spectra-mcp
An MCP server that provides LLMs with a fingerprint-randomized Firefox browser for web browsing, clicking, typing, and taking screenshots, using invisible_playwright.
README
spectra_mcp
An MCP server that gives AI agents a stateful anti-detect Firefox powered by
invisible_playwright.
Agents can navigate, inspect accessible page snapshots, interact through stable element refs, fill forms, read text, and capture screenshots without managing raw Playwright state.
AI agent ── MCP/stdio ──► spectra_mcp ──► patched Firefox
Highlights
- Agent-first
snapshot → ref → actionworkflow - Automatic fingerprint profile, timezone, and locale selection
- Humanized mouse movement and browser-level fingerprint patches
- Typed MCP results and real
isError=truefailures - Secret redaction and environment-based proxy credentials
- Compact default tool profile for Hermes, OpenClaw, and other agents
Install
Requires Python 3.11+.
git clone https://github.com/LowOrbitLab/spectra_mcp.git
cd spectra_mcp
pip install -e .
python -m invisible_playwright fetch
The patched Firefox download is approximately 100 MB and only needs to run once. The browser dependency is pinned to an exact upstream commit.
MCP configuration
{
"mcpServers": {
"spectra_mcp": {
"command": "/absolute/path/to/venv/bin/spectra_mcp",
"env": {
"SPECTRA_MCP_TOOL_PROFILE": "agent"
}
}
}
}
Use an absolute executable path when the client filters subprocess environment variables. Keep parallel tool calls disabled because operations within one browser session are serialized.
Client-specific examples:
Agent workflow
- Call
binary_status; usebinary_installif needed. - Call
browser_start. - Navigate with
browser_navigate. - Inspect the page with
browser_snapshot. - Act through
browser_click_ref,browser_set_value_ref,browser_type_text_ref,browser_select_option_ref, orbrowser_set_form_values. - Use
browser_list_tabsandbrowser_activate_tabwhen a popup or new tab opens. - Use
browser_wait_forfor asynchronous text, URL, or element changes. - Read targeted content with
browser_find_textor paginatedbrowser_get_text. - Call
browser_stopwhen finished.
Mutating ref actions return a compact refreshed snapshot by default; use
observe="full" for structured element/frame arrays or observe="none" to
skip observation. Agent tools automatically use the only live session, so
models normally do not need to remember a session ID.
Documentation
- Tools and profiles
- Configuration and environment variables
- Fingerprint profiles and geo behavior
- Security and operational safeguards
- Development and testing
License
MIT. Firefox remains MPL-2.0. This project downloads the patched browser from upstream releases and does not redistribute it.
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。