"Comment perdre du poids (How to lose weight)" matching MCP servers:

An MCP server that sends plain-text Gmail messages only to a predefined allowlist, using generated recipient IDs instead of email addresses to enforce security.

Multi-user MCP server with user isolation, permissions, resource sharing, and an admin console for managing MCP tools across users.

A demonstration server that reveals security risks by accessing sensitive environment variables, illustrating how MCP tools can potentially leak user data without explicit consent.

A vulnerable MCP server implementation that demonstrates how poor coding practices can lead to security issues like Remote Code Execution, designed for educational purposes to add numbers.

Demonstrates how to secure an MCP server with OAuth 2.1 using AWS Cognito, with support for dynamic client registration and client ID metadata documents.

Enables defenders to deploy a decoy MCP tool server that records and fingerprints how LLM agents probe, escalate, and persist, without exposing real systems.

Tells you how you and your Claude agent actually work together. Reads CLAUDE.md, hooks, skills, memory + scheduled tasks and writes you a letter. Local-only, no API keys, no data leaves your machine.

A remote MCP server implementation that demonstrates authentication and authorization capabilities using OAuth 2.1. This is a workshop project for learning how to build secure MCP servers with user authentication.

An MCP server that measures how effectively hashing tool definitions detects unauthorized changes, evaluating 20 policies across field sets and canonicalization methods. It demonstrates that approval-dialog-based pins miss most attacks, with structural/semantic normalization being free but text folding trading detection for fewer false alarms.

Enables MCP clients to manage Tines cases via the Cases v2 API, supporting create, read, update, close, and comment operations. Runs in a container via podman/docker and defaults to read-only for safety.

A demonstration tool that showcases potential security attack vectors against Model Control Protocol, illustrating how malicious plugins can exploit weaknesses in MCP architecture.

A zero-dependency Node.js playground for debugging how MCP clients authenticate to an MCP server over HTTP.

A secure MCP server example that demonstrates how to deploy to Google Cloud Run with authentication and identity token protection. Serves as a tutorial template for building production-ready MCP servers in the cloud.

Enables remote MCP client connections with WorkOS AuthKit authentication and organization-based permission control. Demonstrates how to gate tool access based on user permissions, including features like image generation behind specific authorization checks.

An MCP server for inventory management (list, add, delete, comment on items) that demonstrates Auth0 for MCP capabilities including JWT bearer auth, fine-grained authorization with FGA, CIBA step-up approval, and Token Vault integration.

Enables AI agents to send and receive email with enforced security policies, scoped mailboxes, and human approval for external sending.

Enables AI assistants to manage software licenses through natural language commands by connecting to the ExisOne licensing platform.

SQL guardrails for AI agents, sitting between the agent and Postgres to enforce policies, block destructive queries, and audit all access.

This server enables interaction with SailPoint IdentityIQ through SCIM API endpoints, allowing MCP clients like Claude Desktop to manage identity resources using natural language.

Multitenant Streamable HTTP wrapper for SentinelOne's purple-mcp. Enables MSPs to expose SentinelOne threat detection and response capabilities to AI assistants across multiple tenants.