sightvane-mcp
Enables AI assistants to perform comprehensive SEO and GEO measurements, including site audits, keyword research, ranking tracking, and brand visibility analysis across search engines and generative AI platforms.
README
sightvane-mcp
An MCP server that turns any AI assistant into an SEO + GEO measurement instrument.
Sightvane measures the two ways buyers find you now: classic search (technical site health, keywords, rankings, performance) and generative engines (whether ChatGPT, Claude, Perplexity, and Google AI Overviews mention your brand and cite your pages). This server exposes the full instrument as 16 Model Context Protocol tools, so an assistant like Claude can run complete SEO sessions: crawl a site, research keywords, sample AI-answer panels, and report visibility scores, in one conversation.
Built by Sightvane. New to GEO? Read the plain-language guide.
Why this exists
- Zero fixed cost. The crawler, keyword engine (live autocomplete graph), and assistant-driven GEO sampling need no API keys at all. Optional free/cheap keys unlock PageSpeed, domain authority, SERP snapshots, and multi-engine sampling.
- The assistant IS the answer engine. The claude-session loop lets the assistant answer realistic buyer prompts naturally, record its own answers, and measure the brand mentions inside them. One sampling engine, effectively free.
- Local-first. Your data and keys stay in a local JSON store. Nothing syncs anywhere.
Quickstart
git clone https://github.com/BaseHoss/sightvane-mcp.git
cd sightvane-mcp && npm install
Register with Claude Code:
claude mcp add sightvane -- node /path/to/sightvane-mcp/src/index.js
Or in any MCP client config:
{
"mcpServers": {
"sightvane": { "command": "node", "args": ["/path/to/sightvane-mcp/src/index.js"] }
}
}
Then ask your assistant: "run an SEO session on example.com".
The 16 tools
| Tool | What it does |
|---|---|
sightvane_list_projects / sightvane_create_project |
Manage measured domains (brand + competitors enable share of voice) |
sightvane_run_audit / sightvane_get_audit |
Polite, sitemap-seeded crawl; 30+ technical checks; health score across 9 categories |
sightvane_keyword_ideas |
Long-tail expansion from the live suggest graph with intent classification |
sightvane_track_keywords / sightvane_check_rankings |
Rank-tracking list + live SERP positions (serper.dev key) |
sightvane_pagespeed |
Lighthouse + Core Web Vitals via Google PageSpeed Insights |
sightvane_authority |
Domain authority for up to 100 domains (OpenPageRank, free key) |
sightvane_serp |
Live SERP snapshot: organic top 20, People Also Ask, related |
sightvane_geo_generate_panel / sightvane_geo_get_panel |
Funnel-staged buyer-question panels for AI-visibility sampling |
sightvane_geo_record |
Record an answer-engine response; extracts mentions, citations, position, sentiment |
sightvane_geo_sample |
Sample configured engine APIs (OpenAI, Anthropic, Perplexity, Gemini) |
sightvane_geo_report |
Visibility score, mention/citation rates, share of voice, per-stage and per-engine breakdowns |
sightvane_recommendations |
Prioritized action plan from the latest audit + visibility report |
The honest-sampling rule
GEO numbers are only meaningful if the sampling is unbiased. When an assistant answers panel
prompts for sightvane_geo_record, it must answer exactly as it would for any user, never
deliberately mentioning the measured brand. A flattering panel is a false map.
Optional keys (environment or the Sightvane app's Settings)
All engines degrade gracefully with zero keys. Optional: Google PageSpeed, OpenPageRank (free), serper.dev (free tier), OpenAI / Anthropic / Perplexity / Gemini for multi-engine GEO sampling.
Data lands in ./data by default; set SIGHTVANE_DATA to point elsewhere (for example, at
the Sightvane dashboard's data directory so results appear there live).
License
MIT
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。