Ploi.io MCP Server
Enables managing Ploi.io servers, sites, databases, and Docker containers through the Ploi API, supporting both local stdio and remote Cloudflare Worker deployments with multi-tenant authentication.
README
Ploi.io MCP Server
MCP server for Ploi.io account management using the Ploi API.
It ships with two transports that share the same tools:
- stdio — run locally, launched by your MCP client. Authenticates with a
PLOI_API_TOKENfrom the environment (src/index.ts). - Cloudflare Worker — remote, multi-tenant Streamable HTTP server. Each
caller supplies their own Ploi token as
Authorization: Bearer <token>; nothing is stored on the Worker (src/worker.ts). See Deploy to Cloudflare and Use with Poke.
Setup (local stdio)
npm install
npm run build
Create a Ploi API token from your Ploi profile, then configure your MCP client to launch this server with the token in the environment:
{
"mcpServers": {
"ploi": {
"command": "node",
"args": ["/path/to/ploi-mcp-server/dist/index.js"],
"env": {
"PLOI_API_TOKEN": "your-ploi-api-token"
}
}
}
}
Optional environment variables:
PLOI_API_BASE_URL: override the API base URL. Defaults tohttps://ploi.io/api.PLOI_USER_AGENT: override the user agent sent to Ploi. Defaults toploi-mcp-server/1.0.0.
Deploy to Cloudflare
The Worker exposes the same tools over the MCP Streamable HTTP transport at
/mcp (legacy SSE at /sse), backed by a Durable Object via the
agents SDK. GET / is a health
check.
Authentication is multi-tenant and pass-through. The Worker stores no
Ploi credentials. Every request must carry the caller's own Ploi token as
Authorization: Bearer <token>; that token is bound to the MCP session and used
for all Ploi API calls in that session. Requests without a bearer token get
401.
Deploy
npm install
npx wrangler login
npm run deploy # deploys to https://ploi-mcp-server.<subdomain>.workers.dev
No secrets to configure. Optional PLOI_API_BASE_URL / PLOI_USER_AGENT
overrides can be added under vars in wrangler.jsonc.
Local development
npm run dev # local worker at http://localhost:8787
Pass a token per request, e.g.:
curl -s http://localhost:8787/health
curl -s -X POST http://localhost:8787/mcp \
-H "Authorization: Bearer <your-ploi-token>" \
-H "Content-Type: application/json" \
-H "Accept: application/json, text/event-stream" \
-d '{"jsonrpc":"2.0","id":1,"method":"initialize","params":{"protocolVersion":"2025-06-18","capabilities":{},"clientInfo":{"name":"dev","version":"0"}}}'
After editing wrangler.jsonc, run npm run cf-typegen (wrangler types) and
typecheck the Worker with npm run typecheck:worker.
Use with Poke
Poke sends the integration's API key as
Authorization: Bearer <key> on every request — so each user simply pastes
their own Ploi API token as the key, and the Worker uses it for that user.
-
Deploy the Worker (above) and note its URL.
-
In Poke, add an MCP integration:
- URL:
https://ploi-mcp-server.<subdomain>.workers.dev/mcp - API Key: the user's Ploi API token (from the Ploi profile page)
Or via CLI:
npx poke@latest mcp add \ https://ploi-mcp-server.<subdomain>.workers.dev/mcp \ -n "Ploi" -k "<user-ploi-api-token>" - URL:
Each Poke user's token only ever touches their own session; the Worker keeps no copy. If a request arrives without a token, or the token is rejected by Ploi, the corresponding tool call returns an error.
Tools
Servers
ploi_list_serversploi_get_serverploi_create_serverploi_create_custom_serverploi_start_custom_server_installationploi_update_serverploi_restart_serverploi_delete_server
Sites
ploi_list_sitesploi_get_siteploi_create_siteploi_update_siteploi_delete_siteploi_deploy_siteploi_get_site_nginx_configurationploi_update_site_nginx_configuration
Databases
ploi_list_databasesploi_get_databaseploi_duplicate_databaseploi_forget_database
Docker containers / services
ploi_list_containersploi_get_containerploi_create_containerploi_update_containerploi_start_containerploi_stop_containerploi_restart_containerploi_delete_container
Ploi exposes documented up and down endpoints for Docker containers. The
restart tool queues a shutdown followed by a startup using those endpoints.
Account helpers
ploi_list_server_providersploi_get_server_providerploi_list_backup_configurationsploi_get_ip_addresses
Destructive tools require a confirm: true argument.
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。