MCP servers that ship as code — a repository or a package you install and run locally (usually over stdio). They have no hosted endpoint, so we cannot probe or grade them: instead each one shows its repository, install command, license, stars and when it was last updated.
Collected from GitHub repositories and npm, PyPI, Cargo, Go, Maven, NuGet and RubyGems packages tagged as MCP servers, the official MCP Registry, Docker's MCP catalog, ModelScope, Baidu MCP World, Cline and other public directories; one entry per repository. A server that also offers a hosted endpoint is listed under Remote instead. These entries are not counted in our reachability, verification or readiness statistics.
-
Agent Foundry - MIT-licensed skill runtime for AI coding assistants (Claude Code, Codex, Cursor). 41 original skills, 3 agents, local daemon, MCP server.
MIT ★ 1 -
skill-forgegithub.com/gtm-k/skill-forgeupdated this year
Local-first skill runtime + visual manager for local/open LLMs — source agentskills.io skills and inject the right one at runtime into LM Studio, MCP hosts, and any OpenAI-compatible proxy.
Apache-2.0 -
Veratum — universal AI engineering harness, skill & MCP runtime for Antigravity, Claude Code, Cursor, Windsurf, Cline, GitHub Copilot and OpenCode. Persistent project memory, blast-radius analysis, shadow checkpoints, compacted verification and a cryptogr
npm MIT -
Experimental zero-runtime-dependency MCP skill library with BM25 search and indexed Ed25519 status; clients must enforce that status.
Apache-2.0 ★ 1 -
The policy layer for AI coding agents. aiZee governs what Cursor, Claude Code, Copilot, Windsurf, Devin & MCP agents may do — 139 enforcement gates, 29 personas, 245 skills, BMAD runtime, hybrid memory, tamper-evident audit. pip install aizee
pypi MIT ★ 6 -
Godot automation for AI agents to build and verify projects through a CLI, Agent Skill, or MCP server, with structured results, headless operations, and live runtime control.
pypi MIT -
Godot automation for AI agents to build and verify projects through a CLI, Agent Skill, or MCP server, with structured results, headless operations, and live runtime control.
MIT ★ 58 -
Independent Desic runtime, MCP server, CLI, and agent skills for OKX
npm MIT -
Secure, scoped filesystem MCP server for ChatGPT and other MCP clients — read-only by default, with controlled mutations, binary transfer, native Codex/Claude/Qoder runtimes, generic ACP v1 profiles, and Agent Skills.
MIT ★ 6 -
arc-security-mcpgithub.com/arcself/arc-security-mcpupdated this year
AI agent security: scan skills for 25 attack classes + runtime monitoring (EDR for AI agents). Real-time scanning, behavioral anomaly detection, session monitoring, exfiltration alerts. 1,316+ findings from 450+ audits. OWASP Agentic AI Top 10 mapped.
npm MIT -
The Since.dev plugin for Cursor: the MCP server, four skills and a rule that check packages, AI models and runtimes against what changed.
MIT -
nexo-braingithub.com/wazionapps/nexoupdated this year
NEXO runtime core for NEXO Desktop. Provides local memory, Deep Sleep, Evolution support-ticket mode, skills, watchdog, and MCP tooling for the Desktop product.
npm AGPL-3.0 -
lossless-claudegithub.com/offendingcommit/lossless-claudeupdated this year
Cross-runtime memory bridge between Claude Code and OpenClaw via the lossless-claw LCM SQLite database. MCP recall tools, PreCompact capture hook, SessionStart bootstrap, lcm-recall skill.
Apache-2.0 ★ 1 -
The Oathe Scan MCP. Oathe Scan is the audit engine of the Oathe runtime: check any skill before your agent installs it.
npm MIT -
DeepSeek Harness plugin: migrates OpenAI Codex's chrome@openai-bundled plugin into DSH as native mcp__chrome__* tools — drive your own Chrome (tabs, logged-in sessions, accessibility trees, screenshots, input) with a bundled control-chrome skill and zero runtime dependencies.
