Mcp Toolbox For Databases vulnerabilities
13 known vulnerabilities in Mcp Toolbox For Databases from Google. 13 are rated high or critical. Each entry lists the affected versions and the release that fixes it, where the vendor has published one.
Latest first
- 8.6 High severity
MCP Toolbox for Databases: Improper Limitation of a Pathname to a Restricted Directory
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 restriction
- 7.5 High severity
mcp-toolbox: Improper Authentication
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
- 7.5 High severity
mcp-toolbox: Allocation of Resources Without Limits or Throttling
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 paylo
- 7.7 High severity
mcp-toolbox: Improper Authorization
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
- 9.8 Critical severity
mcp-toolbox: Incorrect Authorization
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 lega
- 7.5 High severity
MCP Toolbox for Databases (googleapis/mcp-toolb…: Server-Side Request Forgery
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 u
- 8.1 High severity
MCP Toolbox for Databases (googleapis/mcp-toolb…: Improper Neutralization of Special Elements used in an SQL Command
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) a
- 9.1 Critical severity
MCP Toolbox for Databases (googleapis/mcp-toolb…: Improper Limitation of a Pathname to a Restricted Directory
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 r
- 8.1 High severity
MCP Toolbox for Databases (googleapis/mcp-toolb…: Missing Authorization
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 scopesReq
- 9.1 Critical severity
MCP Toolbox for Databases (googleapis/mcp-toolb…: Improper Authentication
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 in
- 9.1 Critical severity
MCP Toolbox for Databases (googleapis/mcp-toolb…: Improper Authentication
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 respo
- 9.4 Critical severity
MCP Toolbox for Databases: Origin Validation Error
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 "--
- 9.4 Critical severity
MCP Toolbox for Databases: Permissive Cross-domain Security Policy with Untrusted Domains
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