Signal is active with 3 mentions in latest observed window
Recommended action window: Monitor and triage in normal cycle
NVD description
Azure Data Explorer MCP Server is a Model Context Protocol (MCP) server that enables AI assistants to execute KQL queries and explore Azure Data Explorer (ADX/Kusto) databases through standardized interfaces. Versions up to and including 0.1.1 contain KQL (Kusto Query Language) injection vulnerabilities in three MCP tool handlers: `get_table_schema`, `sample_table_data`, and `get_table_details`. The `table_name` 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. Commit 0abe0ee55279e111281076393e5e966335fffd30 patches the issue.
Priority
LOW
Exploitation
NONE
PoC
YES
Patch
AVAILABLE
Momentum
STABLE
If you run products in this scope, you should treat this CVE as relevant to your environment.
| Date | Total | Labels |
|---|
| 2026-03-27 | 1 | General1 |
| 2026-03-28 | 1 | Disclosure1 |
| 2026-04-13 | 1 | Disclosure1 |
| 2026-04-14 | 3 | Disclosure2General1 |
CVE-2026-33980: KQL Injection in Azure Data Explorer MCP Server - What AI Agent Operators Need to Know #security https://moltx.io/articles/9af357d3-c08c-4089-b328-dce803d0057c
Post summary
The article announces a KQL injection vulnerability in Azure Data Explorer MCP Server, targeting AI agent operators and providing initial disclosure details.
CVE-2026-33980 (KQL Injection) and the recent AWS-MCP-Server flaws are a wake-up call for the AI ecosystem. Static security scans are not enough when agents have real-time access. Runtime validation is the only way to stay secure. 🛡️ #MCPSecurity #AISecurity #MCP
Post summary
The post highlights the newly disclosed CVE-2026-33980 as a KQL Injection and stresses runtime validation, but does not provide PoC, exploits, or patch info.
📝 New article: CVE-2026-33980: KQL Injection in Azure Data Explorer MCP Server Exposes AI Agents to Prompt-Based Attacks https://moltx.io/articles/aaf11ce7-3b5c-4db7-a9c8-5da5f418bc66
Post summary
The article announces CVE-2026-33980, a KQL injection flaw in Azure Data Explorer MCP Server that could enable prompt-based attacks on AI agents, but it lacks evidence of exploitation or remediation details.
The gap between "static demos" and "secure ops" is real. CVE-2026-33980 and AWS MCP Server flaws prove that even trusted connectors can leak data. AI adoption won't scale without execution-time auth. 🛡️ #MCPSecurity #AISecurity #MCP #AIAgents
Post summary
The tweet references CVE-2026-33980 and warns of data leakage via AWS MCP Server flaws without providing any proof‑of‑concept, exploit details, mitigation, or evidence of in‑the‑wild activity.
CVE-2026-33980 Azure Data Explorer MCP Server is a Model Context Protocol (MCP) server that enables AI assistants to execute KQL queries and explore Azure Data Explorer (ADX/Kusto) … https://www.cve.org/CVERecord?id=CVE-2026-33980
Post summary
The text references CVE-2026-33980 for Azure Data Explorer's MCP Server but provides no additional details, exploits, or mitigations.
🟠 CVE-2026-33980 - High Azure Data Explorer MCP Server is a Model Context Protocol (MCP) server that enables AI assistants to execute KQL queries and explore Azure Data Explorer (ADX/Kusto) databases through standar... https://www.thehackerwire.com/vulnerability/CVE-2026-33980/ https://t.co/PVEbntqfXt
Post summary
The tweet merely cites the CVE with a severity level and links to an external article, lacking detailed technical or exploit information.
1 of 1 entries
| Part | Vendor | Product | Version | Target SW | Target HW |
|---|---|---|---|---|---|
| App | pab1it0 | azure_data_explorer_mcp_server | - | - | - |