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.
-
Session-isolated browser automation over MCP and Chrome DevTools Protocol
npm MIT -
playwright-parallel-mcpgithub.com/sumyapp/playwright-parallel-mcpupdated this year
MCP server for parallel browser automation with isolated Playwright sessions
npm MIT -
MCP server for parallel browser automation with isolated Playwright sessions
npm MIT -
Enhanced Playwright Tools for MCP with Project Session Isolation
npm Apache-2.0 -
trust-boundary-ctfgithub.com/acseguin21/trust-boundary-ctfupdated this year
Browser-based MCP CTF — OAuth token confusion and session isolation failure (CVE-2025-49596 pattern). DevTools only.
MIT -
@linatang/playwright-browser-manager-mcpgithub.com/lumoslnt/playwright-browser-manager-mcpupdated this year
Playwright MCP browser manager for multi-session automation with profile isolation and auto-healing recovery
npm MIT -
playwright-mcp-sessionsgithub.com/gabrielantonyxaviour/playwright-mcpupdated this year
Playwright MCP with persistent named sessions — save/restore browser auth, clone sessions, manage multiple isolated contexts. Fork of microsoft/playwright-mcp.
npm Apache-2.0 -
multi-agent-browser-mcpgithub.com/scrolldynasty/multi-agent-browser-mcpupdated this year
Local isolated multi-session browser runtime for external MCP clients
npm Apache-2.0 -
multi-playwright-mcpgithub.com/filhocf/multi-playwright-mcpupdated this year
Multi-session wrapper around @playwright/mcp — run multiple isolated browsers via a single MCP server
npm MIT -
Isolated, long-lived Chrome sessions for AI agents over MCP — full console + network capture, anti-bot stealth, and human login takeover.
MIT ★ 2 -
playwright-sessionsgithub.com/gabrielantonyxaviour/playwright-sessionsupdated this year
Playwright MCP with persistent named sessions — save/restore browser auth, clone sessions, manage multiple isolated contexts. Fork of microsoft/playwright-mcp.
npm Apache-2.0 -
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 -
Local (stdio) MCP server in Go that gives opencode and other model hosts a safe, isolated sandbox for running arbitrary commands — a secure drop-in replacement for the host shell. Deny-by-default, ephemeral per-session containers with Docker, or macOS seatbelt sandbox-exec with no daemon. Streaming output.
go Apache-2.0 -
wsl-chrome-mcpgithub.com/477174/wsl-chrome-mcpupdated this year
Chrome DevTools Protocol (CDP) server for MCP — per-session Chrome isolation on WSL, 33 browser automation tools
★ 1 -
Azure AI Foundry Agents MCP server with user isolation and session management
MIT ★ 1 -
agentmesh-mcpgithub.com/fedegonzalezm-coder/agentmeshupdated this year
Multi-agent framework with persistent expert sessions and context isolation — MCP server for Claude Code
pypi MIT -
Local MCP teamwork between Claude and Codex, with persistent sessions, isolated workspaces, and reviewed integration.
MIT ★ 2 -
@vxavierr-mindo/teamsmcpupdated this year
Multi-agent orchestration MCP server — discovers and spawns project agents in isolated sessions
npm -
A shared, on-demand pool of isolated headless browser sessions for Claude Code subagents. 59 MCP tools on one headless Chromium, with zero cross-session bleed.
MIT -
Local browser-control engine for MCP agents: existing Chromium sessions, per-site permissions, one-use approvals, and isolated Playwright profiles.
MIT ★ 5 -
ipython-mcpgithub.com/ConorForgie/ipython-mcpupdated this year
MCP server giving Claude a stateful IPython kernel per session, with per-env isolation.
MIT -
Local MCP server for persistent, isolated SSH sessions and safe remote file operations via native OpenSSH
npm MIT -
Secure SSH gateway for AI assistants — MCP server with connection pooling, session isolation, command safety, and web audit panel
pypi MIT ★ 4 -
B2C Model Context Protocol (MCP) server for conversational food ordering — confirmation-token checkout, server-side pricing, allergen safety, session isolation.
MIT -
Lazy, session-isolated Tor Browser automation for AI agents, with a Rust CLI, MCP server, and Nix flake.
MIT -
Telegram forum-supergroup bot for Claude Code / OpenCode — one topic per task, isolated sessions, per-thread MCP
npm MIT -
One shared, logged-in Chrome for every Claude Code session — per-client tab isolation for @playwright/mcp --shared-browser-context, launchd service, guard hook, tab CLI
MIT -
mcp-virtual-fsgithub.com/lu-zhengda/mcp-virtual-fsupdated this year
PostgreSQL-backed virtual filesystem exposed via MCP tools. Persistent, session-isolated file operations for AI agents.
npm MIT ★ 3 -
Browser automation MCP server that does not get blocked. Anti-detect Firefox (Camoufox), sign-in-once profiles, and mandatory session isolation between conversations.
pypi NOASSERTION ★ 3 -
Multi-agent orchestration for AI coding CLIs — Claude Code, Kiro, Codex, and more, coordinated in isolated tmux sessions
go Apache-2.0 ★ 1,562 -
poke-pcgithub.com/calganaygun/poke-pcupdated this year
safely extend poke's capabilities to your machine with an isolated docker environment. poke pc is a secure mcp worker that lets your ai agent run terminal commands and manage sessions within a sandboxed container
npm MIT ★ 20 -
mcp-supersubagentsgithub.com/yigitkonur/mcp-supersubagentsupdated this year
MCP server for spawning and managing parallel AI agents. Run multiple autonomous Copilot sessions as background tasks with isolated workspaces and multi-account PAT rotation.
npm ★ 1 -
MCP server that runs Playwright MCP's browser tools in many isolated sessions at once, so AI agents can work through web pages in parallel.
MIT -
Local-only MCP server for RimWorld modding: search the game's Defs and C# API, decompile installed mods, build mods, and test them in an isolated game session. Works with Claude Code, Codex, and any MCP client.
MIT ★ 4 -
MCP server that gives every AI agent session its own persistent, isolated Chromium browser (Chrome, Edge, Brave, Chromium) with extension control. Built on chrome-devtools-mcp.
MIT -
magic-cc-codex-workergithub.com/wenqingyu/magic-cc-codex-workerupdated this year
Parallel OpenAI Codex agents inside Claude Code — multi-agent orchestration with git worktree isolation, resumable sessions, and dual-model PR review. MCP plugin.
NOASSERTION ★ 5 -
Parallel Claude agents with contracts, not prompts. MCP server that decomposes a task into isolated tenant sessions with structured checkpoint validation and auto-eviction. Runs on your Claude Pro/Max subscription.
-
Local MCP broker for coding agents from Cursor, Antigravity, ZCode, Codex, and Claude Code. Configure agent pools, models, and effort across projects; run parallel workers in isolated workspaces and coordinate independent reviews with durable sessions and artifacts.
MIT -
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 -
Shared Chromium profile with isolated conversation tabs for Codex and OpenCode.
npm MIT ★ 1 -
Free local MCP bridge for background Brave tabs with existing sessions. Rust, macOS App Sandbox, no bridge telemetry or hosted relay. Developer preview.
MIT -
vetka-mcp-coregithub.com/danilagoleen/vetka-mcp-coreupdated this year
MCP server with tools, memory, session management. Connect Claude Code/Desktop to VETKA.
MIT ★ 1 -
Open-source Chrome/Edge extension for QA: log in as multiple users on the same site side by side. Role matrix (RBAC), snapshots, Playwright storageState, bug recorder, device emulation, AI control via MCP.
MIT ★ 1