Vulnerability  ·  2026-07-22

Google MCP Toolbox for Databases — SQL Injection Bypasses BigQuery Dataset Access Boundary

VulnerabilityHigh impactGlobalCVE-2026-15829
Google published CVE-2026-15829 (CVSS 8.6) on 2026-07-21 disclosing a SQL injection and security boundary bypass in its official MCP Toolbox for Databases, which exposes database tools to LLM agents via the Model Context Protocol.
MCP Toolbox for Databases is Google's own officially maintained MCP server bridging LLM agents to enterprise databases including BigQuery; a bypass of its dataset access-control boundary lets any agent or user with access to the forecasting tool exfiltrate data from BigQuery tables the operator explicitly intended to keep off-limits, undermining the core access-control guarantee enterprises rely on when exposing data tools to AI agents.
The prebuilt BigQuery forecasting MCP tool interpolates client-controlled parameters (data_col, timestamp_col, id_cols) unescaped via fmt.Sprintf into a generated AI.FORECAST SQL statement. The operator-configured `allowedDatasets` boundary only validates the history_data parameter, so an attacker can break out of a string-literal field to inject a multi-statement or cross-dataset query, bypassing the dataset access boundary and reading arbitrary BigQuery tables.
googleapis/mcp-toolbox (Google MCP Toolbox for Databases), bigquery-forecast prebuilt tool, v1.4.0
Update to the patched version of googleapis/mcp-toolbox per the vendor fix in PR #3324; audit any deployed bigquery-forecast tool configurations for unescaped parameter interpolation.
CVE Record: CVE-2026-15829googleapis/mcp-toolbox PR #3324
See this in the live feed Explore related AI security and governance findings — updated every morning.
Open the feed →