spectra-mcp

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.

Category
访问服务器

README

Spectra MCP

An MCP server that exposes invisible_playwright — an anti-detect Firefox with patched fingerprint surfaces — to LLMs.

Your assistant can launch a fingerprint-randomized browser, navigate, click, type, read the DOM, and take screenshots through it, using the standard Playwright surface, but with a patched Firefox engine under the hood.

The patched Firefox binary is a one-time ~100 MB download (python -m invisible_playwright fetch, or the fetch_binary tool).


How it works

  • invisible_playwright is a drop-in Playwright replacement that patches Firefox at the C++ level (navigator, GPU/WebGL, canvas, fonts, audio, WebRTC, timezone, network) and humanizes mouse motion in the driver.
  • An MCP server is a resident process, which is exactly what a stateful browser needs. This server keeps long-lived sessions in-process; each session owns an InvisiblePlaywright instance plus one or more pages. Tools operate on the session's active page unless told otherwise.
LLM ──MCP/stdio──► server ──► InvisiblePlaywright ──► patched Firefox
                       ▲                (async API)
              sessions held in-process

Install

pip install -e .                       # or: pip install spectra-mcp
python -m invisible_playwright fetch   # one-time ~100 MB, SHA256-verified

Requires Python 3.11+. Supported platforms: Windows x86_64, Linux x86_64/arm64, macOS arm64/x86_64.

On macOS the app is ad-hoc signed (not notarized): if Gatekeeper complains, clear the quarantine flag once with xattr -dr com.apple.quarantine on the cached Firefox.app.


Configure your MCP client

opencode (opencode.json)

{
  "mcp": {
    "spectra-mcp": {
      "type": "local",
      "command": ["spectra-mcp"],
      "enabled": true
    }
  }
}

Claude Desktop (claude_desktop_config.json)

{
  "mcpServers": {
    "spectra-mcp": {
      "command": "spectra-mcp"
    }
  }
}

Cursor (~/.cursor/mcp.json)

{
  "mcpServers": {
    "spectra-mcp": {
      "command": "spectra-mcp"
    }
  }
}

If the console script isn't on PATH, use the module form instead:

{ "command": "python", "args": ["-m", "spectra_mcp"] }

Quick start (for the LLM)

  1. fetch_binary (once) — download the patched Firefox if binary_status says ready: false.
  2. start_session → returns session_id, seed, and the initial page_id. Pass a proxy_server for residential/socks proxies.
  3. goto a URL, then query_elements / get_text / screenshot to understand the page.
  4. click / fill / press_key to act. Mouse motion is humanized.
  5. close_session when done (or just let the server shut down — the lifespan cleans up all Firefox processes).

Log the seed to replay an identical fingerprint later (start_session with the same seed).


Tool reference

Tool exposure is selected at server startup with SPECTRA_MCP_TOOL_PROFILE:

Profile Tools Approx. tool tokens Intended use
setup 2 ~230 Binary status/download only.
core 28 ~4,165 Default. Setup plus normal browsing, reading, forms, tabs, screenshots and evaluate.
full 55 ~7,942 Every advanced mouse, keyboard, dialog, cookie/storage and frame tool.

Token estimates use the o200k_base tokenizer and an OpenAI-style function-tool payload. Exact numbers vary by MCP client and whether output schemas are included.

core includes session lifecycle, page switching/popups, goto/reload, click/fill/type_text/press_key, scrolling/hover/selects, text/HTML/ attribute/element reads, visibility, screenshots, waits and evaluate.

SPECTRA_MCP_TOOL_PROFILE=core spectra-mcp
SPECTRA_MCP_TOOL_PROFILE=full spectra-mcp

PowerShell equivalent:

$env:SPECTRA_MCP_TOOL_PROFILE = "full"
spectra-mcp

The server must be restarted after changing profiles. The reference below lists the complete full profile; disabled functions remain available internally for tests but are not advertised to the model.

Setup / binary

Tool Description
binary_status Is the patched Firefox cached? Does not download.
fetch_binary Download + SHA256-verify the binary (~100 MB, one-time). force=True to re-download.

Session lifecycle

Tool Description
start_session Launch a browser with a fresh/seeded fingerprint. Returns session_id, seed, page_id.
close_session Close a session and free its Firefox process.
list_sessions Active session ids.
session_info Session metadata, pages, active page id, URL and title.

Pages

Tool Description
new_page Open a new tab; becomes the active page.
close_page Close a page (active by default).
switch_page Change the active page.

Navigation

goto, go_forward, reload

Interaction (humanized)

click, fill, type_text, press_key, keyboard_press, select_option, hover, focus, check, uncheck, scroll

Reading

get_text, get_html, get_attribute, query_elements, is_visible

query_elements returns a structured snapshot (tag, id, name, type, role, href, text, value, placeholder, visible, bounding rect) so the LLM can decide what to click without scraping raw HTML.

Screenshot

screenshot → returns image content directly to the LLM. Defaults to JPEG (quality=85) to keep payloads small; image_format="png" for lossless. full_page=True captures the whole scrollable page.

Waiting

wait_for_selector, wait_for_timeout

wait_for_selector returns reached=true when the requested state is reached; element_present reports whether an element handle still exists (it is normally false after successful hidden / detached waits).

Advanced

evaluate — run arbitrary JavaScript in the page and return its value. Powerful; use sparingly.

