Purpose
BasicDeploy MCP Server is an MCP (Model Context Protocol) server used to let AI coding agents directly create and manage BasicDeploy containers. It provides agents with a persistent runtime: a single MCP call yields a live container with a database, object storage, Kafka broker, and public URL.
Main capabilities
Each container is automatically equipped with a PostgreSQL database, S3-compatible object storage, a Kafka broker, environment variables, and a public HTTPS URL, all automatically configured. Agents can perform the following operations: create containers, deploy applications (Node, Python, Go, or Docker, automatically detected), run commands, read logs, manage Kafka topics, check the current authenticated identity, set always-on, share, or delete containers.
Usage
Requires Node.js ≥ 18, no installation needed, npx fetches on demand.
Get an API key: at https://basicdeploy.com/api-keys (format similar to bd_…, shown only once), then add it to the MCP client.
Claude Code plugin (this repository also serves as a plugin marketplace): then set the environment variable BASICDEPLOY_API_KEY (the plugin reads it via ${BASICDEPLOY_API_KEY}).
OpenAI Codex CLI: or add it directly to ~/.codex/config.toml.
Environment variables: deployed applications must listen on 0.0.0.0:8080, which is the port served by the public URL. DATABASE_URL, S3_ENDPOINT / S3_ACCESS_KEY / S3_SECRET_KEY / S3_BUCKET, and KAFKA_BOOTSTRAP / KAFKA_USERNAME / KAFKA_PASSWORD / KAFKA_GROUP_PREFIX are already preset in the container environment. Startup output is written to /workspace/deploy.log.
Use cases
Suitable for letting AI coding agents automate the deployment and management of applications and infrastructure, including creating containers with databases, storage, and message queues, deploying code, executing operational commands, viewing logs, managing Kafka topics, and container sharing.
Limitations
The material does not provide specific details such as pricing, plan limits, container specification caps, or performance metrics. Deployed applications must listen on the specified port 0.0.0.0:8080. Usage requires first obtaining an API key and configuring environment variables.
