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.
-
Local MCP server and Chrome browser control runtime that lets AI agents use your existing browser session.
Apache-2.0 ★ 9 -
statepilotgithub.com/newsbruno/statepilotupdated this year
Predictable browser runtime for AI agents with memory, validation, recovery, and MCP integration.
MIT ★ 1 -
Deterministic security runtime between AI agents and the browser (MCP server).
Apache-2.0 -
agent-eyesgithub.com/mohanli-eng/agent-eyesupdated this year
Give Claude Code eyes to see the browser runtime — an MCP server + workflow skill for AI coding agents.
-
High-performance Rust MCP browser runtime for AI agents, built on Chromium/CDP with DOM interaction, screenshots, GPU/WebGPU acceleration, live browsing, media, authentication, security guards, and automatic Chrome runtime updates.
-
telecom-browser-mcpgithub.com/grimange/telecom-browser-mcpupdated this year
MCP server for telecom WebRTC applications that provides browser automation, SIP/WebRTC runtime inspection, and call-flow diagnostics using Playwright and the MCP Python SDK.
-
AI-native web browser runtime for autonomous agents with human supervision
npm MIT -
golliathgithub.com/Alaap008/golliathupdated this year
Browser Runtime MCP Server — expose live browser state as structured MCP tools for AI agents
-
TabBridgegithub.com/PuvaanRaaj/TabBridgeupdated this year
Local-first, model-neutral browser automation runtime for MCP clients and deterministic workflows
NOASSERTION -
Sandboxed runtime for programming languages and WASI binaries. Works in the browser, on your server, or via MCP.
npm MIT ★ 775 -
Native Rust Model Context Protocol (MCP) server connecting AI assistants (Claude, Cursor, Antigravity) to live browser sessions with zero runtime dependencies and context shielding
MIT -
OpenChamber extension: ShardX fingerprint-browser multi-session workspace (32 MCP tools, CDP mirror, zero-dependency runtime)
-
A local-first Chromium browser and web-research runtime for AI agents
Apache-2.0 -
Use OpenAI's installed Codex browser runtime from Claude Code or any MCP client on macOS.
npm MIT ★ 5 -
Lightweight stealth-oriented browser MCP server in Rust — one shared Chrome for many AI agents, 64+ Playwright-style tools, no Node.js runtime.
Apache-2.0 ★ 32 -
Multi-agent browser MCP runtime for isolated, persistent, parallel Playwright sessions. Run multiple AI agents without shared tabs or browser state.
npm Apache-2.0 ★ 3 -
Drive the Chrome or Edge you're already signed into — from one script. A zero-dependency browser automation runtime, CLI and MCP server for AI agents.
npm MIT ★ 2 -
Meleysgithub.com/bhumitschaudhry/Meleysupdated this year
Lightweight, agent-first browser runtime in Rust giving LLM agents control over Lightpanda and Chromium via MCP & REST API
Apache-2.0 -
Enterprise Autonomous Multi-Tier Browser Engine, Universal Form Inspector & AI Agent Web Runtime
★ 2 -
A local macOS MCP bridge that lets Claude Code and other MCP clients reuse OpenAI's installed Codex browser runtime.
npm MIT -
Control browser automation with this lightweight Rust-based MCP server for AI agents. Gain stealth capabilities and full page control without runtime dependencies.
-
PilotBrowseMCPgithub.com/EndymionLee/PilotBrowseMCPupdated this year
A browser runtime that lets AI agents control your real Chrome browser via MCP. Agents can explore websites, generate operation manuals, and reuse them to save tokens. AI操控你的真实浏览器。
MIT ★ 22 -
Local browser access and Phoenix runtime tools for coding agents: a persistent Chromium driven through a CLI or MCP server, with honest action outcomes.
npm MIT -
Browser automation, one binary. The simpler alternative to Playwright — no Node, no Python, no runtime. Library, CLI, MCP server, and chat UI for any AI agent.
go MIT ★ 14 -
⚡ Temporal Browser Intelligence & Agent-Owned Workflow Runtime with 350 Certified MCP Tools & Python SDK · Sub-Millisecond DOM Time-Travel, Target Memory & Deterministic Automation.
