Skip to main content
Glama
BasicDeploy MCP Server

BasicDeploy MCP Server

BasicDeploy MCP Server

The persistent runtime your agent deploys to: a database, object storage, a Kafka broker, and a public URL, one MCP call.

An MCP (Model Context Protocol) server that lets AI coding agents (Claude Code, Cursor, and any MCP client) create and manage BasicDeploy containers directly. Every container comes with a PostgreSQL database, S3‑compatible object storage, a Kafka broker, environment variables, and a public HTTPS URL, all provisioned automatically. Your agent can create containers, deploy apps (Node, Python, Go, or Docker, auto‑detected), run commands, read logs, manage Kafka topics, check who it is authenticated as, set always‑on, and share or delete containers.

Quick start

Requires Node.js ≥ 18. No install needed. npx fetches it on demand.

Get an API key at https://basicdeploy.com/api-keys (it looks like bd_…, shown once), then add this to your MCP client:

{
  "mcpServers": {
    "basicdeploy": {
      "command": "npx",
      "args": ["-y", "basicdeploy-mcp@latest"],
      "env": {
        "BASICDEPLOY_API_KEY": "bd_your_api_key",
        "BASICDEPLOY_URL": "https://basicdeploy.com"
      }
    }
  }
}

Claude Code:

claude mcp add basicdeploy \
  --env BASICDEPLOY_API_KEY=bd_your_api_key \
  --env BASICDEPLOY_URL=https://basicdeploy.com \
  -- npx -y basicdeploy-mcp@latest

Claude Code plugin (this repo doubles as a plugin marketplace):

/plugin marketplace add AkaciaNL/basicdeploy-mcp
/plugin install basicdeploy-mcp@basicdeploy

Then set BASICDEPLOY_API_KEY in your environment (the plugin reads it via ${BASICDEPLOY_API_KEY}).

OpenAI Codex CLI:

codex mcp add basicdeploy \
  --env BASICDEPLOY_API_KEY=bd_your_api_key \
  --env BASICDEPLOY_URL=https://basicdeploy.com \
  -- npx -y basicdeploy-mcp@latest

or add it directly to ~/.codex/config.toml:

[mcp_servers.basicdeploy]
command = "npx"
args = ["-y", "basicdeploy-mcp@latest"]
env = { BASICDEPLOY_API_KEY = "bd_your_api_key", BASICDEPLOY_URL = "https://basicdeploy.com" }

Environment variables

Variable

Required

Description

BASICDEPLOY_API_KEY

Yes

Your API key (bd_…). Required to call any tool (the server still starts and lists its tools without it, so clients can introspect it).

BASICDEPLOY_URL

No

API base URL. Defaults to https://basicdeploy.com.

Related MCP server: Dokploy MCP Server

Tools

Tool

Arguments

Description

list_containers

(none)

List your containers: subdomain, status, URL, id, createdAt.

create_container

memoryMb? (256/512/1024/2048), alwaysOn?

Create a container. Database + S3 bucket provisioned automatically. Larger sizes need Pro/Scale; always‑on on Free uses a paid add‑on slot.

get_container

containerId

Full details: URL, status, ports, DB name/user, S3 bucket, volume path.

deploy_app

tarballPath, containerId?

Deploy a .tar/.tar.gz/.tgz/.zip from disk. Unpacks to /workspace, auto‑detects the runtime, and starts the app on :8080. Omit containerId to create a new container; pass one to deploy into an existing container.

exec_command

containerId, command

Run a shell command inside the container; returns output + exit code.

get_logs

containerId, tail? (default 200)

Fetch recent container logs.

set_always_on

containerId, enabled

Turn a container's 24/7 always‑on flag on/off.

wake_container

containerId

Wake a slept container so it serves traffic again.

sleep_container

containerId

Sleep a running container to free memory (wakes on next request).

get_account

(none)

Your plan, container limit (plan + add‑ons), selectable memory sizes, storage limit, and add‑ons.

share_container

containerId, email, expiresInHours?

Share a container with another user by email (they get a sign‑in link). Omit expiresInHours for an unlimited share.

delete_container

containerId

Permanent: destroys the container, its database, and all files.

whoami

(none)

The account this connection is authenticated as (email + id).

get_kafka

(none)

Kafka connection details (SASL/SCRAM): internal + external bootstrap, username/password, consumer‑group prefix, topics, usage and limits. Provisions on first call.

create_topic

label?

