mcp-teamate-server
About
mcp-teamate-server is a server-side program that provides an HTTP API for MCP Teamate. It runs on the Bun JavaScript runtime and manages data using a local database directory.
Details
- Author
- aokihu
- Downloads
- 119
- Categories
- Other
Jump to
- Provides HTTP API services for MCP Teamate
- Built with the fast Bun all-in-one runtime
- Automatically creates data/ directory for database storage
- Data directory excluded from version control
- Simple two‑command setup and run
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
mcp-teamate-serverCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
Install dependencies with bun install, then start the server with bun run src/server/index.ts. The data/ directory is created automatically on first run and must be maintained per environment.
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"mcp-teamate-server": {
"mcp-teamate-server": {
"command": "bun",
"args": [
"run",
"src/server/index.ts"
]
}
}
}
}
McpServers
{
"mcp-teamate-server": {
"command": "bun",
"args": [
"run",
"src/server/index.ts"
]
}
}
mcp-teamate-server
MCP Teamate HTTP API Server
项目说明
这是一个为MCP Teamate提供HTTP API服务的服务器端程序。
目录结构
src/ # 源代码目录
server/ # 服务器端代码
data/ # 数据目录(自动创建,不包含在版本控制中)
tests/ # 测试文件目录
安装依赖
bun install
运行
bun run src/server/index.ts
测试
bun test
注意事项
- data 目录用于存储数据库文件,会在程序首次运行时自动创建
- 该目录不包含在版本控制中,每个环境需要维护自己的数据
This project was created using bun init in bun v1.2.4. Bun is a fast all-in-one JavaScript runtime.
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.



