"Reading terminal outputs from a Next.js dev server while developing in Cursor" matching MCP servers:

MCP server enabling Claude Code to capture screenshots of Windows applications through WSL2, allowing AI to diagnose UI errors and verify layouts.

A secure terminal execution server that enables controlled command execution with security features and resource limits via the Model Context Protocol (MCP).

Enables Claude AI to play a cookie-themed dungeon RPG, including clicking cookies, recruiting heroes, exploring dungeons, and managing inventory through natural language commands.

Enables AI agents to request an independent second opinion from a different frontier model, with PII scrubbing before transit, live web search grounding, caching, and multi-provider failover.

This MCP server provides secure access to databases for AI agents, enforcing authentication, authorization, human approval, logging, and notifications to prevent dangerous actions.

Provides deterministic local development tools over stdio MCP, including repository mapping, code review, secret and dependency scanning, release checks, whitelisted checks, scaffolding, and workflow state tracking.

MCP server for querying Google's Open Source Vulnerabilities (OSV) database. Enables vulnerability lookups by package, version, commit, or ID using natural language via Pipeworx gateway.

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 authorized web/API security analysis as a stateful, multi-stage workflow with persistent session state, human-controlled validation, candidate versus confirmed finding tracking, and stop conditions.

Enables secure MCP server functionality with Clerk authentication and user-specific API key management. Provides Next.js documentation tools through protected endpoints with multiple authentication methods including OAuth 2.1 with PKCE.

Enables AI agents to interact with a user management REST API, providing list, get, and create operations while preventing destructive actions like update/delete through an explicit access registry.

Enables AI coding agents to execute commands that require credentials while resolving secrets from HashiCorp Vault, injecting them only for the spawned process and redacting them from agent-visible output. It also lets users authenticate via OIDC and check which Vault secret references resolve without exposing secret values.

Blocks AI coding assistants from installing non-existent packages and accessing non-existent files.

Enables AI assistants and signed-in support staff to search and read customer tickets, add internal notes, issue refunds under per-scope and per-customer limits, and export ticket data over a remote, OAuth-protected Streamable HTTP endpoint. Tool lists, resources, prompts, and write operations are gated by bearer tokens and audience-bound scopes so that refund and export actions stay bounded.

Enables AES-256-CBC encryption and decryption of messages with passphrase-derived keys, exposing tools, resources, and prompts for MCP clients like VS Code Copilot Chat.

Provides agent certification and trust verification tools for AI agents, enabling certification checks, trust score calculations, audit ticket issuance, and emergency kill switch activation through the A-SOC trust network.

Enables executing arbitrary Joern/CPGQL queries against a loaded Code Property Graph, loading source code in multiple languages (PHP, Java, JavaScript, Python, C/C++) to build new CPGs, and inspecting loaded projects and the active workspace. It communicates with a running Joern server over its synchronous HTTP query endpoint, so no state polling is required.

Enables agents to perform independent security review of AI-built apps by watching a GitHub repository and querying what the last reading found.

Enables AI agents to use upstream GitHub MCP tools only within task-scoped grants by filtering exposed tools and checking each call against repository, branch, base, path, destination, and count limits. Denied calls become reviewable widen requests instead of being silently allowed.

Enables autonomous agents and MCP-compatible clients to enforce policy-approved actions using risk tiers, reversible checkpoints, and token approval bounds.