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
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.