About Rimbra
Rimbra connects Claude Code to a Rimbra workspace and provides guidance on using Rimbra. Access is set during sign-in as Developer, which may deploy, or Viewer, which is read-only.
Key features
- 01Connect Claude Code to a Rimbra workspace
- 02Choose Developer or Viewer access
- 03Sign in through the MCP flow
- 04Connect with a bearer key
Use cases
- 01Deploy apps from Claude Code
- 02Read workspace data with Viewer access
MCP support
Provides an MCP endpoint for Claude Code to connect to a Rimbra workspace. It supports sign-in and bearer-key authentication, with Developer or Viewer access.
Configuration
Remote servers need no local install. Pick your client, then copy the config or install in one click.
https://app.rimbra.app/mcpclaude mcp add --transport http app-rimbra-rimbra https://app.rimbra.app/mcp{"mcpServers":{"app-rimbra-rimbra":{"type":"http","url":"https://app.rimbra.app/mcp"}}}Open in Cursor{"servers":{"app-rimbra-rimbra":{"type":"http","url":"https://app.rimbra.app/mcp"}}}Open in VS Code{"mcpServers":{"app-rimbra-rimbra":{"type":"http","url":"https://app.rimbra.app/mcp"}}}{"mcpServers":{"app-rimbra-rimbra":{"serverUrl":"https://app.rimbra.app/mcp"}}}Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.
Tools
Details
From the project READMERimbra for Claude Code
Connects Claude Code to your Rimbra workspace and teaches it how Rimbra works.
/plugin marketplace add AdejareAkolawole/rimbra-agents
/plugin install rimbra@rimbra
The first time Claude uses Rimbra, run /mcp and sign in. Pick the workspace and whether Claude may deploy (Developer) or only read (Viewer).
Prefer a key? Make one in Rimbra → MCP and run:
claude mcp add --transport http rimbra https://app.rimbra.app/mcp --header "Authorization: Bearer YOUR_KEY"
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.