MCP servers that give coding agents real developer tooling: linters, package registries, test runners, language docs and local build commands. 13,969 servers in this category.
Scan code, live URLs, and perform launch readiness checks directly within your AI client to identify security flaws and generate fixes.
$claude mcp add vibesafe-mcp -- npx -y vibesafe-mcp
Enforces security guardrails for Model Context Protocol traffic by filtering, redacting, and modifying tool calls and responses.
Provides a cognitive engine for AI coding agents with multi-layer memory, knowledge graph reasoning, and cross-session collaboration.
Provides AI agents with access to Stellar ecosystem documentation, live data, and ecosystem skills through a single authenticated gateway.
Manages MCP servers and AI skills within the DeepSeek Harness web interface using hot-reloading and JSON configuration.
Provides a self-hosted, privacy-first web analytics platform that lets an AI client query real-time visitor data, heatmaps, and conversions via MCP.
Enables AI clients to manage and configure modern WordPress Gutenberg carousel and slider blocks via a dedicated MCP server.
Enables AI coding agents to use GLM as a cost-effective subagent for file editing tasks.
$claude mcp add glm-mcp -- npx -y glm-mcp
Provides tools to build, validate, and lint conformant 3D scene artifacts for returning interactive scenes as MCP tool results.
Provides a persistent, AI-native object representation layer that uses semantic transactions and deterministic compilation to ensure verifiable state changes.
Routes Claude Code symbol and file searches through JetBrains Rider's index to reduce token usage in large Unreal C++ and .NET codebases.
Provides a hands-on workspace for learning IBM Bob IDE through guided labs on agentic Git workflows, microservices, and MCP server integration.
Adds a retrieval layer to coding models to find, rank, and read specific code evidence and logs from large repositories.
Scans MCP servers, configurations, and agent rule files to detect poisoned tools, hidden prompts, leaked tokens, and risky permissions.
Provides AI-assisted pull request reviews, tracking pending PRs per environment and proposing code changes after explicit approval.
Scans MCP server configurations, agent trust settings, and instruction files to detect security risks like tool poisoning and hidden instructions.
Trims, filters, and packs codebase context into lean Markdown to reduce token bloat for LLMs like Claude, ChatGPT, and Cursor.
Provides a visual workbench to inspect tools, test JSON-RPC traffic, and sync configurations with Claude Desktop and Cursor.
Allows AI agents to list hosts and execute commands on remote servers through a secure, auditable MCP server.
Allows an AI agent to remotely debug and automate a running LibreWolf or Firefox browser using WebDriver BiDi, Marionette, and D-Bus.