Citesurf MCP
Enables brand visibility monitoring across major AI platforms like ChatGPT, Claude, Gemini, and Perplexity. It allows users to track visibility scores, analyze competitor data, and receive actionable insights to improve AI-generated brand recommendations.
README
@citesurf/mcp
MCP server for Citesurf. AI visibility monitoring.
Check if ChatGPT, Claude, Perplexity, and Gemini recommend any brand. Get visibility scores, sentiment, competitor data, and actionable insights, all from your AI agent.
Install
npx -y @citesurf/mcp
Requirements
- A Citesurf account with an active Plus or Max subscription
- An API key (create one in Dashboard > Settings)
- Prepaid credits for scan operations
Setup
Add to your MCP client config:
Claude Desktop
~/Library/Application Support/Claude/claude_desktop_config.json
{
"mcpServers": {
"citesurf": {
"command": "npx",
"args": ["-y", "@citesurf/mcp"],
"env": {
"CITESURF_API_KEY": "cs_live_..."
}
}
}
}
Cursor
.cursor/mcp.json in your project or global settings
{
"mcpServers": {
"citesurf": {
"command": "npx",
"args": ["-y", "@citesurf/mcp"],
"env": {
"CITESURF_API_KEY": "cs_live_..."
}
}
}
}
Claude Code
claude mcp add citesurf -e CITESURF_API_KEY=cs_live_... -- npx -y @citesurf/mcp
Environment Variables
| Variable | Required | Description |
|---|---|---|
CITESURF_API_KEY |
Yes | Your API key from Dashboard > Settings |
CITESURF_BASE_URL |
No | API base URL (default: https://citesurf.com) |
Tools
Brands
| Tool | Description | Credits |
|---|---|---|
list_brands |
List all monitored brands with latest metrics | 0 |
get_brand |
Get detailed brand info: score, platforms, competitors | 0 |
create_brand |
Start monitoring a brand across all 4 AI platforms | 0 |
update_brand |
Update brand type, category, description, or prompts | 0 |
delete_brand |
Stop monitoring and archive a brand | 0 |
Data
| Tool | Description | Credits |
|---|---|---|
list_scans |
Paginated scan list for a brand | 0 |
get_scan |
Full scan detail with probes and citations | 0 |
get_trends |
Historical scan trends (7, 30, or 90 days) | 0 |
get_prompts |
AI platform probe results grouped by prompt | 0 |
get_personas |
Probe results grouped by persona | 0 |
get_insights |
AI generated recommendations for visibility | 0 |
update_insight |
Dismiss or complete an insight | 0 |
get_site_audit |
Technical audit (robots.txt, llms.txt, schema) | 0 |
get_report |
Comprehensive report with all data in one call | 0 |
get_account |
Plan, credit balance, brand count | 0 |
Scans
| Tool | Description | Credits |
|---|---|---|
trigger_scan |
Trigger new scan for existing brand | 1 |
Each scan costs 1 credit and runs across all 4 platforms (ChatGPT, Claude, Gemini, Perplexity). Reading data never costs credits. Purchase credit packs in the Citesurf dashboard.
Example Usage
> List my monitored brands
> What are the top insights for brand xyz?
> How has my visibility score changed over the last 30 days?
> Show me the latest scan detail for my brand
> What do different personas see when asking about my brand?
> Run a comprehensive report on my brand
> Update my brand's description and monitoring prompts
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。