MCP servers that give coding agents real developer tooling: linters, package registries, test runners, language docs and local build commands. 13,951 servers in this category.
Enables AI clients to run Cursor's agent with any available model through the Model Context Protocol, supporting resumable sessions and parallel execution.
$claude mcp add cursor-mcp -- npx -y @qmediat.io/cursor-mcp
Provides AI agents with official sandbox test cards and decline code explanations for Latin American and global payment gateways.
$claude mcp add test-card-hub -- npx -y test-card-hub-mcp
Allows AI agents to interact with live Expo or React Native apps on real devices by reading screens, tapping, typing, and debugging errors.
$claude mcp add expo-mcp-bridge -- npx -y expo-mcp-bridge
Allows AI agents to free up system RAM on Windows by triggering the Mem Reduct hotkey without requiring administrator prompts.
$claude mcp add memreduct-mcp -- npx -y memreduct-mcp
Offloads bulk reading, web research, and test-gated code writing from frontier models to local LLMs to save tokens and context.
$claude mcp add localize -- npx -y localize-mcpOffloads bulk reading, web research, and test-gated code generation to a local LLM to save frontier-model tokens.
$claude mcp add local-llm-worker -- npx -y local-llm-worker
Correlates commits, pull requests, issues, and contributors between two Git references to generate structured release evidence.
$claude mcp add release-intel-mcp -- npx -y @barissozudogru/release-intel-mcp
Perform image resizing, format conversion, compression, cropping, and watermarking directly through a chat interface.
$https://github.com/theluckystrike/mcp-servers/releases/download/v0.21.0/image.mcpbAllows an AI client to create, list, and extract zip archives with built-in security guards against zip bombs, directory traversal, and symlink attacks.
$https://github.com/theluckystrike/mcp-servers/releases/download/v0.21.0/zip.mcpb
Enforces architectural decision integrity for coding agents using a FalkorDB graph-based causal verification firewall.
$claude mcp add cavdax -- npx -y @cavdax/mcp-server
A local gateway that manages Node.js service packages and exposes their gRPC capabilities to AI agents via MCP, Connect RPC, and gRPC.
Transforms any IDE into an autonomous software development studio using a swarm of 178 specialized AI agents and 8 subagents.
Provides a centralized management dashboard for DeepSeek Harness to manage MCP servers, skills, experts, and plugins with integrated marketplaces.
$claude mcp add dsh-armory -- npx -y dsh-armory
Provides coding agents with design guidance, real app references, design systems, fonts, and icons for web and iOS interfaces.
$claude mcp add --transport http uizze https://uizze.com/mcp
Isolate agent environments, audit MCP configurations for security leaks, and synchronize engineering instructions between Claude Code and OpenAI Codex.
$claude mcp add codex-multi-profile -- npx -y codex-multi-profile
Integrates the REA reverse engineering MCP server into DeepSeek Harness with automated provisioning of Node, JDK, and Ghidra.
$claude mcp add dsh-plugin-rea -- npx -y dsh-plugin-rea
Validates documentation against code implementation to detect drift and provides structured repair tasks for AI agents.
$claude mcp add docguard -- npx -y docguard-cli
Acts as a pre-action firewall for AI coding agents to intercept, evaluate, and block destructive tool calls before execution.
$claude mcp add rlhf-feedback-loop -- npx -y rlhf-feedback-loopActs as a pre-action firewall for AI coding agents to intercept and block destructive tool calls or secret leaks before execution.
$claude mcp add mcp-memory-gateway -- npx -y mcp-memory-gatewayBlocks, warns on, or logs risky AI agent tool calls before execution using local feedback lessons and prevention rules.
$claude mcp add thumbgate -- npx -y thumbgate