BetaDrop MCP

@betadrop/mcpexposes BetaDrop to any client that speaks the Model Context Protocol (Claude Code, Claude Desktop, Cursor, VS Code with Copilot) as ten tools an assistant can call. It runs locally over stdio and uses the same credentials as the CLI.The MCP overviewcovers per-editor setup in more detail; this page is the tool surface.

claude mcp add betadrop -s user -- npx -y @betadrop/mcp

{ "mcpServers": { "betadrop": { "command": "npx", "args": ["-y", "@betadrop/mcp"] } } }

Restart or refresh the client afterwards; MCP servers are discovered at startup.

The server resolves credentials exactly the way the CLI does, which gives you three options in decreasing order of how much you should like them.

- Already logged in with the CLI.Nothing to do. Both read the same credentials file, so a machine wherebetadrop loginhas been run is already authenticated here. This is the option with no secret in a config file anywhere.
- Ask the assistant to log in.Callbetadrop_loginwith a token. It validates the token against the server before saving, and it writes to the same shared config. Doing this once also logs the CLI in.
- An environment variable in the config.BETADROP_TOKENis read from the server's environment and takes precedence over the stored credential. It works, but it means a plaintext token sitting in an editor config file — worth avoiding unless the other two are impossible.

Token in the client config (last resort)

{ "mcpServers": { "betadrop": { "command": "npx", "args": ["-y", "@betadrop/mcp"], "env": { "BETADROP_TOKEN": "bd_live_xxxxxxxx" } } } }

Tokens come fromSettings → Developer → API tokensin the dashboard, or frombetadrop_token_createbelow. Either way the plaintext value is shown exactly once.

Ten tools. Required arguments are marked; everything else is optional. You do not call these by name in practice. You ask the assistant for the outcome and it picks. Knowing what exists is what stops you asking for something that does not.

betadrop_publishis the one tool that can set a build's expiry at upload time, and its four expiry arguments work together rather than independently.expiryTypechooses the strategy and the numeric arguments supply the threshold that strategy needs.

Your plan's retention ceiling still applies. These arguments choose a shorter life than the maximum, never a longer one. Device and download limits are the reason this tool is worth using over the CLI for a sensitive build: neither has an equivalentpublishflag.

- Absolute paths.betadrop_publishtakes an absolutefilePath. An MCP server does not necessarily share a working directory with your editor, so a relative path is ambiguous rather than convenient.
- Same validation as the CLI.The extension must be.ipaor.apkand the file must really be a ZIP archive — both are checked locally before anything is uploaded.
- It runs on your machine.The server is a local process speaking stdio to your client. The build file never passes through the assistant; it is read from disk and uploaded directly.
- Token tools are real.betadrop_token_createandbetadrop_token_deletemint and revoke live credentials. That is convenient and it is also a reason to read what an assistant proposes before approving it.

This is a web browser that enables your coding agent, such as Claude Code, to visit websites on your behalf and assist you in identifying bugs or creating UI test cases.

Manage apps, builds, and artifacts on Bitrise, a Continuous Integration and Delivery (CI/CD) platform.

A local Python MCP server that exposes the Codemagic CI/CD REST API as Claude-callable tools.

Access and interact with Harness platform data, including pipelines, repositories, logs, and artifact registries.

An SSE-based MCP server that allows LLM-powered applications to interact with OCI registries. It provides tools for retrieving information about container images, listing tags, and more.

The Octopus MCP Server provides your AI assistant with powerful tools that allow it to inspect, query, and diagnose problems within your Octopus instance, transforming it into your ultimate DevOps wingmate.

The Railway MCP Server enables natural language interaction with your Railway projects and infrastructure. Ask your IDE or AI assistant to create projects, deploy templates, manage environments, pull variables, redeploy services, and more.

The Shipyard CLI provides an MCP server for agents to manage Shipyard environments directly: by pulling logs, comparing branches, running tests, and stopping/starting environments..

MCP server for managing Unleash feature flags and automate best practices.