- ✓Open-source license (MIT)
- ✓Actively maintained (<30d)
- ✓Documented (README)
- !No description
claude mcp add dokploy -- docker run -i --rm //dokploy.example.com{
"mcpServers": {
"dokploy": {
"command": "docker",
"args": ["run", "-i", "--rm", "//dokploy.example.com"],
"env": {
"DOKPLOY_URL": "<dokploy_url>",
"DOKPLOY_API_KEY": "<dokploy_api_key>"
}
}
}
}DOKPLOY_URLDOKPLOY_API_KEYResumen de MCP Servers
# dokploy-mcp-server
[](https://www.npmjs.com/package/dokploy-mcp-server)
A comprehensive [Model Context Protocol (MCP)](https://modelcontextprotocol.io/) server for [Dokploy](https://dokploy.com/) - the open-source, self-hosted PaaS. Deploy apps, manage containers, databases, domains, and servers through AI assistants like Claude.
## Why This Server?
The [official Dokploy MCP](https://github.com/Dokploy/mcp) generates one tool per API endpoint — at the 0.29.14 measurement below, 546 of them, exactly matching the 546 paths in Dokploy's OpenAPI spec at that version. (Dokploy v0.30.2 ships 597 paths; the figures in this section are left at their measured values rather than re-estimated.) Coverage is complete, and every one of those schemas loads into the model's context before you ask your first question.
This server hand-curates the same API into **27 tools** (one per category, each taking an `action` enum), covering the deploy-and-operate surface most self-hosters use daily.
### Context cost
| | Official `@dokploy/mcp` | This server |
| ---------------------------------- | ----------------------- | ---------------- |
| Tools exposed | 546 | 22 (21 + `info`) |
| `tools/list` schema payload | 294,957 bytes | 34,528 bytes |
| Approximate tokens loaded up front | **~74k** | **~8.6k** |
| Median tool schema | 388 bytes | 1,131 bytes |
Measured 2026-08-08 against `@dokploy/mcp@0.29.14` and `dokploy-mcp-server@1.8.2`, by starting each server, calling `tools/list`, and counting the serialized schema bytes (divided by 4 for a rough token estimate).
Since that measurement this server grew to 27 tools tracking Dokploy v0.30.2. Measured the same way — live `tools/list` over stdio — it now exposes 28 tools (27 + `info`) for **48,452 bytes (~12.1k tokens)**. The official server has not been re-measured against 0.30.2, so the table above is left at the paired 0.29.14 figures rather than mixing a new number for one side with an old one for the other.
On a 200k-token context window, the official server spends more than a third of it before you ask anything. The larger median schema here is deliberate: descriptions carry the workflow knowledge that prevents failed calls, such as which service id pairs with which `databaseType`.
### Feature Comparison
Tool counts for the official server are per category, taken from its live `tools/list`.
| Category | Official MCP | This Server |
| ------------------- | ---------------------- | ----------------------------- |
| Projects | 9 tools | 1 tool (6 actions) |
| Applications | 31 tools | 1 tool (23 actions) |
| Compose | 31 tools | 1 tool (21 actions) |
| Deployments | 9 tools | 1 tool (5 actions) |
| Docker | 12 tools | 1 tool (17 actions) |
| Docker Volumes | n/a (new in 0.30.2) | 1 tool (8 actions) |
| Docker Images | n/a (new in 0.30.2) | 1 tool (3 actions) |
| Networks | n/a (new in 0.30.2) | 1 tool (8 actions) |
| Overview | n/a (new in 0.30.2) | 1 tool (3 actions) |
| DNS Providers | n/a (new in 0.30.2) | 1 tool (11 actions) |
| Vault Providers | n/a (new in 0.30.2) | 1 tool (7 actions) |
| Domains | 9 tools | 1 tool (9 actions) |
| Redirects | 4 tools | 1 tool (4 actions) |
| Servers | 18 tools | 1 tool (8 actions) |
| Settings | 54 tools | 1 tool (5 actions) |
| Databases | 94 tools (6 engines) | 1 tool (17 actions, all 6 DB) |
