Can my agent scale my Dokku processes automatically?

Yes. Use the 'ps_scale' tool. You can specify the application name and the target replica count for processes like 'web' or 'worker'. The agent will manipulate the explicit counts within your Dokku cluster instantly.

How do I update environment variables via chat?

Use the 'set_config' tool. Provide the app name, key, and value. The agent will inject the pair into the Docker environment mapping, which typically triggers a rolling deployment to apply the new configuration safely.

Can I run database migrations through the agent?

Absolutely. Use the 'run_command' tool. It boots an ephemeral isolated container cloning your production image, allowing you to run maintenance commands like 'rake db:migrate' or custom scripts without affecting live traffic.

Dokku MCP Server for CrewAI 10 tools — connect in under 2 minutes

Name: Dokku
Availability: InStock
Author: Vinkius

docs.crewai.com/mcp/overview

Built by Vinkius GDPR 10 Tools Framework

Connect your CrewAI agents to Dokku through Vinkius, pass the Edge URL in the `mcps` parameter and every Dokku tool is auto-discovered at runtime. No credentials to manage, no infrastructure to maintain.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

from crewai import Agent, Task, Crew

agent = Agent(
    role="Dokku Specialist",
    goal="Help users interact with Dokku effectively",
    backstory=(
        "You are an expert at leveraging Dokku tools "
        "for automation and data analysis."
    ),
    # Your Vinkius token. get it at cloud.vinkius.com
    mcps=["https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"],
)

task = Task(
    description=(
        "Explore all available tools in Dokku "
        "and summarize their capabilities."
    ),
    agent=agent,
    expected_output=(
        "A detailed summary of 10 available tools "
        "and what they can do."
    ),
)

crew = Crew(agents=[agent], tasks=[task])
result = crew.kickoff()
print(result)

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About Dokku MCP Server

Connect your Dokku instance to any AI agent and take full control of your self-hosted PaaS and container orchestration through natural conversation.

When paired with CrewAI, Dokku becomes a first-class tool in your multi-agent workflows. Each agent in the crew can call Dokku tools autonomously, one agent queries data, another analyzes results, a third compiles reports, all orchestrated through Vinkius with zero configuration overhead.

What you can do

Application Lifecycle — List all managed apps and retrieve the overarching directory of deployments on your own infrastructure bypassing standard PaaS fees
Provisioning & Deallocation — Barely instantiate new application repositories or irreversibly dismantle all bound containers and DNS routing records
Environment Auditing — Retrieve the exact .env dictionary bound dynamically via the config plugin to observe runtime inputs and SQL credentials
Configuration Mutation — Inject or remove sensitive environment variables securely, triggering rolling app deployments natively across your cluster
Process Scaling — Manipulate explicit replica counts dynamically, determining whether web or worker containers spool up to meet demand
Live Log Streaming — Pull precise system execution tails to investigate explicit request stack traces and crashing node backtraces without SSH
One-off Executions — Launch raw commands inside ephemeral isolated containers for maintenance tasks like DB migrations or custom scripts

The Dokku MCP Server exposes 10 tools through the Vinkius. Connect it to CrewAI in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect Dokku to CrewAI via MCP

Follow these steps to integrate the Dokku MCP Server with CrewAI.

Install CrewAI

Run pip install crewai

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token from cloud.vinkius.com

Customize the agent

Adjust the role, goal, and backstory to fit your use case

Run the crew

Run python crew.py. CrewAI auto-discovers 10 tools from Dokku

Why Use CrewAI with the Dokku MCP Server

CrewAI Multi-Agent Orchestration Framework provides unique advantages when paired with Dokku through the Model Context Protocol.

Multi-agent collaboration lets you decompose complex workflows into specialized roles, one agent researches, another analyzes, a third generates reports, each with access to MCP tools

CrewAI's native MCP integration requires zero adapter code: pass Vinkius Edge URL directly in the `mcps` parameter and agents auto-discover every available tool at runtime

Built-in task delegation and shared memory mean agents can pass context between steps without manual state management, enabling multi-hop reasoning across tool calls

Sequential and hierarchical crew patterns map naturally to real-world workflows: enumerate subdomains → analyze DNS history → check WHOIS records → compile findings into actionable reports

Dokku + CrewAI Use Cases

Practical scenarios where CrewAI combined with the Dokku MCP Server delivers measurable value.