Apache-2.0 ★ 13 -
Agent-first browser automation runtime — deterministic Chromium sessions with replay-equal hash chains, MCP-native tools, and a content-addressed action store.
Apache-2.0 ★ 1 -
Record a browser workflow once, get a deterministic MCP tool your AI agent can call. Zero tokens at runtime. Postman for AI agents.
npm MIT ★ 24 -
A local Chrome runtime for browser agents. Reuse logins, run tasks in the background, handle supported verification steps, and keep submission receipts.
pypi MIT ★ 33 -
MCP server that connects AI assistants to Chrome DevTools Protocol for runtime debugging - set breakpoints, inspect variables, monitor network traffic, and automate browser interactions
npm MIT ★ 19 -
Local-first ChatGPT MCP runtime for secure computer use, code, browser automation, and developer workflows.
npm MIT ★ 14 -
browsegithub.com/ulpi-io/browseupdated this year
Fast headless browser and native app automation CLI for AI coding agents — persistent Chromium via Playwright, camoufox stealth runtime, session multiplexing, MCP server, and Android/iOS/macOS app automation.
Apache-2.0 ★ 15 -
Local MCP toolkit for AI agents: OCR, speech recognition, vision, document conversion, and browser automation with self-hosted local runtimes.
MIT -
PageCraft — Live Webpage Customizer & Local Browser MCP Runtime for Chrome/Edge (0.1s CSS + MV3 UserScripts + Gemini Nano / Ollama / BYOK / Claude Code & Cursor MCP)
npm MIT -
Purr-Verify-MCPgithub.com/0xheycat/Purr-Verify-MCPupdated this year
Self-hosted MCP verification and VPS operator runtime for AI agents, with durable jobs, isolated builds, browser QA, deployment, and redacted evidence.
MIT -
cdp-tools-mcpgithub.com/indate/cdp-tools-mcpupdated this year
MCP server that connects AI assistants to Chrome DevTools Protocol for runtime debugging - set breakpoints, inspect variables, monitor network traffic, and automate browser interactions
npm MIT -
Cross-platform MCP runtime for supervised computer use and developer automation: files, terminal, code intelligence, browser/desktop control, durable jobs, recovery, and workflows.
Apache-2.0 ★ 3 -
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 -
Local AI desktop app: a Chromium browser with a GPU-aware llama.cpp runtime, OpenAI-compatible API, AI chat and agents, Stable Diffusion image/video, TTS and music, plus an MCP server so Claude Code, Codex and Cline can drive your browser. Windows, macOS, Linux.
NOASSERTION ★ 151 -
@agentlensjs/mcp-servergithub.com/youngdan-hero/agentlensupdated this year
AgentLens daemon — collects browser runtime signals and exposes them to AI agents over the Model Context Protocol.
npm MIT -
maponcegithub.com/shivampatel0714/maponceupdated this year
AI authors browser automations once (record or map); deterministic Playwright replays them at zero token cost - self-healing when the UI drifts, with business rules, credential housing, and an MCP server. LLMs at build time, auditable code at runtime.
MIT -
mcp-error-hubgithub.com/nhonhgeargame/mcp-error-hubupdated this year
MCP server that bridges browser runtime errors to IDE AI agents — real-time debugging without leaving your editor
npm MIT -
Zero-config dev server & browser runtime error sensor for AI coding agents (Claude Code, Codex, Cursor, Antigravity) via MCP.