Create a Kafka topic (auto‑namespaced under your prefix; optional readable label). Fails if the topic/storage budget is exceeded.

purge_topic

name

Empty a topic you own (deletes its messages, keeps the topic). Restart processing after a mistake.

delete_topic

name

Permanent: delete a topic you own and all its messages.

Runtime

Deployed apps must listen on 0.0.0.0:8080, the port the public URL serves. DATABASE_URL, S3_ENDPOINT / S3_ACCESS_KEY / S3_SECRET_KEY / S3_BUCKET, and KAFKA_BOOTSTRAP / KAFKA_USERNAME / KAFKA_PASSWORD / KAFKA_GROUP_PREFIX are preset in the container environment. Startup output goes to /workspace/deploy.log.

Example prompts

  • "Create a 1GB always‑on container and deploy ./dist/app.tar.gz to it, give me the URL."

  • "Show the last 100 log lines of my blue-fox container."

  • "What plan am I on and how many containers can I run?"

  • "Share my container with teammate@example.com for 24 hours."

License

MIT. BasicDeploy is a product of Akacia (KVK 99629569, Netherlands).

Available Tools

18 tools
create_containerA

Create a new empty BasicDeploy container. A PostgreSQL database and an S3 bucket are provisioned automatically for it. Returns the container's id, subdomain, and public URL. Its public URL is proxied to PORT 8080 inside the container, so whatever you deploy MUST listen on 0.0.0.0:8080 (any other port/binding returns 503). Use deploy_app or exec_command afterwards to put an application in it. Optional memoryMb (256/512/1024/2048) and alwaysOn require the plan/add-ons to allow them (see get_account); larger sizes need Pro/Scale, and always-on on Free consumes a paid add-on slot.

Inputs: alwaysOn, memoryMb. Returns: A BasicDeploy container (non-secret fields).

create_topicA

Create a Kafka topic for the user. The name is auto-namespaced under their prefix; an optional 'label' becomes a readable suffix (sanitized), otherwise it's randomized. Retention, partitions and the per-topic size are fixed by the plan. Fails if the topic count or storage budget is exceeded (see get_kafka / get_account). Returns the full topic name.

Inputs: label. Returns: name

delete_containerA
Destructive

PERMANENTLY delete a container. This destroys the container, its database, and all its files (S3 bucket contents included) and cannot be undone. Only call this when the user has clearly asked for the container to be removed.

Inputs: containerId (required). Returns: deleted, message

delete_topicA
Destructive

PERMANENTLY delete one of the user's Kafka topics (the topic and all its messages). Cannot be undone. Only call when the user clearly asked to remove the topic. The name must be one they own.

Inputs: name (required). Returns: name, deleted

deploy_appA

Deploy an application from a local tarball (.tar, .tar.gz, .tgz, or .zip) to BasicDeploy. The runtime (Node.js, Python, or Go) is auto-detected from the archive contents; the app must listen on 0.0.0.0:8080. If containerId is omitted, a new container (with DB + S3) is created for the app; if provided, the archive is deployed into that existing container. Returns the resulting container and its public URL. IMPORTANT: tarballPath is a path on the machine running THIS MCP client (i.e. the local/stdio install). When BasicDeploy is added as a REMOTE connector (Claude/ChatGPT/Gemini chat) there is no shared filesystem, so this tool cannot read your tarball — deploy with exec_command instead (write the files into the container and start the server on 0.0.0.0:8080).

Inputs: tarballPath (required), containerId. Returns: message, containerId

exec_commandA
Destructive

Run a shell command inside a container (like docker exec). Returns the combined stdout/stderr output and the exit code. Useful for inspecting files, installing packages, or restarting processes inside the container. DEPLOYING WITHOUT A TARBALL (the way to deploy over a remote/chat connector, where there is no shared filesystem for deploy_app): write your app's files into the container with exec_command (e.g. heredoc/echo or install from git), install deps, then start the server. CRITICAL: the container's public URL (https://.basicdeploy.com) is ALWAYS proxied to PORT 8080 inside the container, so your app MUST listen on 0.0.0.0:8080 — NOT localhost/127.0.0.1, and NOT 3000/5000/etc. Any other port or binding returns HTTP 503 at the public URL even though the process is running. The routing is wired when the container is created; you do NOT need deploy_app to 'register' it. There is no init/supervisor: a process you start runs only until the container sleeps or restarts and is NOT relaunched — for a long-running web server enable always-on (set_always_on) and start it detached.

Inputs: command (required), containerId (required). Returns: output, exitCode

get_accountA
Read-only

Show the account's plan and capabilities: plan tier, container limit (plan base + add-ons), the memory sizes you may select, storage limit, how many always-on add-ons you hold, and whether containers auto-sleep. Use this to see what you're allowed to set.

