Lets LLMs execute Python code within a specified Conda environment.
接入配置
选择客户端,复制配置,再按项目文档补齐环境变量。
claude mcp add code-executor --env CODE_STORAGE_DIR='<CODE_STORAGE_DIR>' --env CONDA_ENV_NAME='<CONDA_ENV_NAME>' -- node /path/to/mcp_code_executor/build/index.js~/.codex/config.toml
[mcp_servers.code-executor]
command = "node"
args = ["/path/to/mcp_code_executor/build/index.js"]
env = { CODE_STORAGE_DIR = "<CODE_STORAGE_DIR>", CONDA_ENV_NAME = "<CONDA_ENV_NAME>" }
# codex mcp add code-executor --env CODE_STORAGE_DIR='<CODE_STORAGE_DIR>' --env CONDA_ENV_NAME='<CONDA_ENV_NAME>' -- node /path/to/mcp_code_executor/build/index.js~/.cursor/mcp.json
{
"mcpServers": {
"code-executor": {
"command": "node",
"args": [
"/path/to/mcp_code_executor/build/index.js"
],
"env": {
"CODE_STORAGE_DIR": "<CODE_STORAGE_DIR>",
"CONDA_ENV_NAME": "<CONDA_ENV_NAME>"
}
}
}
}.vscode/mcp.json
{
"servers": {
"code-executor": {
"type": "stdio",
"command": "node",
"args": [
"/path/to/mcp_code_executor/build/index.js"
],
"env": {
"CODE_STORAGE_DIR": "<CODE_STORAGE_DIR>",
"CONDA_ENV_NAME": "<CONDA_ENV_NAME>"
}
}
}
}~/.gemini/settings.json
{
"mcpServers": {
"code-executor": {
"command": "node",
"args": [
"/path/to/mcp_code_executor/build/index.js"
],
"env": {
"CODE_STORAGE_DIR": "<CODE_STORAGE_DIR>",
"CONDA_ENV_NAME": "<CONDA_ENV_NAME>"
}
}
}
}claude_desktop_config.json
{
"mcpServers": {
"code-executor": {
"command": "node",
"args": [
"/path/to/mcp_code_executor/build/index.js"
],
"env": {
"CODE_STORAGE_DIR": "<CODE_STORAGE_DIR>",
"CONDA_ENV_NAME": "<CONDA_ENV_NAME>"
}
}
}
}.trae/mcp.json
{
"mcpServers": {
"code-executor": {
"command": "node",
"args": [
"/path/to/mcp_code_executor/build/index.js"
],
"env": {
"CODE_STORAGE_DIR": "<CODE_STORAGE_DIR>",
"CONDA_ENV_NAME": "<CONDA_ENV_NAME>"
}
}
}
}需要的环境变量
CODE_STORAGE_DIRCONDA_ENV_NAME
把占位值换成你自己的密钥;不要把密钥提交到代码仓库。