// SCAN REPORT

Fabric Ontology MCP Server

45 tools. 21 can modify or destroy data without limits.

7 destructive tools with no built-in limits. Policy required.

Last updated: 11 Jun 2026

21 can modify or destroy data

24 read-only

45 tools total

Community server · catalogue entry verified 11/06/2026

How to control Fabric Ontology MCP Server ↓

TOOL MAP

What Fabric Ontology MCP Server exposes to your agents

Read (24) Write / Execute (14) Destructive / Financial (7)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous Fabric Ontology MCP Server tools

Destructive · High delete_ontology This tool irreversibly deletes entire ontology objects, which are foundational metadata structures in Microsoft Fabric. Destructive · High remove_contextualization Removing a contextualization from a relationship type is an irreversible deletion operation that modifies the ontology schema. Destructive · High remove_data_binding Removing a data binding disconnects an entity type from its underlying data source in the ontology. Destructive · High remove_document This tool permanently deletes documents from ontology entity types.

21 of Fabric Ontology MCP Server's 45 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Fabric Ontology MCP Server

PolicyLayer is an MCP gateway — it sits between your AI agents and Fabric Ontology MCP Server, and nothing reaches the server without passing your rules. These are the rules we recommend:

Deny destructive operations

{
  "delete_ontology": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Blocked by default. Requires approval."
      }
    ]
  }
}

Destructive tools should never be available to autonomous agents without human approval.

Rate limit write operations

{
  "add_contextualization": {
    "limits": [
      {
        "counter": "add_contextualization_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "discover_lakehouse_tables": {
    "limits": [
      {
        "counter": "discover_lakehouse_tables_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register Fabric Ontology MCP Server — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON FABRIC ONTOLOGY →

Free to start. No card required.

FULL CATALOGUE

All 45 Fabric Ontology MCP Server tools

DESTRUCTIVE 7 tools

Destructive delete_ontology Delete an ontology. Destructive remove_contextualization Remove a contextualization from a relationship type. Destructive remove_data_binding Remove a data binding from an entity type. Destructive remove_document Remove a document from an entity type by its URL. Destructive remove_entity_type Remove an entity type from an ontology. Destructive remove_property Remove a property from an entity type. Destructive remove_relationship_type Remove a relationship type from an ontology.

WRITE 14 tools

Write add_contextualization add_contextualization Write add_data_binding add_data_binding Write add_document Add a document reference to an entity type. Write add_entity_type add_entity_type Write add_property add_property Write add_relationship_type add_relationship_type Write create_ontology Create a new ontology in a workspace. Write set_overview set_overview Write set_resource_links set_resource_links Write update_entity_type update_entity_type Write update_ontology Update the display name and/or description of an ontology. Write update_ontology_definition_raw update_ontology_definition_raw Write update_property update_property Write update_relationship_type Rename a relationship type.

READ 24 tools

Read discover_lakehouse_tables List all tables in a Lakehouse with their names and formats. Read discover_workspace_data discover_workspace_data Read get_entity_type Get a single entity type by ID, including its data bindings, documents, overviews, and resource links. Read get_kql_database_details Get details of a KQL database including its query URI, database name, and parent Eventhouse. Read get_kql_table_schema get_kql_table_schema Read get_lakehouse_table_schema get_lakehouse_table_schema Read get_ontology Get metadata of a specific ontology. Read get_ontology_definition get_ontology_definition Read get_overview Get the current overview configuration for an entity type. Read get_relationship_type Get a single relationship type by ID, including its contextualizations. Read get_resource_links Get the current resource links for an entity type. Read list_contextualizations List all contextualizations for a relationship type. Read list_data_bindings List all data bindings for an entity type. Read list_documents List all documents attached to an entity type. Read list_entity_types List all entity types in an ontology. Read list_kql_tables List all tables in a KQL database (Eventhouse). Read list_ontologies List all ontologies in a Fabric workspace. Read list_relationship_types List all relationship types in an ontology. Read list_workspace_items list_workspace_items Read list_workspaces List all Fabric workspaces accessible to the current user. Read preview_kql_table preview_kql_table Read preview_lakehouse_table preview_lakehouse_table Read profile_kql_table profile_kql_table Read profile_lakehouse_table profile_lakehouse_table

EXPLORE

Related servers

Other MCP servers with similar tools — same risk classification, starter policies for each.

FAQ

Questions about Fabric Ontology MCP Server

Can an AI agent delete data through the Fabric Ontology MCP Server MCP server? +

Yes. The Fabric Ontology MCP Server server exposes 7 destructive tools including delete_ontology, remove_contextualization, remove_data_binding. These permanently remove resources with no undo. PolicyLayer blocks destructive tools by default so they never reach the upstream server.

How do I prevent bulk modifications through Fabric Ontology MCP Server? +

The Fabric Ontology MCP Server server has 14 write tools including add_contextualization, add_data_binding, add_document. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach Fabric Ontology MCP Server.

How many tools does the Fabric Ontology MCP Server MCP server expose? +

45 tools across 3 categories: Destructive, Read, Write. 24 are read-only. 21 can modify, create, or delete data.

How do I enforce a policy on Fabric Ontology MCP Server? +

Register the Fabric Ontology MCP Server MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every Fabric Ontology MCP Server tool call.

Deterministic rules across all 45 Fabric Ontology MCP Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON FABRIC ONTOLOGY →

Free to start. No card required.

45 Fabric Ontology MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.