by dogukanakkaya
Runs a Pulumi‑based MCP server inside Docker, allowing AI clients to invoke Pulumi commands through the Model Context Protocol.
Provides an MCP‑compatible server that executes Pulumi operations in a Docker container, enabling AI assistants such as Claude Desktop, VS Code Copilot, and Cline to manage cloud infrastructure via natural‑language prompts.
{
"pulumi-mcp-server": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"--name",
"pulumi-mcp-server",
"-e",
"PULUMI_ACCESS_TOKEN",
"dogukanakkaya/pulumi-mcp-server"
],
"env": {
"PULUMI_ACCESS_TOKEN": "${YOUR_TOKEN}"
},
"transportType": "stdio"
}
}
${YOUR_TOKEN}
with your actual Pulumi access token.--rm
ensures the container is removed after the session.PULUMI_ACCESS_TOKEN
for authentication.Q: Do I need Pulumi installed on my host machine? A: No. The server runs Pulumi inside the Docker image.
Q: How is the Pulumi token secured? A: It is passed as an environment variable to the container; avoid committing the token in source control.
Q: Can I customize Pulumi settings (e.g., stack, project)? A: Yes, you can issue additional Pulumi commands through the client after the server starts.
Q: What transport does the server use?
A: The configuration sets transportType
to stdio
, which is the default for most MCP clients.
Q: Is the server compatible with other MCP clients beyond the listed ones? A: Any client that follows the MCP specification can connect using the same JSON configuration.
To interact with the MCP Server, you'll need an MCP client. Supported clients include Claude Desktop, VSCode, and Cline, among others. The configuration process is similar across all of them.
Below is a sample configuration you can add to your client:
{
"pulumi-mcp-server": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"--name",
"pulumi-mcp-server",
"-e",
"PULUMI_ACCESS_TOKEN",
"dogukanakkaya/pulumi-mcp-server"
],
"env": {
"PULUMI_ACCESS_TOKEN": "${YOUR_TOKEN}"
},
"transportType": "stdio"
}
}
Please log in to share your review and rating for this MCP.
{ "mcpServers": { "pulumi-mcp-server": { "command": "docker", "args": [ "run", "-i", "--rm", "--name", "pulumi-mcp-server", "-e", "PULUMI_ACCESS_TOKEN", "dogukanakkaya/pulumi-mcp-server" ], "env": { "PULUMI_ACCESS_TOKEN": "${YOUR_TOKEN}" } } } }
Explore related MCPs that share similar capabilities and solve comparable challenges
by zed-industries
A high‑performance, multiplayer code editor designed for speed and collaboration.
by modelcontextprotocol
Model Context Protocol Servers
by modelcontextprotocol
A Model Context Protocol server for Git repository interaction and automation.
by modelcontextprotocol
A Model Context Protocol server that provides time and timezone conversion capabilities.
by cline
An autonomous coding assistant that can create and edit files, execute terminal commands, and interact with a browser directly from your IDE, operating step‑by‑step with explicit user permission.
by continuedev
Enables faster shipping of code by integrating continuous AI agents across IDEs, terminals, and CI pipelines, offering chat, edit, autocomplete, and customizable agent workflows.
by upstash
Provides up-to-date, version‑specific library documentation and code examples directly inside LLM prompts, eliminating outdated information and hallucinated APIs.
by github
Connects AI tools directly to GitHub, enabling natural‑language interactions for repository browsing, issue and pull‑request management, CI/CD monitoring, code‑security analysis, and team collaboration.
by daytonaio
Provides a secure, elastic infrastructure that creates isolated sandboxes for running AI‑generated code with sub‑90 ms startup, unlimited persistence, and OCI/Docker compatibility.