Google Mcp Toolbox For Databases vulnerabilities

CVE-2026-14537 [CRITICAL] CWE-863 CVE-2026-14537: Incorrect Authorization in the direct HTTP API tool invocation endpoint in Google mcp-toolbox versio Incorrect Authorization in the direct HTTP API tool invocation endpoint in Google mcp-toolbox versions v1.3.0 and v1.4.0 allows an unauthenticated attacker to invoke tools protected by the scopeRequired feature via sending tool invocation requests through legacy HTTP endpoints when the --enable-api flag is active.

CVE-2026-11717 [CRITICAL] CWE-287 CVE-2026-11717: An authentication bypass vulnerability exists in the generic opaque token validation path (validateO An authentication bypass vulnerability exists in the generic opaque token validation path (validateOpaqueToken) of googleapis/mcp-toolbox. When verifying an unparsed opaque token via an OAuth 2.0 introspection endpoint (RFC 7662), the toolbox decodes the response into an introspectResp struct where the Active field is declared as a pointer to a b

CVE-2026-11720 [CRITICAL] CWE-22 CVE-2026-11720: A path traversal vulnerability exists in the HTTP tool URL builder of googleapis/mcp-toolbox. When A path traversal vulnerability exists in the HTTP tool URL builder of googleapis/mcp-toolbox. When constructing downstream API requests, the URL builder substitutes user-controlled pathParams into the configured tool path and parses the resulting string as a relative URL. While it checks that the input does not alter the scheme, host, or user info,

CVE-2026-11718 [CRITICAL] CWE-287 CVE-2026-11718: An authentication bypass vulnerability exists in the generic opaque token validation path (validateO An authentication bypass vulnerability exists in the generic opaque token validation path (validateOpaqueToken) of googleapis/mcp-toolbox. When the toolbox validates an opaque token via an OAuth 2.0 introspection endpoint (RFC 7662), it decodes the response into an introspectResp struct. However, the subsequent claim-checking logic (validateClaim

CVE-2026-102242 [HIGH] CWE-22 CVE-2026-102242: Improper link resolution (CWE-59 / CWE-22) in the allowedLocalRoots path validation in Google MCP To Improper link resolution (CWE-59 / CWE-22) in the allowedLocalRoots path validation in Google MCP Toolbox for Databases versions 1.2.0 through 1.9.0 allows a remote authenticated attacker with tool execution permissions to bypass directory boundary restrictions via symbolic links. Because path validation checks directories lexically without resolving

CVE-2026-15829 [HIGH] CWE-89 CVE-2026-15829: A SQL injection (CWE-89) and security boundary bypass (CWE-863) vulnerability exists in the prebuilt A SQL injection (CWE-89) and security boundary bypass (CWE-863) vulnerability exists in the prebuilt BigQuery forecasting tool (bigquery-forecast) of googleapis/mcp-toolbox. The tool accepts client-controlled parameters (data_col, timestamp_col, and id_cols) as plain strings and interpolates them unescaped via fmt.Sprintf directly into a generated AI.

CVE-2026-11719 [HIGH] CWE-862 CVE-2026-11719: An authenticated authorization bypass vulnerability exists in MCP Toolbox for Databases due to missi An authenticated authorization bypass vulnerability exists in MCP Toolbox for Databases due to missing scope enforcement across older protocol handlers. While the 2025-11-25 protocol version handler correctly enforces per-tool restrictions defined by scopesRequired, older supported protocol versions (2025-06-18, 2025-03-26, and 2024-11-05) omit this

CVE-2026-14538 [HIGH] CWE-285 CVE-2026-14538: An improper authorization and security-boundary bypass vulnerability in the bigquery-execute-sql too An improper authorization and security-boundary bypass vulnerability in the bigquery-execute-sql tool component of Google mcp-toolbox versions 0.16.1 through 1.4.0 allows an authenticated attacker to bypass allowedDatasets validation checks. The toolbox relies on the BigQuery dry-run API to enforce dataset restrictions, but due to a fail-open logic fl

CVE-2026-16481 [HIGH] CWE-918 CVE-2026-16481: A Server-Side Request Forgery (SSRF) and credential exfiltration vulnerability exists in the cloud-h A Server-Side Request Forgery (SSRF) and credential exfiltration vulnerability exists in the cloud-healthcare-fhir-fetch-page tool of googleapis/mcp-toolbox. The tool takes an unvalidated pageURL parameter from the client and issues an HTTP GET request to it using an authenticated client. The underlying transport automatically attaches an Authorizati

CVE-2026-9739 [CRITICAL] CWE-942 CVE-2026-9739: Vulnerable to DNS rebinding attacks when using SSE (http://b/499408790). During the beta phase, we i Vulnerable to DNS rebinding attacks when using SSE (http://b/499408790). During the beta phase, we implemented `allowed-origins` and `allowed-hosts` flags to align with MCP security guidelines. However, the hardcoded `Access-Control-Allow-Origin: *` header in the SSE initialization handler was inadvertently retained. This vulnerability specifically

CVE-2026-11624 [CRITICAL] CWE-346 CVE-2026-11624: The Model Context Protocol has a security warning advising servers to validate the "Origin" header o The Model Context Protocol has a security warning advising servers to validate the "Origin" header on all incoming connections to prevent DNS rebinding attacks. Prior to the v0.25.0 release, users had no way to validate the origin's host. In v0.25.0, a new "--allowed-hosts" flag was introduced alongside the existing "--allowed-origins" flag, enabl

CVE-2026-14541 [HIGH] CWE-287 CVE-2026-14541: An authentication bypass and audience confusion vulnerability exists in the Google OAuth provider co An authentication bypass and audience confusion vulnerability exists in the Google OAuth provider component of Google mcp-toolbox version 1.4.0. When a Google authService is initialized with mcpEnabled: true but lacks an explicitly defined audience or clientId, the ValidateMCPAuth pipeline for opaque tokens skips audience validation entirely. As a res

CVE-2026-14539 [HIGH] CWE-770 CVE-2026-14539: An allocation of resources without limits vulnerability in the HTTP handler component of Google mcp- An allocation of resources without limits vulnerability in the HTTP handler component of Google mcp-toolbox versions up to and including 1.4.0 allows an unauthenticated attacker to cause a denial of service (DoS). The /mcp endpoint handler reads incoming payloads directly into system memory using an unrestricted buffer loop (io.ReadAll) without applyi

CVE-2026-14540 [MEDIUM] CWE-918 CVE-2026-14540: A Server-Side Request Forgery (SSRF) vulnerability exists in the generic HTTP source and tool compon A Server-Side Request Forgery (SSRF) vulnerability exists in the generic HTTP source and tool components of Google mcp-toolbox versions 0.3.0 through 1.4.0. While the toolbox implements baseline input sanitization for user-controlled parameters, the underlying HTTP client (internal/sources/http/http.go) fails to safely regulate request redirection b