Automated multi-step research: a reconnaissance agent queries Dokku for raw data, then a second analyst agent cross-references findings and flags anomalies. all without human handoff

Scheduled intelligence reports: set up a crew that periodically queries Dokku, analyzes trends over time, and generates executive briefings in markdown or PDF format

Multi-source enrichment pipelines: chain Dokku tools with other MCP servers in the same crew, letting agents correlate data across multiple providers in a single workflow

Compliance and audit automation: a compliance agent queries Dokku against predefined policy rules, generates deviation reports, and routes findings to the appropriate team

Dokku MCP Tools for CrewAI (10)

These 10 tools become available when you connect Dokku to CrewAI via MCP:

create_app

Performs the structural network allocations setting up reverse-proxy hooks (Nginx/Traefik) preceding the actual codebase transfer. Provision a root App boundary wrapper on the Dokku VM

destroy_app

Instantly shuts down bound running docker containers orchestrating web/worker traffic, detaches volumes seamlessly, and removes explicit DNS routing records from the local VHOST mappings. Deallocate an App and dismantle all bound containers completely

get_logs

Bypasses SSH to investigate explicit request stack traces, crashing node backtraces, or slow SQL queries happening inside the closed containers. Stream Dokku Application Docker stdout and stderr logs

list_apps

Determines exactly which Docker containers are orchestrated internally by Dokku Core scaling plugins. List self-hosted Git-push Apps deployed via Dokku

list_config

env` or `ENV` dictionary bound dynamically via the `dokku config` plugin. Used strictly to observe runtime inputs (SQL credentials, external REST API tokens, Node_ENV bindings) governing app execution. Extract internal Environment variables loaded into the App

ps_restart

Dokku tears down old running docker processes spanning the App UUID, allocating updated dynamic ports tied via standard proxies (Nginx), ensuring zero downtime deploys if multiple replicas are alive. Bounce the application container dynamically

ps_scale

Determines whether the "web" container spins zero replicas (suspension), or if "worker" background tasks spool up to 10 endpoints. Scale structural internal application containers

run_command

Boots a brand new isolated Docker container cloning the production image layers for a single execution cycle. Useful for running `rake db:migrate`, `npm run script` safely disconnected from web traffic. Launch a raw one-off command inside an ephemeral container

set_config

Triggers a mandatory rolling app deployment unless the `--no-restart` daemon flag applies natively to the process. Critical for updating expired API auth tokens. Inject Environment Variables into a running Dokku Application

unset_config

Immediately triggers the executing Docker cluster to orchestrate a rapid replacement cycle to strip out the revoked value. Removes stale credentials safely. Remove sensitive Environment Variables disrupting App config

Example Prompts for Dokku in CrewAI

Ready-to-use prompts you can give your CrewAI agent to start working with Dokku immediately.

"List all apps on my Dokku host"

"Scale the 'web' process of app 'api-server' to 3 replicas"

"Get the last 50 lines of logs for 'frontend-web'"

Troubleshooting Dokku MCP Server with CrewAI

Common issues when connecting Dokku to CrewAI through the Vinkius, and how to resolve them.

MCP tools not discovered

Ensure the Edge URL is correct. CrewAI connects lazily when the crew starts. check console output.

Agent not using tools

Make the task description specific. Instead of "do something", say "Use the available tools to list contacts".

Timeout errors

CrewAI has a 10s connection timeout by default. Ensure your network can reach the Edge URL.

Rate limiting or 429 errors

Vinkius enforces per-token rate limits. Check your subscription tier and request quota in the dashboard. Upgrade if you need higher throughput.

Dokku + CrewAI FAQ

Common questions about integrating Dokku MCP Server with CrewAI.

How does CrewAI discover and connect to MCP tools?

CrewAI connects to MCP servers lazily. when the crew starts, each agent resolves its MCP URLs and fetches the tool catalog via the standard tools/list method. This means tools are always fresh and reflect the server's current capabilities. No tool schemas need to be hardcoded.

Can different agents in the same crew use different MCP servers?

Yes. Each agent has its own mcps list, so you can assign specific servers to specific roles. For example, a reconnaissance agent might use a domain intelligence server while an analysis agent uses a vulnerability database server.

What happens when an MCP tool call fails during a crew run?

CrewAI wraps tool failures as context for the agent. The LLM receives the error message and can decide to retry with different parameters, fall back to a different tool, or mark the task as partially complete. This resilience is critical for production workflows.

Can CrewAI agents call multiple MCP tools in parallel?

CrewAI agents execute tool calls sequentially within a single reasoning step. However, you can run multiple agents in parallel using process=Process.parallel, each calling different MCP tools concurrently. This is ideal for workflows where separate data sources need to be queried simultaneously.

Can I run CrewAI crews on a schedule (cron)?

Yes. CrewAI crews are standard Python scripts, so you can invoke them via cron, Airflow, Celery, or any task scheduler. The crew.kickoff() method runs synchronously by default, making it straightforward to integrate into existing pipelines.