Azure Data Explorer MCP Server: KQL Injection in multiple tools allows MCP client to execute arbitrary Kusto queries

Exploitation

No confirmed exploitation recorded. Patch Next marks exploitation only from CISA KEV.

CVSS

8.3 · CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:L

EPSS

• CVE-2026-33980: 0.40% estimated exploitation activity in the next 30 days; percentile 34.62 (FIRST EPSS, 2026-11-03). This is a model estimate, not proof of exploitation or customer exposure.

As published by the source; long descriptions are shortened.

Summary adx-mcp-server (<= latest, commit 48b2933) contains KQL (Kusto Query Language) injection vulnerabilities in three MCP tool handlers: gettableschema, sampletabledata, and gettabledetails. The tablename parameter is interpolated directly into KQL queries via f-strings without any validation or sanitization, allowing an attacker (or a prompt-injected AI agent) to execute arbitrary KQL queries against the Azure Data Explorer cluster. Details The MCP tools construct KQL queries by directly embedding the tablename parameter into query strings: Vulnerable code (permalink): KQL allows chaining query operators with | and executing management commands prefixed with .. An attacker can inject: - sensitivetable | project Secret, Password | take 100 // to read arbitrary tables - Newline-separated management commands like .drop table importantdata via gettabledetails - Arbitrary KQL analytics queries via any of the three tools Note: While the server also has an executequery tool that…

Published by the source

27 Mar 2026, 19:08 UTC

Last modified by the source

13 Jul 2026, 16:43 UTC

Source last checked

26 Oct 2026, 13:40 UTC

1. Revision 2 · amended · 26 Oct 2026

   Amended from ghsa record GHSA-vphc-468g-8rfp

2. Revision 1 · created · 24 Oct 2026

   Published from osv record GHSA-vphc-468g-8rfp

Preview the exact text before you copy it. Commands are read-only suggestions; review them before running anything.

# Patch Next advisory brief: CVE-2026-33980

Advisory: Azure Data Explorer MCP Server: KQL Injection in multiple tools allows MCP client to execute arbitrary Kusto queries
IDs: CVE-2026-33980, GHSA-vphc-468g-8rfp
Record: https://patchnext.com/advisories/cve-2026-33980 (revision 2, source checked 26 Oct 2026, 13:40 UTC)
Inventory: none attached. This brief comes from a public page and does not say whether any deployment is affected.
Severity: High (CVSS 8.3)
Exploitation: no confirmed exploitation recorded. Patch Next confirms exploitation only from CISA KEV.
Vendor response: Vendor response not established. A vendor fix does not mean a deployment is fixed.

## Affected components
- PyPI adx-mcp-server: affected <= 1.1.0

## Suggested inspection (read-only)
- `python -m pip show adx-mcp-server`: prints the installed version. Run with the environment that serves production active.

## Supported action
No complete vendor fix is recorded. Follow the primary source's mitigation guidance and check this record again before closing anything.

## Required regression checks
- Run the test suite and a production build.
- Exercise the features that depend on adx-mcp-server.
- Repeat the inspection and confirm that only fixed versions remain installed.

## Rollback considerations
- Keep the previous lockfile and deployment artifact. Rolling back reinstates the vulnerable version, so apply any documented mitigation while you fix forward.

## Unresolved questions
- Which deployments run an affected version?
- Exploitation status can change. Check again before lowering the priority.
- Mark the work resolved only after the fixed version is verified in production.

## Sources
- Verified: https://osv.dev/vulnerability/GHSA-vphc-468g-8rfp (OSV record GHSA-vphc-468g-8rfp lists affected ranges: PyPI adx-mcp-server >=0 <=1.1.0)
- Verified: https://github.com/advisories/GHSA-vphc-468g-8rfp (GitHub-reviewed advisory GHSA-vphc-468g-8rfp lists affected ranges: PyPI adx-mcp-server >=0 <=1.1.0)

Commands are suggestions: review each one before running it.