Coordinate mouse

mouse_drag, mouse_move, mouse_click

mouse_drag is intended for sliders, canvas handles and similar coordinate-based controls. With the current firefox-15 patched binary, hold-drag requires a session started with humanize=False.

Focused keyboard

keyboard_down, keyboard_up, keyboard_type

Use keyboard_down / keyboard_up for modifier-key combinations. Always release keys that were explicitly held.

Dialogs and popups

set_dialog_handler, get_dialogs, wait_for_page

Dialogs are handled automatically according to the session policy so they cannot freeze an in-flight action. Popups are adopted into the session without changing the active page.

Cookies and storage state

get_cookies, add_cookies, clear_cookies, save_storage_state

Storage state contains cookies and localStorage. Treat saved files as secrets and resume them with start_session(storage_state_path=...). Files are written via a private temporary file and atomically replaced; on Unix the final mode is 0600.

Frames

list_frames, frame_click, frame_fill, frame_type, frame_get_text, frame_wait_for_selector, frame_query_elements, frame_evaluate, frame_get_html, frame_get_attribute

list_frames returns a unique selector for each top-level iframe. Chain selectors with >>> to address nested iframes.


start_session parameters

Param Default Notes
seed random Reproducible fingerprint when set.
headless true Windows/macOS self-cloak the window.
proxy_server "" socks5://host:1080, http://..., etc. DNS routes via proxy.
proxy_username / proxy_password "" Proxy auth.
timezone "" IANA zone; empty = auto from egress IP.
locale "auto" auto = from egress country, or e.g. en-US.
humanize true Bezier mouse paths + human timing.
profile_dir "" Persistent profile path (enables persistent context).
prep_recaptcha false Pre-seed reCAPTCHA cookies (non-persistent only).
storage_state_path "" JSON file created by save_storage_state; cannot be combined with profile_dir.

Runtime safeguards

The resident server applies hard limits so a single tool call cannot exhaust the browser host or the stdio/MCP channel. Defaults can be changed with environment variables:

  • SPECTRA_MCP_MAX_SESSIONS=8
  • SPECTRA_MCP_MAX_PAGES_PER_SESSION=32
  • SPECTRA_MCP_MAX_TEXT_CHARS=200000
  • SPECTRA_MCP_MAX_ELEMENT_RESULTS=500
  • SPECTRA_MCP_MAX_TIMEOUT_MS=300000
  • SPECTRA_MCP_MAX_DELAY_MS=10000
  • SPECTRA_MCP_MAX_CLICK_COUNT=10
  • SPECTRA_MCP_MAX_MOUSE_STEPS=1000
  • SPECTRA_MCP_MAX_SCREENSHOT_BYTES=10485760
  • SPECTRA_MCP_MAX_SCREENSHOT_PIXELS=50000000
  • SPECTRA_MCP_MAX_EVALUATE_RESULT_BYTES=1048576

Set SPECTRA_MCP_DATA_ROOT to restrict profile_dir, storage-state input, and storage-state output to one filesystem tree. When it is unset, arbitrary local paths remain available for trusted local MCP use.

timeout_ms=0 keeps Playwright's conventional “no timeout” meaning. Negative timeouts and positive values above the configured maximum are rejected. fetch_binary(force=true) is rejected while sessions are active or cleaning up; binary launch/download/cache mutation is serialized with a cross-process lock.


Notes & caveats

  • IP matters. The browser fingerprint is handled; ~90% of captchas that remain are from known/blocked proxy IPs. Use clean residential IPs.
  • First start_session needs network to resolve geo/timezone (and to download the binary if you skipped fetch_binary).
  • Humanized clicks are slower than vanilla Playwright — raise timeout_ms if needed.
  • Coordinate hold-drag requires humanize=False on the current patched Firefox build.
  • File chooser, browser download events, selector drag-and-drop and back navigation are intentionally not exposed because firefox-15 does not support them reliably. Use evaluate-based workflows when appropriate.
  • evaluate runs arbitrary JS — only enable for trusted use.
  • All logging goes to stderr so it never corrupts the stdio JSON-RPC stream.
  • Calls against a single session must be sequential (the natural LLM pattern: the model waits for each tool result before sending the next). Concurrent calls to one session are not supported.

Development checks

The regression suite uses only Python's standard library:

python -m unittest discover -s tests -v
python -m compileall -q src tests

Real-browser integration checks are opt-in because they launch the patched Firefox and may require network access for session geo initialization:

SPECTRA_MCP_RUN_INTEGRATION=1 python -m unittest tests.test_integration -v

License

MIT. The patched Firefox binary is MPL-2.0 (Firefox upstream). This wrapper does not redistribute the binary; it downloads it on demand from the upstream releases.

推荐服务器

Baidu Map

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。

官方
精选
JavaScript
Playwright MCP Server

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。

官方
精选
TypeScript
Audiense Insights MCP Server

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。

官方
精选
本地
TypeScript
Magic Component Platform (MCP)

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。

官方
精选
本地
TypeScript
VeyraX

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。

官方
精选
本地
Kagi MCP Server

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。

官方
精选
Python
graphlit-mcp-server

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。

官方
精选
TypeScript
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

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。

官方
精选
mcp-server-qdrant

mcp-server-qdrant

这个仓库展示了如何为向量搜索引擎 Qdrant 创建一个 MCP (Managed Control Plane) 服务器的示例。

官方
精选