mcpField
M
Mcp Server Kusto

Mcp Server Kusto

Local
github.com/ZZZHDWDatabases1Updated 98w ago

About Mcp Server Kusto

Mcp Server Kusto is an MCP server for accessing Azure Data Explorer clusters. It lets MCP clients inspect tables and schemas, and run queries against internal and external tables or materialized views.

Key features

  1. 01List internal and external tables
  2. 02List materialized views
  3. 03Query internal tables and materialized views
  4. 04Query external tables
  5. 05Retrieve table schemas

Use cases

  1. 01Inspect available Azure Data Explorer tables
  2. 02Run queries against cluster data
  3. 03Check schemas before querying

MCP support

Exposes Azure Data Explorer table listing, schema retrieval, and query execution tools to MCP clients.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

No install method listed yet

We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.

Repository

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

Kusto MCP Server

A mcp server that provides access to Azure Data Explorer (ADX) clusters.

Tools

The following tools are provided by the server:

  • list tables:
    • list_internal_tables:list all internal tables in the cluster
    • list_external_tables:list all external tables in the cluster
    • list_materialized_views:list all materialized views in the cluster
  • execute query:
    • execute_query_internal_table:execute a query on an internal table or materialized view
    • execute_query_external_table:execute a query on an external table
  • get table schema:
    • get_internal_table_schema:get the schema of an internal table or materialized view
    • get_external_table_schema:get the schema of an external table
Claude Desktop configuration

Edit claude_desktop_config.json to add the following configuration:

{
  "mcpServers": {
    "kusto": {
      "command": "uv",
      "args": [
        "--directory",
        "{{PATH_TO_PROJECT}}\\mcp-server-kusto\\src\\mcp_server_kusto",
        "run",
        "mcp-server-kusto",
        "--cluster",
        "{{ADX_CLUSTER_URL}}",
        "--authority_id",
        "{{TENANT_ID}}",
        "--client_id",
        "{{CLIENT_ID}}",
        "--client_secret",
        "{{CLIENT_SECRET}}"
      ]
    }
  }
}

When using azure data explorer emulator locally, provide the cluster url like https://localhost:8082 and not need to provide --authority_id, --client_id, --client_secret.

{
  "mcpServers": {
    "kusto": {
      "command": "uv",
      "args": [
        "--directory",
        "{{PATH_TO_PROJECT}}\\mcp-server-kusto\\src\\mcp_server_kusto",
        "run",
        "mcp-server-kusto",
        "--cluster",
        "{{ADX_CLUSTER_URL}}"
      ]
    }
  }
}

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.