.
  • Scope which teams and agents can use Fabric tools with role-based access control, and trace every call.
  • Prefer to run it yourself? Metorial is open source and self-hostable.

More integrations teams use with Fabric

Google Sheets

Create, read, and update spreadsheets and their cell data. Read and write values to individual cells, ranges, or multiple ranges using A1 notation or named ranges. Apply cell formatting including text styles, backgrounds, borders, number formats, and conditional formatting. Manage sheets (tabs) within a spreadsheet—add, delete, copy, rename, and reorder them. Create and manage embedded charts, pivot tables, filter views, data validation rules, protected ranges, named ranges, and merged cells. Perform batch operations to apply multiple updates atomically.

GitHub

Manage repositories, issues, and pull requests. Create and configure branches, star repositories, review code, and merge changes. Automate CI/CD workflows with GitHub Actions, manage workflow runs, secrets, and artifacts. Track issues with labels, milestones, and assignees. Search across code, repositories, issues, and users. Manage organizations, teams, and memberships. Create and manage projects, gists, packages, deployments, and environments. Access security alerts including code scanning, secret scanning, and Dependabot alerts. Read and write file contents in repositories. Manage webhooks, notifications, and codespaces.

Salesforce

Manage CRM data including Accounts, Contacts, Leads, Opportunities, Cases, and custom objects. Create, read, update, and delete records. Query data using SOQL and search across objects using SOSL. Perform bulk data operations for large-scale imports, exports, and migrations. Execute composite requests to batch multiple operations in a single API call. Access analytics, reports, and dashboards. Manage files and attachments associated with records. Interact with Chatter feeds, posts, and groups for social collaboration. Manage org metadata including custom objects, fields, layouts, and workflows. Query data using GraphQL for precise data retrieval across related objects.

Sharepoint

Manage SharePoint sites, document libraries, lists, and files. Create, read, update, and delete lists and list items with custom columns. Resolve site users to numeric Person/Group LookupId values. Upload, download, move, copy, and version files in document libraries. Search across sites, files, folders, lists, and list items using Microsoft Search. Manage permissions at site, list, and item levels with granular access control. Define and manage content types and site columns. Retrieve site properties and search for sites across Microsoft 365.

Airtable

Create, read, update, and delete records in Airtable bases and tables. Manage base schemas including creating tables and fields. Filter records using formulas, sort by fields, and scope queries to specific views. Upsert records to find, create, or update in a single call. Upload attachments to records, read and write record comments, list accessible bases, and receive real-time base change events through webhooks.

Google Drive

Upload, download, create, copy, move, rename, trash, and permanently delete files and folders in Google Drive. Search for files using complex queries filtering by name, MIME type, owner, modification date, labels, and other metadata. Share files and folders with specific users, groups, or domains with role-based permissions (owner, writer, commenter, reader). Manage shared drives and their members. Export Google Workspace files (Docs, Sheets, Slides) to standard formats like PDF, DOCX, and XLSX. Track file revision history and restore earlier versions. Create, read, update, and delete threaded comments and replies on files. Read label definitions and search files by label. Browse the Drive apps installed for your account. Store app-specific data in a hidden per-user folder.

Technical notes for Fabric

Use Microsoft Fabric REST, OneLake data-plane APIs, and Fabric documentation resources to inspect workspaces and items, move files through OneLake, create Fabric items, and manage Data Factory pipelines and dataflows.

Frequently asked questions

Common questions about connecting Fabric to AI agents with Metorial.

  1. How many tools does the Fabric MCP server have?
    The Fabric MCP server exposes 36 tools, including Docs Workload API Spec, Docs Platform API Spec, Docs Workloads. Each one is governed and traced through Metorial.
  2. Fabric exposes tools your agents call on demand; it does not publish event triggers yet. Everything still runs through one governed MCP URL.
  3. Any MCP client, including VS Code, Windsurf, Zed, OpenCode and Grok. Each one reaches the Fabric MCP server through the same Metorial URL.
  4. Use role-based access control to decide which teams, users, and agents can use Fabric and which of its tools they can call.
  5. Yes. Metorial is open source, so you can run the Fabric MCP server yourself or use the hosted gateway.

Connect Fabric to production AI agents

See how Metorial gives your team governed access to Fabric, with tracing and security controls built in.