MCP Inspector

mcpc is Apify's open-source universal command-line client for the Model Context Protocol (MCP). It maps MCP operations for tools, prompts, resources, asynchronous tasks, skills, notifications, and logging to shell commands, communicating with local stdio servers and remote Streamable HTTP servers. Persistent named sessions keep connections, caches, notifications, and authentication state available across commands. The CLI supports progressive tool discovery through grep and compact tool listings, interactive shells, JSON output for jq, xargs, and shell pipelines, schema validation for scripts and CI, OAuth 2.1 with PKCE and bearer authentication, and a local proxy mode that keeps upstream credentials and OAuth tokens outside AI sandboxes. Its single configuration and credential store can be reused by shell-based AI coding agents, with credentials stored in the operating system keychain. It is distributed as the `@apify/mcpc` npm package.

An MCP server from Zapier that connects authenticated applications so compatible AI tools can access and use them through a single integration layer. It supports clients including Cursor, Claude Code, and Codex.

Chrome DevTools for agents (chrome-devtools-mcp) is an MCP server from the Chrome DevTools project that lets coding agents control and inspect a live Google Chrome or Chrome for Testing browser. It uses Puppeteer for browser automation, including navigation and actions that wait for results, and exposes DevTools capabilities for recording and inspecting performance traces and insights, analyzing network requests, taking screenshots, and inspecting browser console messages with source-mapped stack traces. A CLI is also provided for use without MCP, with configuration options including headless, isolated, slim, concurrent-session, persistent-profile, WebSocket, and Android-debugging modes. It requires Node.js LTS, a current stable Chrome version or newer, and npm. Browser contents are exposed to MCP clients; performance tools may query the Google CrUX API, and usage statistics and update checks are enabled by default with an opt-out flag.

Awesome MCP Servers is a curated collection of Model Context Protocol (MCP) server implementations, maintained as a GitHub repository with a synchronized web directory. It catalogs production-ready and experimental servers that let AI models interact with local and remote resources through standardized interfaces, including file access, databases, API integrations, browser automation, cloud platforms, research services, and other contextual tools. The repository organizes entries by capability, programming language, deployment scope, operating system, and whether an implementation is official.