Citlyze
Read-only access to your Citlyze AI search visibility workspace: visibility scores, tracked prompts, citations, competitor comparison, recommendations, and AI crawler analytics.
README
Citlyze MCP
Connect AI assistants to Citlyze, the AI search visibility platform. Ask questions like "how visible is my brand in AI answers this month?" or "which domains get cited for my tracked prompts?" and get answers straight from your workspace data.
The Citlyze MCP server is a hosted, read-only endpoint:
https://app.citlyze.com/api/mcp
It speaks streamable HTTP and authenticates with a workspace API key sent as a bearer token. Create a key at app.citlyze.com/workspace-settings (requires a plan with API access).
Tools
| Tool | What it returns |
|---|---|
get_workspace_overview |
Workspace name, target brand, active prompt/location/engine counts, competitors, latest completed measurement window |
list_prompts |
Tracked prompts with text, intent, tier, and active state |
list_measurement_windows |
Tracking snapshots, newest first |
get_visibility_overview |
Headline AI visibility metrics per brand and engine |
get_prompt_visibility |
Per-engine and per-location metrics for one prompt |
list_citations |
Domains cited in AI answers, with counts and sample URLs |
list_recommendations |
Optimization recommendations, highest priority first |
list_competitor_visibility |
Your brand versus tracked competitors |
list_crawler_events |
Daily AI crawler visits (GPTBot, ClaudeBot, PerplexityBot, and more) |
Every tool is read-only. Nothing in your workspace can be modified through MCP.
Gemini CLI extension
This repository is a Gemini CLI extension. Install it with:
gemini extensions install https://github.com/citlyze/citlyze-mcp
Then export your API key before starting Gemini CLI:
export CITLYZE_API_KEY="aeo_live_..."
If your Gemini CLI version does not expand environment variables in extension headers, run gemini extensions edit citlyze and replace ${CITLYZE_API_KEY} with your key.
Other MCP clients
Setup guides for Claude Code, Claude Desktop, Cursor, Codex, Windsurf, JetBrains, and more are in the Citlyze MCP docs. The short version for any streamable-HTTP client:
{
"url": "https://app.citlyze.com/api/mcp",
"headers": {
"Authorization": "Bearer aeo_live_..."
}
}
For clients that only support stdio servers, bridge with mcp-remote:
{
"command": "npx",
"args": [
"-y",
"mcp-remote",
"https://app.citlyze.com/api/mcp",
"--header",
"Authorization: Bearer aeo_live_..."
]
}
Agent skills
Ready-made skills that use these MCP tools (visibility reports, citation gap analysis, prompt audits, action plans) plus a standalone AEO page audit live in Citlyze/citlyze-skills. They follow the open SKILL.md standard, so they work in Claude Code, Codex, Cursor, Gemini CLI, and any compatible agent.
Support and privacy
- Documentation: https://www.citlyze.com/docs/mcp/overview
- Troubleshooting: https://www.citlyze.com/docs/mcp/troubleshooting
- Privacy policy: https://www.citlyze.com/privacy-policy
- Terms: https://www.citlyze.com/terms-of-service
The MCP server only reads data from the workspace tied to your API key. Requests are rate limited per key.
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。