MCP servers that give coding agents real developer tooling: linters, package registries, test runners, language docs and local build commands. 13,953 servers in this category.
Lets an AI agent access mobile QA results, including bug evidence, screen graphs, network hosts, and build comparisons for Android and iOS apps.
$claude mcp add mcp -- npx -y @flytrap-qa/mcp
Verifies AI agent claims and documentation promises by checking them against the actual codebase with evidence-based proof.
$https://github.com/EmanueleCell4/elliot-mcp/releases/download/v0.6.0/elliot-mcp-0.6.0.mcpb
Provides read-only analysis tools for Google Search Console, Google Ads, and AdSense to AI clients.
$claude mcp add metricport-mcp -- npx -y metricport-mcp
Checks project lockfiles against security advisories to identify vulnerable packages, runtime flaws, and platform breaches.
$claude mcp add keep-me-secure-mcp -- docker run -i --rm ghcr.io/robertkeus/keep-me-secure-mcp:v1.7.0
Lets an AI client manage video and voice rooms, place AI-agent or SIP calls, and scaffold MediaSFU SDK integrations across multiple platforms.
$claude mcp add mcp-sdk-tools -- npx -y @mediasfu/mcp-sdk-tools
Allows an AI assistant to search a catalog of Quasar Framework components and retrieve their source code directly into a project.
$claude mcp add quasarui-mcp -- npx -y quasarui-mcp
Allows AI agents to manage and use credentials like SSH, HTTP, and database secrets without exposing them in the prompt or logs.
$claude mcp add demipass -- npx -y demipass
Lets users claim free subdomains to point at their own hosting, email forwarding, or URL redirects.
Converts web pages, documents, images, audio, and YouTube videos into clean, token-efficient Markdown for AI agents and humans.
Provides a local AI desktop workspace for managing DeepSeek Harness sessions, projects, files, web research, and community plugins.
Enables AI agents to perform real Chrome automation through a platform-neutral browser automation layer and SDKs.
Lets an AI client inspect, edit, clean up, and security-scan Claude Code, Codex CLI, OpenCode, and DSH configs, MCP servers, skills, and memories.
Enables AI clients to create, manage, and monitor n8n workflows using natural language through a conversational interface.
Exposes a suite of 38 tools for files, shell, search, and browser automation to web-based AI clients via an OAuth-gated MCP endpoint.
Lets an AI agent create, inspect, and fix pixel art sprites, tiles, and animations from JSON recipes, exporting PNG, APNG, GIF, and atlases.
$https://github.com/skulitom/Pixelbolt/releases/download/v0.16.0/pixelbolt.mcpb
Lets an AI coding client query Cursor CCE for source-anchored project context and optionally run a scoped Cursor Agent task.
Lets AI clients query what coding agents actually changed, ran and tested on the local machine, with evidence from real output.
$claude mcp add dotpals -- npx -y dotpals
Stores long-term memory in a local SQLite file and lets AI coding agents recall, reflect on, and forget context across sessions.
$claude mcp add synabun -- npx -y synabun
Lets AI clients read, search, compose, and manage email through Mozilla Thunderbird without exposing credentials.
$claude mcp add thunderbird-cli -- npx -y thunderbird-cli-mcp
Provides a shared local memory, context, and safety layer for multiple AI coding tools to synchronize sessions and project knowledge.
$claude mcp add egc -- npx -y @egchq/egc