// SCAN REPORT

Semantic Model MCP Server

39 tools. 7 can modify or destroy data without limits.

1 destructive tool with no built-in limits. Policy required.

Last updated: 29 Jun 2026

7 can modify or destroy data

32 read-only

39 tools total

Community server · catalogue entry verified 29/06/2026

How to control Semantic Model MCP Server ↓

TOOL MAP

What Semantic Model MCP Server exposes to your agents

Read (32) Write / Execute (6) Destructive / Financial (1)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous Semantic Model MCP Server tools

Destructive · Medium clear_azure_token_cache Clearing the token cache is an irreversible action that removes stored authentication tokens, forcing re-authentication for all subsequent operations. Execute · High execute_dax_query DAX query execution is a code/query execution operation whose effects depend on query arguments. Execute · High execute_local_powerbi_dax DAX query execution is an Execute action—it triggers external operations (queries against Power BI semantic models) whose effects depend on the query arguments. Execute · High query_lakehouse_sql_endpoint The tool name strongly implies executing SQL queries against a lakehouse SQL endpoint.

7 of Semantic Model MCP Server's 39 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Semantic Model MCP Server

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

Deny destructive operations

{
  "clear_azure_token_cache": {
    "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

{
  "generate_directlake_tmsl_template": {
    "limits": [
      {
        "counter": "generate_directlake_tmsl_template_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "analyze_model_bpa": {
    "limits": [
      {
        "counter": "analyze_model_bpa_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 Semantic Model 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 SEMANTIC MODEL →

Instant setup, no code required.

FULL CATALOGUE

All 39 Semantic Model MCP Server tools

DESTRUCTIVE 1 tools

Destructive clear_azure_token_cache Clears the Azure authentication token cache.

EXECUTE 3 tools

Execute execute_dax_query execute_dax_query Execute execute_local_powerbi_dax execute_local_powerbi_dax Execute query_lakehouse_sql_endpoint query_lakehouse_sql_endpoint

WRITE 3 tools

Write generate_directlake_tmsl_template generate_directlake_tmsl_template Write update_local_powerbi_tmsl_definition update_local_powerbi_tmsl_definition Write update_model_using_tmsl update_model_using_tmsl

READ 32 tools

Read analyze_model_bpa analyze_model_bpa Read analyze_tmsl_bpa analyze_tmsl_bpa Read compare_analysis_services_connections compare_analysis_services_connections Read compare_powerbi_detection_methods compare_powerbi_detection_methods Read debug_lakehouse_contents Debug function to check various API endpoints for lakehouse contents including files and items. Read detect_local_powerbi_desktop detect_local_powerbi_desktop Read explore_local_powerbi_columns explore_local_powerbi_columns Read explore_local_powerbi_measures Explore measures in a local Power BI Desktop model. Read explore_local_powerbi_model_structure explore_local_powerbi_model_structure Read explore_local_powerbi_tables Explore tables in a local Power BI Desktop model. Read generate_bpa_report generate_bpa_report Read get_azure_token_status Gets the current status of the Azure token cache. Read get_bpa_categories Get list of available BPA rule categories. Read get_bpa_rules_summary Get summary information about loaded BPA rules. Read get_bpa_violations_by_category get_bpa_violations_by_category Read get_bpa_violations_by_severity get_bpa_violations_by_severity Read get_lakehouse_sql_connection_string Gets the SQL endpoint connection string for a specified Fabric Lakehouse. Read get_learn_microsoft_content Get specific Microsoft Learn content by URL. Read get_learn_microsoft_modules get_learn_microsoft_modules Read get_learn_microsoft_paths Get Microsoft Learn learning paths. Read get_local_powerbi_tmsl_definition get_local_powerbi_tmsl_definition Read get_model_definition get_model_definition Read get_powerbi_workspace_id Gets the workspace ID for a given workspace name. Read get_server_version Get the version information for the Semantic Model MCP Server. Read list_fabric_delta_tables list_fabric_delta_tables Read list_fabric_lakehouses Lists all lakehouses in a specified Fabric workspace. Read list_powerbi_datasets Lists all datasets in a specified Power BI workspace. Read list_powerbi_notebooks Lists all notebooks in a specified Power BI workspace. Read list_powerbi_workspaces Lists available Power BI workspaces for the current user. Read query_local_powerbi_table query_local_powerbi_table Read search_learn_microsoft_content search_learn_microsoft_content Read test_local_powerbi_connection test_local_powerbi_connection

EXPLORE

Related servers

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

FAQ

Questions about Semantic Model MCP Server

Can an AI agent delete data through the Semantic Model MCP Server MCP server? +

Yes. The Semantic Model MCP Server server exposes 1 destructive tools including clear_azure_token_cache. 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 Semantic Model MCP Server? +

The Semantic Model MCP Server server has 3 write tools including generate_directlake_tmsl_template, update_local_powerbi_tmsl_definition, update_model_using_tmsl. 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 Semantic Model MCP Server.

How many tools does the Semantic Model MCP Server MCP server expose? +

39 tools across 4 categories: Destructive, Execute, Read, Write. 32 are read-only. 7 can modify, create, or delete data.

How do I enforce a policy on Semantic Model MCP Server? +

Register the Semantic Model 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 Semantic Model MCP Server tool call.

Deterministic rules across all 39 Semantic Model MCP Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON SEMANTIC MODEL →

Instant setup, no code required.

39 Semantic Model MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.