Inputs: no named parameters. Returns: Account plan, limits and add-ons.

get_containerA
Read-only

Get full details of one container: id, subdomain, public URL, status, ports, database name and username, S3 bucket, volume path, and timestamps.

Inputs: containerId (required). Returns: A BasicDeploy container (non-secret fields).

get_docsA
Read-only

Fetch the BasicDeploy documentation as Markdown so you can answer the user's questions and deploy correctly without leaving the chat. Covers: what BasicDeploy is, deploying an app (the 0.0.0.0:8080 rule), the runtime and preset env vars, the PostgreSQL database and S3 object storage, the REST API, the MCP tools, custom domains, SSH, plans/pricing, and hosted auth-as-a-service (OpenID Connect) for your app's own end-users. Optional 'topic' returns only the matching section(s).

Inputs: topic. Returns: markdown

get_kafkaA
Read-only

Get the user's Kafka connection details and topics. BasicDeploy gives every account a Kafka broker (SASL/SCRAM, SCRAM-SHA-256) shared by all their containers. Returns the internal bootstrap (preset as KAFKA_BOOTSTRAP inside containers), the external bootstrap (for outside clients), the SASL username/password, the mandatory consumer-group id prefix (group ids MUST start with it), the current topics, usage and the plan limits. Provisions the tenancy on first call.

Inputs: no named parameters. Returns: limits, topics, enabled, password, +7 more

get_logsA
Read-only

Fetch recent logs from a container. Use this to debug crashes or check application output.

Inputs: containerId (required), tail. Returns: logs

list_containersA
Read-only

List all BasicDeploy containers owned by (or shared with) the authenticated user. Returns each container's id, subdomain, public URL, status, and creation time.

Inputs: no named parameters. Returns: count, containers

purge_topicA
Destructive

Purge (empty) one of the user's Kafka topics — deletes all its messages but KEEPS the topic. Use this to restart processing after a mistake: purge, then have consumers read from the start again. The topic name must be one the user owns (starts with their prefix).

Inputs: name (required). Returns: name, purged

set_always_onA

Turn a container's always-on (24/7, never sleeps) flag on or off. On Free this consumes a paid always-on add-on slot (fails if none is free); on Pro/Scale every container is always-on already. Returns the updated container.

Inputs: enabled (required), containerId (required). Returns: A BasicDeploy container (non-secret fields).

share_containerA

Share a container with another BasicDeploy user by email, giving them access to it. The recipient is emailed a link that signs them in and opens the container. Optionally pass expiresInHours to make the share expire after that many hours (omit for a share that never expires).

Inputs: email (required), containerId (required), expiresInHours. Returns: message

sleep_containerA

Sleep a running container: stop it to free memory while keeping its volume, database, and public URL, so it wakes again on the next request. Returns the updated container.

Inputs: containerId (required). Returns: A BasicDeploy container (non-secret fields).

wake_containerA

Wake a slept container so it serves traffic again (start it). A no-op if it is already running. Note: any web request to the container's public URL also wakes it automatically. Returns the updated container.

Inputs: containerId (required). Returns: A BasicDeploy container (non-secret fields).

whoamiA
Read-only

Return the identity of the BasicDeploy account this connection is authenticated as — the user's email and account id. Use it to confirm WHICH user is logged in before acting on their behalf.

Inputs: no named parameters. Returns: id, plan, email

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A4.1/5.0

    Scored across 18 tools

    Disambiguation4/5

    Container tools and Kafka tools are cleanly separated, and lifecycle actions (create/get/list/delete/wake/sleep) each target a distinct operation. The only mild overlap is deploy_app vs exec_command, but their descriptions clearly differentiate local-tarball vs remote deployment.

    Naming Consistency4/5

    Most tools follow verb_noun snake_case (list_containers, create_topic, delete_container), making the set predictable. Exceptions like whoami and set_always_on are minor and still readable.

    Tool Count4/5

    18 tools is on the higher end but justified by two resource domains (containers and Kafka) plus account/meta helpers. Each tool addresses a real operation, though a few (get_docs, whoami) are auxiliary.

    Completeness4/5

    Container lifecycle is well covered: create, list, get, deploy, exec, logs, sleep/wake, share, delete, plus always-on. Kafka has get/create/purge/delete; missing container resize/custom-domain tools are workaroundable via exec_command but notable gaps.

    Maintenance

    ActivityNo data
    ResponsivenessOutdated data

    Related MCP Connectors

    Related MCP Servers