AdxCAUTION
A Model Context Protocol (MCP) server that enables AI assistants to query and analyze Azure Data Explorer databases through standardized interfaces.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
[](https://github.com/pab1it0/adx-mcp-server/actions/workflows/ci.yml) [](https://codecov.io/gh/pab1it0/adx-mcp-server) [](https://opensource.org/licenses/MIT) [](https://www.python.org/downloads/)
A [Model Context Protocol][mcp] (MCP) server that enables AI assistants to execute KQL queries and explore Azure Data Explorer (ADX/Kusto) databases through standardized interfaces.
This server provides seamless access to Azure Data Explorer and Eventhouse (in Microsoft Fabric) clusters, allowing AI assistants to query and analyze your data using the powerful Kusto Query Language.
[mcp]: https://modelcontextprotocol.io
Features
Query Execution
- Execute KQL queries - Run arbitrary KQL queries against your ADX database
- Structured results - Get results formatted as JSON for easy consumption
Database Discovery
- List tables - Discover all tables in your database
- View schemas - Inspect table schemas and column types
- Sample data - Preview table contents with configurable sample sizes
- Table statistics - Get detailed metadata including row counts and storage size
Authentication
- DefaultAzureCredential - Supports Azure CLI, Managed Identity, and more
- Workload Identity - Native support for AKS workload identity
- Flexible credentials - Works with multiple Azure authentication methods
Deployment Options
- Multiple transports - stdio (default), HTTP, and Server-Sent Events (SSE)
- Docker support - Production-ready container images wi
54b43c805543OBSERVED · 2026-10-08Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add adx_mcp_server --env ADX_TOKEN_FILE_PATH=${ADX_TOKEN_FILE_PATH} -- uvx adx_mcp_server{
"mcpServers": {
"adx_mcp_server": {
"command": "uvx",
"args": [
"adx_mcp_server"
],
"env": {
"ADX_TOKEN_FILE_PATH": "${ADX_TOKEN_FILE_PATH}"
}
}
}
}Exposed tools (3)
3 read · 0 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
get_table_details | read | Get detailed statistics and metadata for a table. |
get_table_schema | read | Get schema information for a specific table. |
list_tables | read | List all tables in the configured ADX database. |
Trust audit
CAUTIONgrade B · trust 89/100 Install with care. The audit found things worth knowing before you trust its output.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | FAIL |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (1 observation(s))
- Network
- declared (3 observation(s))
- Shell
- none-observed
- Dependencies
- pinned
- Secrets in source
- none-found
Findings (3)
* Added DevContainer Feature for seamless development experience (PR #34, @caol-ila @cmbrose)
.env.template
curl -LsSf https://astral.sh/uv/install.sh | sh
Gates applied: no_behavioural_pass.
54b43c805543full audit observations/trust-audit/mcp-server/pab1it0__adx.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-08 | 54b43c805543 | CAUTION | B | 89 | first audit |
Questions
What is the Adx MCP server?
A Model Context Protocol (MCP) server that enables AI assistants to query and analyze Azure Data Explorer databases through standardized interfaces.
What tools does Adx expose?
3 in total: 3 read-only, 0 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is Adx safe to connect to an agent?
With care. The audit graded it B (89/100) and found 3 things worth knowing before you trust this server, listed below with the exact line each was found on.
What credentials does Adx need?
It reads ADX_TOKEN_FILE_PATH from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How does Adx run?
It speaks stdio, so it runs as a local process your client starts. It is published on PyPI as adx_mcp_server.
How current is this page?
The grade is for one exact copy of the source (54b43c805543), read on 2026-10-08. The repository is watched and re-audited when it changes.