"Improving Cursor Functionality with Structured Plans and Multi-Step Tasks" matching MCP servers:

Implements a secure MCP server with API Key and JWT authentication, providing tools like echo, login, secure_action, and admin_action. Includes MCP Inspector integration for testing and debugging.

A wrapper for mcp-remote that provides secure authentication for protected MCP servers using Adobe IMS or Okta OAuth flows. It features automated token management, validation, and background refreshing for seamless access to remote resources.

A centralized gateway and router that integrates multiple MCP servers into a single endpoint with built-in policy enforcement and secret management. It features a Web GUI for managing tool access, audit logs, and multi-environment configurations across various sub-servers.

MCP server that gives an AI assistant simultaneous access to multiple Gmail accounts with per-account read-only, draft, or send tiers, two-phase write confirmation, and safeguards for handling untrusted email content.

Enables an MCP client to read, draft, organize, send, and delete email across multiple Gmail and Exchange Online/Outlook.com accounts, with per-account capability policies, recipient allowlists, confirmations, minimum OAuth scopes, and local audit logging.

Enables secure multi-agent property operations with delegated authorization, human approvals, and MCP tool execution through Ruhusa policy enforcement.

Enables role-based order management through MCP tools, allowing users to view and refund orders according to their permissions (USER, MANAGER, ADMIN) with audit logging and JWT authentication handled by a FastAPI client.

A proof-of-concept attack that exploits Model Context Protocol (MCP) tool registration to achieve persistent agent poisoning in AI assistants like Cursor, embedding malicious instructions that persist across chat contexts without requiring tool execution.

Enables enforcing memory boundary compartmentalization and multi-tenant security isolation for autonomous agents via a deterministic, zero-dependency Python skill. Seamlessly integrates with Claude Desktop, Cursor, and other MCP-compliant clients to execute isolation policies through structured JSON-RPC requests.

Enables developers and AI agents to enforce per-tenant security isolation for autonomous agents by compartmentalizing memory boundaries and managing sandboxed tenant execution. It exposes this deterministic, dependency-free guard through a native MCP server that plugs into Claude Desktop, Cursor, and other MCP-compliant clients.

Enables named, authenticated callers to run read-only introspection of a Google Cloud project and to read and write per-tenant notes that stay isolated between callers. Every request is scope-checked against a reviewed policy, rate-limited per caller, and audited without ever logging argument values.

A Model Context Protocol (MCP) server with HTTP transport that implements JWT authentication, allowing secure tool execution and prompt handling with role-based access control.

A deployable MCP server template for Cloudflare Workers that provides Google OAuth authentication and comprehensive analytics tracking of tool usage, performance metrics, and user behavior.

MCP server for the StepSecurity platform that enables investigating supply-chain and CI/CD security issues through natural language.

Provides 14 MCP tools for AI agent infrastructure, enabling knowledge base queries, skill search, handoffs, blueprint validation, trust scoring, identity verification, SLA validation, and compliance checks.

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 secure filesystem access with privacy controls using .mcpignore files to block MCP clients from reading or writing sensitive files and directories while allowing directory browsing and search.

A Cloudflare Workers-deployed MCP server that provides secure remote access to MCP tools through GitHub OAuth authentication. Includes example tools for basic math operations, user info retrieval, and image generation with configurable user access controls.

Enables agents to discover and securely invoke heterogeneous backend tools over unified SSE using JSON-RPC 2.0, with dynamic tool filtering, RBAC, quotas, and audit logging.

Enables AI agents to discover and execute tools via a secure MCP server with JWT authentication, RBAC, rate limiting, and audit logging.