
Sequa AI
Stop stitching context for Copilot and Cursor. With Sequa MCP, your AI tools know your entire codebase and docs out of the box.
README
Sequa MCP
This repository is the entry point for using Sequa via the Model Context Protocol (MCP). If you arrived here looking to "add Sequa as an MCP server" to Cursor, Claude, Windsurf, VSCode, Cline, Highlight, Augment, or any other MCP‑capable client — you are in the right place.
It gives you a single drop‑in command that bridges STDIO/command MCP transports used by many IDEs today with Sequa’s native streamable HTTP MCP endpoint.
🧱 Prerequisites (Read First!)
Before you configure any AI agent:
- Create / sign in to your Sequa account at https://app.sequa.ai/login.
- Setup a Project inside the Sequa app.
- Inside that project, locate the MCP Setup URLs and select the transport your AI agent supports.
- Copy the URL or configuration and install it in your client.
❗ If you skip project creation the MCP server will refuse connections — the proxy can launch but you will receive auth / project errors.
🤔 What is Sequa?
Sequa is a Contextual Knowledge Engine that unifies code, documentation and more across multiple repositories and continuously streams that context to any LLM‑powered agent. By injecting deep, current project knowledge, Sequa enables assistants to:
- Execute architecture aware & cross‑repo tasks
- Understand project goals and state
- Generate more accurate production ready code
- Centralize AI coding rules and best practices
🚀 Quick Start (Proxy Launch)
NPX (most common)
npx -y @sequa-ai/sequa-mcp@latest https://mcp.sequa.ai/v1/setup-code-assistant
Replace the URL if you use an endpoint from the specific project
🔌 IDE / Tool Configuration
Cursor (~/.cursor/mcp.json
)
{
"mcpServers": {
"sequa": {
"url": "https://mcp.sequa.ai/v1/setup-code-assistant"
}
}
}
Claude Desktop (Settings → Developer → Edit Config)
{
"mcpServers": {
"sequa": {
"command": "npx",
"args": [
"-y",
"@sequa-ai/sequa-mcp@latest",
"https://mcp.sequa.ai/v1/setup-code-assistant"
]
}
}
}
Windsurf (~/.codeium/windsurf/mcp_config.json
)
{
"mcpServers": {
"sequa": {
"command": "npx",
"args": [
"-y",
"@sequa-ai/sequa-mcp@latest",
"https://mcp.sequa.ai/v1/setup-code-assistant"
]
}
}
}
VS Code (.vscode/mcp.json
)
{
"servers": {
"sequa": {
"command": "npx",
"args": [
"-y",
"@sequa-ai/sequa-mcp@latest",
"https://mcp.sequa.ai/v1/setup-code-assistant"
]
}
}
}
Cline / Claude Dev Tools (cline_mcp_settings.json
)
{
"mcpServers": {
"sequa": {
"command": "npx",
"args": [
"-y",
"@sequa-ai/sequa-mcp@latest",
"https://mcp.sequa.ai/v1/setup-code-assistant"
],
"disabled": false,
"autoApprove": []
}
}
}
Highlight AI (GUI → Plugins → Custom Plugin → Add using a command)
npx -y @sequa-ai/sequa-mcp@latest https://mcp.sequa.ai/v1/setup-code-assistant
Augment Code
npx -y @sequa-ai/sequa-mcp@latest https://mcp.sequa.ai/v1/setup-code-assistant
Or augment_config.json
:
{
"mcpServers": {
"sequa": {
"command": "npx",
"args": [
"-y",
"@sequa-ai/sequa-mcp@latest",
"https://mcp.sequa.ai/v1/setup-code-assistant"
]
}
}
}
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。