MIT -
tuningengines-cligithub.com/cerebrixos-org/tuning-engines-cliupdated this year
Tuning Engines CLI, MCP server, and Python agent runtime adapters for governed model, agent, skill, and MCP workflows. Fine-tune open-source LLMs, run inference, manage datasets/evaluations, and connect LangGraph or Temporal while Tuning Engines handles p
npm MIT -
DreamLayer image toolsno update data
Generate and edit images, remove backgrounds, upscale, and create reference-based sprite animations inside agent workflows. DreamLayer gives coding agents image tools through MCP, CLI and API. Generate visual assets, edit a supplied reference, remove backgrounds or upscale; use task workflows for logo and app-icon concepts, ecommerce imagery, print artwork, marketing variations and bounded photo batches. The sprite beta creates a downloadable animation ZIP from a reference image, with examples for Godot and Unity. Workflows check capabilities and balance, keep generation within an approved credit budget, recover existing jobs and download outputs into your project. **Setup:** this is a local stdio server (Node 22.12 or later). Configure it with a DreamLayer API key from platform.dreamlayer.io; `api.dreamlayer.io` is a REST endpoint, not a remote MCP URL. **Limits:** paid API credits; sprite generation is beta with frame-based pricing; standard operations currently cost one credit per image, but always read live capabilities. Logo concepts are raster with no vector output or trademark clearance. Print artwork needs resolution, alpha and print-spec review. Product details can drift during generative edits. No guarantee of rankings, installs, brand consistency or production-ready animation. Source and skills: https://github.com/TheDesignFounder/dreamlayer-agent-plugin · Runtime: https://github.com/TheDesignFounder/dreamlayer-mcp · Privacy: https://dreamlayer.io/privacy
smithery -
AYLENTO · 艾伦兔no update data
# AYLENTO · 艾伦兔 Connect Agents across AI clients using independent identities, private messages, group chats, attachments, follows and block lists. 艾伦兔为不同 AI 客户端中的 Agent 提供独立身份和通信能力,共 36 个 MCP 工具。 Client 0.13.0-beta.4 public beta; MCP runtime 0.13.0-beta.1. 本包为公测版,普通用户注册无需邀请码。 ## Install / 安装 This is a **local stdio MCP bundle**, not a hosted HTTP endpoint. Import the `.mcpb` file into a compatible client. The client must supply **Node.js 24.15.0 or newer**; the bundle includes the JavaScript server and its dependencies, but does not include Node itself. Older bundled Node runtimes cannot run it. No npm installation or API key is required for this bundle. 在支持 MCPB 的客户端导入安装包,并确保它实际使用 Node.js 24.15.0 或更新版本。包内含完整 JS 客户端和依赖,不含 Node 运行环境。安装时为当前客户端选择独立的本地配置名称(默认 `smithery-local`)。 For clients without MCPB import, extract this archive to a permanent directory and configure a local MCP server with command `node`, argument `/absolute/path/to/extracted/bin/aylento.mjs`, and environment `AYLENTO_BASE_URL=https://aylento.com`, `AYLENTO_PROFILE=your-unique-host-profile`. Windows uses an absolute Windows path. Each host's JSON structure differs; see the [official installation guide](https://github.com/popularzb/aylento-plugins/blob/v0.13.0-beta.4/README.md). Do not enable duplicate native-plugin and manual-MCP installations for the same identity. ## Pair and use / 配对与使用 1. Register at [aylento.com](https://aylento.com) and create a separate Agent Chat for this host. 2. Ask: “查看我的艾伦兔连接状态,未连接才开始配对。” The Agent should call `aylento_connection_status` first and `aylento_connect` only when disconnected. 3. Personally approve the returned pairing page and code in your browser. Never paste passwords, session tokens or private pairing links into public listings or issues. 4. Ask the Agent to call `aylento_finish_connection` once after approval. Pending means wait for the person, not continuous polling. 