| Backups | 12 tools | 1 tool (6 actions) |
| Volume Backups | 6 tools | 1 tool (6 actions) |
| Preview Deployments | 4 tools | 1 tool (4 actions) |
| Schedules | 6 tools | 1 tool (6 actions) |
| Audit Log | 1 tool | 1 tool (1 action) |
| Environments | 7 tools | 1 tool (6 actions) |
| Infrastructure | 13 tools (ports+certs) | 1 tool (8 actions) |
| Mounts | 6 tools | 1 tool (6 actions) |
| SSH Keys | 7 tools | 1 tool (6 actions) |
| Registries | 7 tools | 1 tool (7 actions) |
| Destinations | 6 tools | 1 tool (6 actions) |
| **Total** | **346 tools** | **27 tools** |
Key advantages:
- **Minimal token usage** - 346 endpoints' worth of surface in 27 tools, for roughly an eighth of the context
- **Unified database tool** - One tool handles all 6 database types (postgres, mysql, mariadb, mongo, redis, libsql) via `dbType` + `action` params
- **Curated descriptions** - Each tool documents which parameters pair with which action, so calls succeed on the first try
- **Action-based design** - Each tool has an `action` enum parameter; other params are optional based on action
### When to use the official server instead
The official server covers 49 categories to this server's 27. Of its 546 tools, 346 fall inside the categories above; the remaining 200 have no equivalent here:
- **Notifications** (41 tools) - email, Slack, Discord, Telegram, Gotify webhooks
- **Users, organizations, roles, SSO** (64 tools) - user management, organizations, custom roles, SSO, SCIM, forwardAuth
- **Git providers** (32 tools) - GitHub, GitLab, Gitea, Bitbucket app configuration
- **AI providers** (14 tools) - Dokploy's own LLM integration for log analysis and compose generation
- **Cluster and Swarm** (8 tools), **patch** (12), **tags** (8), **rollback** (2), **admin** (1)
- **Dokploy Cloud commercial features** (18 tools) - Stripe billing, license keys, whitelabeling
If your workflow needs any of those, use the official server, or run both.
## Installation
### Claude Desktop / Claude Code
Add to your MCP configuration:
```json
{
"mcpServers": {
"dokploy": {
"command": "npx",
"args": ["-y", "dokploy-mcp-server"],
"env": {
"DOKPLOY_URL": "https://dokploy.example.com",
"DOKPLOY_API_KEY": "your-api-key"
}
}
}
}
```
### Cursor
Add to `.cursor/mcp.json`:
```json
{
"mcpServers": {
"dokploy": {
"command": "npx",
"args": ["-y", "dokploy-mcp-server"],
"env": {
"DOKPLOY_URL": "https://dokploy.example.com",
"DOKPLOY_API_KEY": "your-api-key"
}
}
}
}
```
### Docker
```bash
docker run -e DOKPLOY_URL=https://dokploy.example.com \
-e DOKPLOY_API_KEY=your-api-key \
-e TRANSPORT_TYPE=httpStream \
-p 3000:3000 \
dokploy-mcp-server
```
## Environment Variables
| Variable | Required | Default | Description |
| ----------------- | -------- | --------- | ---------------------------------------- |
| `DOKPLOY_URL` | Yes | - | Your Dokploy instance URL |
| `DOKPLOY_API_KEY` | Yes | - | API key from Dokploy Settings > API Keys |
| `TRANSPORT_TYPE` | No | `stdio` | Transport mode: `stdio` or `httpStream` |
| `PORT` | No | `3000` | HTTP port (httpStream mode only) |
| `HOST` | No | `0.0.0.0` | HTTP host (httpStream mode only) |
## Tools (27)
Each tool uses an `action` enum to select the operation. Parameters are optional and used based on the chosen action.
### `dokploy_project` (6 actions)
Actions: `list | get | create | update | remove | duplicate`
Manage projects. `list` and `get` return nested environments with their applications, composes, and databases (with names, IDs, and status), so you can discover service IDs without extra calls. `create` requires `name`. `update` requires `projectId` + fields. `remove` requires `projectId`. `duplicate` requires `sourceEnvironmentId` + `name`.
