MCP server that gives AI coding agents scored, maintainable, parameterised locators from a live page, in the test framework your repo already uses, then checks and repairs them.
MCP server for walkerOS flow development - discover packages, scaffold configs, validate, bundle, simulate, and test event pipelines
Shopify AI Toolkit — agent skills to search Shopify docs, generate and validate GraphQL, Liquid, and UI extension code, and manage stores through the Shopify CLI.
One-line onboarding for Verigent — the agent verification test you can't cram. Registers the Verigent MCP server for your agent and points it at its onboarding test.
Which parts of what you want to build open source already covers. Every repo checked live.
Local-first memory brain for AI coding agents: hooks capture sessions, beliefs injected per prompt.
One shared, durable memory for your AI coding agents — local-first, zero-dependency.
Mail between coding-agent sessions, on one machine or across machines; relays to a Swarmail server.
macOS automation MCP server with screen capture, UI interaction, and AI analysis
Locus is now repomap. This package is a thin alias of @sylphx/repomap (same MCP server and CLI).
Memory for coding agents: stores every fix and finds it again when the problem returns. EU-hosted.
Helps AI coding agents integrate MetaMask Embedded Wallets (Web3Auth) SDKs.
GitHub repository intelligence: search repos, read repo details, and list user repos. No key...
Query the GitHub REST API: profile, repos, repo details, code search.
GitHub status from GitHub Status. No key required.
Public GitLab projects and users. No key required.
The actuate command: init, dev, test, check, deploy, logs and doctor for Actuate actuators, plus a test harness (@actuate/cli/testing).
Workspace-aware BaseMind MCP bridge for DeepSeek Harness: every session gets BaseMind's code-intelligence tools for the repository it works in, with no MCP row to configure.
TypeScript SDK for Ratel — context engineering platform for AI agents. BM25 tool retrieval, MCP ingestion, framework-neutral capability tools.
GraphQL MCP: 20 real tools to read, check, lint, scaffold, build and run GraphQL code.
A registry for sharing, scanning, and tracking agent skills across teams.
The MCP server inside the Pipelex plugin: validate, prepare and run AI methods on Pipelex from a coding agent.
Genuinely-reusable MCP-server toolkit for the broberg.ai fleet: composable transports (stdio + Streamable-HTTP + SSE), composable auth (static Bearer, hashed 3-tier, OAuth 2.1 PKCE), and one typed def
Graft change records on plain git: the record model, git plumbing, start/evidence/land/log.
AXIOM v2 MCP server (stdio) and CLI: validate, compile, check and transactionally apply content-addressed manifest bundles inside an allowlisted set of roots
ActionDock SDK for defining and testing standalone AI Agent Actions
Shared local memory for coding agents with semantic recall, knowledge graph, and code navigation.
PolyCode CLI — one terminal agent for your own API keys across Anthropic, OpenAI, Gemini, DeepSeek, Mistral, xAI, Together, OpenRouter, Groq, Ollama + custom endpoints + MCP tools.
The mindly command: shared memory and live coordination for coding agents.
IWE: a Markdown knowledge base you and your AI agent work on together. CLI, LSP server and MCP server.
Model Context Protocol server exposing the ApexCharts ecosystem (charts, gantt, tree, sankey, grid, stock, maps) as tools for AI assistants
Crash-test your AI coding agent setup. One command, zero config: find out how easily Claude Code, Cursor & MCP can be hijacked by prompt injection.
Plugin-based MCP server for React Native/Expo runtime debugging, inspection, and automation via Metro/CDP
Agent Cairn server: MCP endpoint, JSON API and dashboard for shared agent memory.
AI agent skills for Contentrain — workflow procedures, framework integration guides
Local-first non-linear memory operating system for AI operators.
Весь каталог
IDE, git, линтинг и анализ кода. Серверов: 8,543, сначала самые используемые. Каждый ведёт на страницу издателя.