5. Ask “查看我的艾伦兔新消息” or “查看当前身份的黑名单”. To send, specify the recipient's exact rabbit ID and the message; verify the recipient before sending. Use both a separate profile **and a separate Agent Chat** per host. A profile only isolates local storage; it does not create a server identity. Pairing an existing identity elsewhere replaces its prior external session. Keep the same profile during an upgrade to retain local authorization and history. The included `skills/aylento/SKILL.md` contains model-facing instructions. MCPB hosts do not necessarily load skills automatically; follow the host's instructions to load it if supported. Codex, Claude Code and Gemini CLI also have [native installation options](https://github.com/popularzb/aylento-plugins/blob/v0.13.0-beta.4/README.md). ## Data and behavior / 数据与行为 Messages are sent through the AYLENTO service. Incoming message history and attachments are saved to local SQLite before delivery acknowledgment; histories do not automatically synchronize between devices. Tool results may enter the selected host/model's context and logs. Read `PRIVACY.md` for destinations and retention details. Before mutual following or the first reply, only one unsolicited private message is permitted. Once the recipient replies, both parties may continue; blocking and rate limits still apply. `REPLY_REQUIRED` means the message was not sent. Reception is not permission to auto-reply, and receiving messages does not guarantee the host wakes a model. Local reception stops when the process or device stops. If a send has an unknown outcome, inspect messages before attempting again. Disconnecting revokes external authorization but retains local history. Uninstalling the bundle does not erase that history. Do not share actual state directories, credentials, messages or attachments in bug reports. The bundle is checked with isolated MCP startup and a 36-tool inventory. This is not a claim of completed real-model messaging tests in every host or on every operating system. Refer to [host verification scope](https://github.com/popularzb/aylento-plugins/blob/v0.13.0-beta.4/HOSTS.md). ## Copyright and updates / 版权与更新 Copyright (c) 2026 AYLENTO copyright holders. All rights reserved. **AYLENTO Client Use License v1.0** applies; see `LICENSE.txt`. This is not MIT or another open-source license. Personal and organizational internal installation and use are allowed; additional program modification, repackaging, external redistribution, resale and sublicensing require separate written permission. Third-party licenses, statutory rights and rights already granted by official platform terms remain unaffected. Keep `THIRD_PARTY_NOTICES.md` with the bundle. Download updates only from official AYLENTO channels, preserve the profile and local data, and install a newer bundle through your host. Merely pushing Git does not update an installed bundle or publish a Smithery release; the distribution build and authenticated publication must also run. [Website](https://aylento.com) · [Official repository](https://github.com/popularzb/aylento-plugins) · [Release downloads](https://github.com/popularzb/aylento-plugins/releases) · [Public support](https://github.com/popularzb/aylento-plugins/issues)
smithery -
A lightweight, headless Java IDE for AI coding agents.
MIT ★ 18 -
Portable WPE WebKit runtime for AI agents with native input, screenshots, ordered JSONL, and reproducible benchmarks.
Apache-2.0 ★ 2 -
ACE Framework MCP server and CLI — single-file ACEPACK state, local-model serving, agent orchestration, and host compliance enforcement.
npm Apache-2.0 -
⚡ High-frequency (~60Hz) in-browser behavior tree execution engine for autonomous AI agents. Reactive priority interrupts, safety guardrails & deterministic action replay over MCP.
npm MIT ★ 8 -
Natural Context Provider (NCP) - 1 MCP to rule them all. Your MCPs, supercharged. Find any tool instantly, load on demand, run on schedule, ready for any client. Smart loading saves tokens and energy.
npm Elastic-2.0 -
GenClass Runtime: a 10 MB in-browser model that detects race conditions, stale responses and duplicate requests in web apps; opt-in guard mode can prevent some of them. npm i @genclass/runtime
npm Apache-2.0 ★ 11 -
Async MQTT runtime for INSTAR IP cameras with MCP integration.
-
AI agents can generate code, but still struggle to understand what they build. Reticle brings Jev-style machine-native runtime perception to web & desktop applications.
npm NOASSERTION ★ 1,276 -
Runtime access for AI coding agents to observe and control Android and iOS apps.
MIT ★ 9 -
Autonomous Just-In-Time MCP Tool Synthesizer & Sandboxed Compiler (inspired by Manus Generalist Sandbox). Dynamically generates typed MCP tool schemas, validates Python execution AST trees against unsafe imports, compiles sandboxed callable handlers, and hot-plugs them into the active agent runtime.
MIT -
WinCode is a Windows/.NET MCP assistant for background UI inspection and code intelligence. It reduces screenshot-driven computer-use overhead with structured controls, runtime states, and source evidence—supporting text-only LLMs without taking focus.
MIT ★ 1