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 like Claude Code to drive Unreal Editor 5.8+ by automating engine toolsets, Python scripting, and asset importing.
Provides portable agentic engineering rules and an MCP tool server for managing project logs and global agent instructions.
Provides a local-first desktop infrastructure that connects AI agents to applications and workflows through an MCP gateway and permission layer.
Tests MCP servers for vulnerabilities by sending malformed JSON-RPC payloads to identify crashes, hangs, and information leaks.
Provides a collection of production-ready AI agents built with Google ADK and Gemini that compose existing public MCP servers to perform specific tasks.
Performs offline, read-only security audits of MCP configuration files to detect credential leaks and tool-description poisoning.
Probes OAuth discovery issuer validation to prevent credential leakage to attacker-controlled token endpoints.
A local, air-gapped multi-agent coding harness that executes tools in a Podman sandbox and uses sequential agent roles on local models.
Provides shared project memory, tasks, and rules for AI coding agents to maintain context across different chats and computers.
Manages Google Antigravity CLI configurations, MCP servers, plugins, and custom skills using GNU Stow dotfiles.
Tests and audits Korean public data MCP servers for protocol compliance, schema accuracy, and error handling in isolated environments.
A planned monorepo providing Python-based MCP servers for Zendesk, Google Workspace, Gmail, Calendar, and Skilljar.
Build, run, edit, and review native Sley programs using a command-line toolkit, SDKs, and specialized application adapters.
Benchmarks static analyzers on real, publicly disclosed vulnerabilities in open-source MCP servers using Docker and SARIF scoring.
Provides shared task state, source-backed memory, and executable completion checks for AI coding clients like Claude Code and Cursor.
Provides an offline, end-to-end test environment to validate the Commonpost MCP for Thunderbird extension using real Thunderbird instances and containers.
Enables AI agents to orchestrate Unreal Engine scene construction through a controlled eight-stage workflow driven by reference images.
Provides a self-hosted gateway to connect AI agents to files, shell commands, and SSH targets on remote or local machines.
Provides a secure MCP tool service featuring three-layer SQL guardrails, JWT-based tool scoping, and a Text2SQL state machine.
Scans MCP tool declarations for security risks like command injection, secret exposure, and improper tenant boundaries.