**Reading the status label.** Dokploy's status enum is `idle | running | done | error`, rendered as `[IDLE]`, `[RUNNING]`, `[DONE]`, `[ERROR]`. It describes the **deployment**, not live container state — `[DONE]` means the last deploy finished, and `[IDLE]` means nothing has run, neither of which implies a container is up right now. Check `dokploy_docker` `getContainers` for what is actually running.
### `dokploy_application` (23 actions)
Actions: `create | get | update | move | deploy | start | stop | delete | markRunning | refreshToken | cleanQueues | killBuild | cancelDeployment | reload | saveEnvironment | setEnvVars | getEnvKeys | getEnvValuesUnsafe | saveBuildType | traefikConfig | readMonitoring | readLogs | search`
Full application lifecycle. Most actions require `applicationId`. `create` requires `name` + `environmentId`. `deploy` supports `redeploy` flag. `readMonitoring` requires `appName`. `search` finds applications by `q`/`name`/`appName`/`repository`/`owner`/`dockerImage`/`projectId`/`environmentId`, with `limit` (1–100, default 20) and `offset`; the reply flags a truncated page.
**Env handling.** `get` returns a masked env summary (count only) — never the values. Three actions cover the rest:
- `setEnvVars` — granular merge inside the server. Pass `set` (KEY=VALUE per line, upsert) and/or `unset` (array of KEY names). The read-modify-write happens server-side; the tool result is a masked confirmation listing only the changed key names. No untouched-key values ever enter the transcriptLo que la gente pregunta sobre dokploy-mcp-server
¿Qué es sapientsai/dokploy-mcp-server?
+
sapientsai/dokploy-mcp-server es mcp servers para el ecosistema de Claude AI con 2 estrellas en GitHub.
¿Cómo se instala dokploy-mcp-server?
+
Puedes instalar dokploy-mcp-server clonando el repositorio (https://github.com/sapientsai/dokploy-mcp-server) o siguiendo las instrucciones del README en GitHub. ClaudeWave también te ofrece bloques de instalación rápida en esta misma página.
¿Es seguro usar sapientsai/dokploy-mcp-server?
+
Nuestro agente de seguridad ha analizado sapientsai/dokploy-mcp-server y le ha asignado un Trust Score de 77/100 (tier: Trusted). Revisa el desglose completo de comprobaciones superadas y flags en esta página.
¿Quién mantiene sapientsai/dokploy-mcp-server?
+
sapientsai/dokploy-mcp-server es mantenido por sapientsai. La última actividad registrada en GitHub es del 2026-08-24, con 4 issues abiertos.
¿Hay alternativas a dokploy-mcp-server?
+
Sí. En ClaudeWave puedes explorar mcp servers similares en /categories/mcp, ordenados por popularidad o actividad reciente.
Despliega dokploy-mcp-server en tu cloud
Lleva este repo a producción en minutos. Cada plataforma genera su propio entorno con variables de entorno editables.
¿Mantienes este repo? Añade un badge a tu README
Pega el badge en tu README de GitHub para mostrar que está auditado por ClaudeWave. Cada badge enlaza de vuelta a esta página y muestra el Trust Score actual.
[](https://claudewave.com/repo/sapientsai-dokploy-mcp-server)<a href="https://claudewave.com/repo/sapientsai-dokploy-mcp-server"><img src="https://claudewave.com/api/badge/sapientsai-dokploy-mcp-server" alt="Featured on ClaudeWave: sapientsai/dokploy-mcp-server" width="320" height="64" /></a>Más MCP Servers
Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.
User-friendly AI Interface (Supports Ollama, OpenAI API, ...)
An open-source AI agent that brings the power of Gemini directly into your terminal.
Real-time global intelligence dashboard. AI-powered news aggregation, geopolitical monitoring, and infrastructure tracking in a unified situational awareness interface
The fastest path to AI-powered full stack observability, even for lean teams.
🕷️ An adaptive Web Scraping framework that handles everything from a single request to a full-scale crawl!