Mcp Toolbox For Databases Googleapis Mcp Toolbox
Monthly
SQL injection and security-boundary bypass in Google's MCP Toolbox for Databases (googleapis/mcp-toolbox) lets a low-privileged MCP client abuse the prebuilt BigQuery forecasting tool (bigquery-forecast) to read arbitrary BigQuery tables. The tool interpolates client-supplied column parameters (data_col, timestamp_col, id_cols) unescaped into a generated AI.FORECAST SELECT statement, and the operator-configured allowedDatasets guard only validates the history_data parameter - not the final assembled query - so an attacker breaks out of a string literal to reach datasets that should be off-limits. There is no public exploit identified at time of analysis; risk derives from the injection primitive plus the confidentiality impact of cross-dataset reads.
Authorization bypass in Google's MCP Toolbox for Databases (googleapis/mcp-toolbox) allows authenticated low-privilege clients to invoke high-privilege tools by selecting a legacy MCP protocol version. The flaw stems from missing scopesRequired enforcement in the 2025-06-18, 2025-03-26, and 2024-11-05 protocol handlers, and is reachable simply by omitting the MCP-Protocol-Version header so the server falls back to the vulnerable 2024-11-05 default. No public exploit identified at time of analysis, but the upstream fix (PR #3335) confirms the issue and its trivial triggering condition.
Authentication bypass in googleapis/mcp-toolbox allows remote unauthenticated attackers to gain access by presenting opaque OAuth tokens issued by unauthorized identity providers. The flaw lives in validateOpaqueToken's claim-checking logic, which silently skips issuer validation when an OAuth 2.0 introspection response omits the optional iss field. No public exploit identified at time of analysis, but the upstream fix in PR #3360 confirms the defect and CVSS 4.0 scores it 9.3 (Critical).
Authentication bypass in googleapis/mcp-toolbox lets remote unauthenticated attackers reach protected tools and backing data sources by submitting an OAuth 2.0 introspection response that omits the mandatory 'active' field. Because validateOpaqueToken stores Active as *bool and only rejects when the pointer is non-nil and false, a nil value falls through as authorized. No public exploit identified at time of analysis, but the CVSS 4.0 score of 9.3 and trivial logic flaw make this a priority fix.
SQL injection and security-boundary bypass in Google's MCP Toolbox for Databases (googleapis/mcp-toolbox) lets a low-privileged MCP client abuse the prebuilt BigQuery forecasting tool (bigquery-forecast) to read arbitrary BigQuery tables. The tool interpolates client-supplied column parameters (data_col, timestamp_col, id_cols) unescaped into a generated AI.FORECAST SELECT statement, and the operator-configured allowedDatasets guard only validates the history_data parameter - not the final assembled query - so an attacker breaks out of a string literal to reach datasets that should be off-limits. There is no public exploit identified at time of analysis; risk derives from the injection primitive plus the confidentiality impact of cross-dataset reads.
Authorization bypass in Google's MCP Toolbox for Databases (googleapis/mcp-toolbox) allows authenticated low-privilege clients to invoke high-privilege tools by selecting a legacy MCP protocol version. The flaw stems from missing scopesRequired enforcement in the 2025-06-18, 2025-03-26, and 2024-11-05 protocol handlers, and is reachable simply by omitting the MCP-Protocol-Version header so the server falls back to the vulnerable 2024-11-05 default. No public exploit identified at time of analysis, but the upstream fix (PR #3335) confirms the issue and its trivial triggering condition.
Authentication bypass in googleapis/mcp-toolbox allows remote unauthenticated attackers to gain access by presenting opaque OAuth tokens issued by unauthorized identity providers. The flaw lives in validateOpaqueToken's claim-checking logic, which silently skips issuer validation when an OAuth 2.0 introspection response omits the optional iss field. No public exploit identified at time of analysis, but the upstream fix in PR #3360 confirms the defect and CVSS 4.0 scores it 9.3 (Critical).
Authentication bypass in googleapis/mcp-toolbox lets remote unauthenticated attackers reach protected tools and backing data sources by submitting an OAuth 2.0 introspection response that omits the mandatory 'active' field. Because validateOpaqueToken stores Active as *bool and only rejects when the pointer is non-nil and false, a nil value falls through as authorized. No public exploit identified at time of analysis, but the CVSS 4.0 score of 9.3 and trivial logic flaw make this a priority fix.