inboxfewer
Verified Safeby teemow
Overview
inboxfewer serves as a Model Context Protocol (MCP) server, granting AI assistants programmatic access to Google services like Gmail, Google Docs, Drive, Calendar, Meet, and Tasks.
Installation
docker run -p 8080:8080 ghcr.io/teemow/inboxfewer:latestEnvironment Variables
- GOOGLE_CLIENT_ID
- GOOGLE_CLIENT_SECRET
- MCP_BASE_URL
- MCP_OAUTH_ALLOW_PUBLIC_REGISTRATION
- MCP_OAUTH_REGISTRATION_TOKEN
- MCP_OAUTH_ENCRYPTION_KEY
- MCP_OAUTH_ALLOW_NO_STATE
- MCP_OAUTH_MAX_CLIENTS_PER_IP
- MCP_INTERSTITIAL_LOGO_URL
- MCP_INTERSTITIAL_LOGO_ALT
- MCP_INTERSTITIAL_TITLE
- MCP_INTERSTITIAL_MESSAGE
- MCP_INTERSTITIAL_BUTTON_TEXT
- MCP_INTERSTITIAL_PRIMARY_COLOR
- MCP_INTERSTITIAL_BACKGROUND_GRADIENT
- ALLOWED_ORIGINS
Security Notes
The project exhibits an exceptionally strong security posture. It adheres to Kubernetes Pod Security Standards (Restricted profile) by running as a non-root user, dropping all capabilities, and enforcing a read-only root filesystem. NetworkPolicy support is included for defense-in-depth. Crucially, it provides critical warnings against common secret management anti-patterns (e.g., `--set` for secrets, committing to Git) and recommends robust solutions like Kubernetes Secrets, External Secrets Operator, and Sealed Secrets. Its OAuth 2.1 implementation features an OAuth Proxy architecture, ensuring LLMs never handle sensitive tokens directly. This includes dynamic client registration (RFC 7591), PKCE, mandatory state parameters, refresh token rotation, per-IP client limits, and optional token encryption at rest (`MCP_OAUTH_ENCRYPTION_KEY`). All HTTP responses include security headers, and HTTPS is enforced for non-loopback addresses. Image scanning with Trivy is integrated into CI/CD. The development team clearly prioritizes security-by-design.
Similar Servers
zenfeed
An AI-powered information hub that acts as an intelligent RSS reader, real-time news knowledge base, and personal assistant for monitoring events and delivering analysis reports.
cupertino
Local Apple Developer documentation crawler and Model Context Protocol (MCP) server for AI agents, providing offline access and structured API information.
mcp-server-computer
This server acts as a Spring AI MCP Server component to provide cross-platform computer configuration information (OS, user, Java, and platform-specific details) to an AI agent.
meds-mcp
Provides a medical context protocol (MCP) server and a React-based chat interface for interacting with patient records via LLMs and medical ontologies, facilitating evidence review and patient data exploration.