codaveri-mcp-server
MCP server for executing code in various languages via the Codaveri API.
README
Codaveri MCP Server
This is a Model-Context-Protocol (MCP) server for the Codaveri API, allowing you to execute code in various languages.
Installation
-
Clone the repository:
git clone https://github.com/satviksinha/codaveri-mcp-server.git -
Install the dependencies:
npm install
Configuration
- Create a
.env.development.localfile in the root of the project. - Add your Codaveri API key to the file:
API_KEY=<your_codaveri_api_key> CODAVERI_API_BASE_URL=<codaveri-url>
Using this MCP server from any repo
When you run the codaveri MCP server from another repository (your client repo or any working directory), it looks for environment variables in a .env.development.local file in the current working directory.
- Create a
.env.development.localfile in that repo as well, with the same variables:
API_KEY=your_codaveri_api_key
CODAVERI_API_BASE_URL=https://staging.codaveri.com
Notes:
- The file must be placed in the repo where you execute the
codavericommand (because dotenv loads from the current working directory). - Alternatively, you can export these variables in your shell environment instead of using the file.
Building the Server
To build the server, run the following command:
npm run build
This will compile the TypeScript code into JavaScript and place it in the build directory.
Running the Server
You can run the server locally using npm link:
-
Link the package to make the
codavericommand available globally:npm link -
Now you can run the server by simply typing
codaveriin your terminal.
Client Integration
To use this server in an MCP client, you need to configure the client to connect to the codaveri command.
Here is an example of how you might configure your MCP client:
{
"mcpServers": {
"codaveri": {
"command": "codaveri"
}
}
}
executeCode Tool
This server provides a single tool, executeCode.
Description
Executes a given code snippet in a specified language and returns the output.
Parameters
code(string, required): The code to be executed.language(string, required): The programming language of the code. Supported languages are:pythonjavascriptjavaccpptypescriptgorustcsharp
Example Usage in an MCP Client
executeCode(code="print('Hello, world!')", language="python")
Example Output
The tool will return the standard output of the executed code.
{
"content": [
{
"type": "text",
"text": "Hello, world!\\n"
}
]
}
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。
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。
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。
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。
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。
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。
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。
mcp-server-qdrant
这个仓库展示了如何为向量搜索引擎 Qdrant 创建一个 MCP (Managed Control Plane) 服务器的示例。