MIT -
Document-Review-AI-Assistantgithub.com/LaurentVeyssier/Document-Review-AI-Assistantupdated this year
A minimal document review AI assistant with an interactive in-browser editor and LLM-powered review tools, where the UI is generated by AI tools at runtime via MCP
-
sentinelgithub.com/firatorhan/sentinelupdated this year
Runtime intelligence for React UIs — inspect components, Redux state, Saga effects, and API calls in the browser, and expose it all to coding agents via MCP.
npm MIT -
AI-native debugging layer for PWAs: an AI agent (Claude Code via MCP) inspects live service workers, CacheStorage, IndexedDB, installability, and React/Vue/Svelte/Solid + Redux/Zustand/Pinia/Jotai state in your real logged-in browser. Why won't my SW update / why is my cache stale / why won't my PWA install — answered from the runtime.
npm MIT -
The Missing Runtime Telemetry Bridge for AI Coding Agents. Give your AI assistants (Cursor, Claude Code, Antigravity, Windsurf) real-time vision into active browser sessions — including web pages behind SSO, 2FA, VPNs, and dynamic client-side state — via standard Model Context Protocol (MCP).
MIT ★ 2 -
Avatar runtime for an AI VTuber: a browser-rendered character driven over a local HTTP API, one turn of dialogue at a time. No model provider, no API key, no prompt state.
Apache-2.0 ★ 2 -
Your AI coding agent can finally see what your dev server sees. Real-time runtime, bundler (Vite/Next.js/Storybook), TypeScript, and browser errors for Claude Code, Codex, Cursor, Antigravity, and Copilot via MCP.
npm MIT -
One MCP stdio endpoint for a whole toolchain — GitHub, GitLab, cloud, mail, browser and research tools — with capability-gated dispatch, a machine-checked ABI, and cartridges fetched on demand from boj-server-cartridges. Zero runtime dependencies.
MPL-2.0 ★ 3 -
SAP ABAP MCPgithub.com/Coaspe/sap-abap-mcpno update data
SAP ABAP MCP is a local-first Model Context Protocol server that enables AI coding agents to develop, test, analyze, and operate SAP ABAP systems through the official ABAP Development Tools HTTP services. It supports repository search and source editing, structured DDIC workflows, enhancement inspection, paged package navigation, source-backed object creation, semantic services, activation, ABAP Unit and ATC, transports, abapGit, RAP generation, debugging, bounded class and executable-program profiling, runtime dumps, traces and feeds, cross-system comparison, dependency analysis, guarded refactoring, and an opt-in same-origin Screen/GUI Status bridge. Curated compact, development, and assurance presets reduce tool-schema token use without removing capabilities from the default surface. The default local stdio mode can be extended with governed self-hosted Streamable HTTP, API-key roles, OIDC/JWT authentication, request-scoped SAP bearer forwarding, per-session isolation, rate limits, structured audit logs, or a side-effect-free embeddable Node.js API. It also includes browser OAuth Authorization Code with PKCE, a read-only transport assurance CLI and GitHub Action, BTP service-key profile import, and live-SAP evidence tooling. SAP profiles and credentials remain on the user's computer, with passwords and OAuth credentials protected by macOS Keychain or Windows DPAPI. SAP-dependent capabilities are validated against the user's own SAP release, configuration, and authorizations.
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 -
The hands of an AI agent.
MIT ★ 1 -
Portable WPE WebKit runtime for AI agents with native input, screenshots, ordered JSONL, and reproducible benchmarks.
oci Apache-2.0 ★ 2 -
Portable MCP runtime with 21 tools for processes, files, images, Chromium profiles and Windows desktop control. Shared OpenAI and Cloudflare connections with owner-approved OAuth.
AGPL-3.0 ★ 1 -
Powerful local-first browser automation for AI agents with real Chromium, isolated profiles, MCP, Maqam approvals, and verifiable evidence.
npm AGPL-3.0 ★ 9 -
A governed agent runtime prototype with a private know-how vault, capability APIs, and a native macOS MCP gateway.
-
High-frequency in-browser behavior tree execution engine for autonomous AI agents — 60Hz tick loops, reactive triggers, telemetry recordings, and safety guardrails.
npm MIT -
Turn any machine into an LLM-callable execution node — sandboxed exec, files, browser and native GUI automation over NATS. No inbound ports.
go MIT -
Give agents every interface—install once to search, run, inspect, and repair real software across APIs, browsers, desktops, local tools, and MCP.
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