Replit MCP Server
Enables AI assistants to interact with Replit workspaces directly, including managing repls, file operations, environment variables, and deployments without constant user intervention.
README
Replit MCP Server
An MCP (Model Context Protocol) server that enables AI assistants to interact with Replit workspaces directly, without needing an agentic browser or constant user intervention.
Features
- User Management: Get current user, lookup users by ID or username
- Repl Management: List, create, fork, delete, and get detailed repl information
- File Operations: Read, write, create, delete files and directories
- Environment Variables: Manage secrets and environment variables
- Deployments: Get deployment info and publish repls
- Search: Search for content within files
Installation
From Smithery
smithery install replit-workspace --client claude
Manual Installation
- Clone this repository
- Install dependencies:
npm install - Build:
npm run build - Run:
npm start
Configuration
The server requires a REPLIT_TOKEN environment variable containing your Replit connect.sid cookie token.
Getting Your Token
- Log into Replit in your browser
- Open Developer Tools (F12)
- Go to Application > Cookies > replit.com
- Copy the value of
connect.sid
Claude Desktop Configuration
Add to your Claude Desktop config file:
{
"mcpServers": {
"replit": {
"command": "node",
"args": ["/path/to/replit-mcp-server/dist/index.js"],
"env": {
"REPLIT_TOKEN": "your-connect-sid-token"
}
}
}
}
Available Tools (24 Total)
User Operations
| Tool | Description |
|---|---|
get_current_user |
Get info about the authenticated user |
get_user_by_id |
Get user info by numeric ID |
get_user_by_username |
Get user info by username |
Repl Management
| Tool | Description |
|---|---|
list_repls |
List repls owned by the user |
get_repl_by_url |
Get repl info by URL |
get_repl_details |
Get detailed repl info (comments, multiplayers, tags, stats) |
set_active_repl |
Set the active repl for subsequent operations |
create_repl |
Create a new repl |
fork_repl |
Fork an existing repl |
delete_repl |
Delete a repl (requires confirmation) |
run_repl |
Start a repl |
stop_repl |
Stop a running repl |
File Operations
| Tool | Description |
|---|---|
read_file |
Read file contents |
write_file |
Write content to a file |
list_files |
List files in a directory |
create_file |
Create a new file |
delete_file |
Delete a file |
create_directory |
Create a new directory |
search_files |
Search for content in files |
Environment Variables
| Tool | Description |
|---|---|
get_secrets |
List all environment variables for a repl |
set_secret |
Set an environment variable |
delete_secret |
Delete an environment variable |
Deployments
| Tool | Description |
|---|---|
get_deployment |
Get deployment info for a repl |
create_deployment |
Deploy/publish a repl |
Development
# Install dependencies
npm install
# Run in development mode
npm run dev
# Build
npm run build
# Start production server
npm start
Deployment to Smithery
- Ensure you have a
Dockerfileandsmithery.jsonin your repo - Push to GitHub
- Connect your repository via Smithery dashboard
- Deploy
API Coverage
This MCP server provides comprehensive coverage of Replit's GraphQL API including:
- User queries and lookups
- Repl CRUD operations
- File system operations
- Environment variable management
- Deployment management
- Search functionality
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。