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.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.