NimbleBrain and MCP
NimbleBrain is built on the Model Context Protocol. Every tool the agent calls, every app it renders, and every external client that reaches a workspace does so over MCP. A server written to the specification works here without modification.
Three roles
Section titled “Three roles”NimbleBrain plays three MCP roles at once, and each one is a different contract for you:
| Role | Who is on the other side | What you build against |
|---|---|---|
| MCP client | The MCP servers installed in a workspace (connectors) | Protocol support: the capabilities the host advertises, and the extensions it offers a server |
| MCP Apps host | An app’s ui:// view, running in a sandboxed iframe |
The MCP App Bridge: the ext-apps specification plus three bridge extensions |
| MCP server | External clients (Claude, Cursor, another agent) connecting to a workspace | The MCP endpoint: one Streamable HTTP server per workspace |
Most server developers only need the first row. Build a spec-compliant server, and then use the extensions that fit.
Extensions
Section titled “Extensions”Where the specification has no answer yet, for things a long-running, multi-workspace host needs from a server, NimbleBrain adds an extension under the ai.nimblebrain/ namespace. Each one is negotiated, has a named consumer on the other side, and is safe to ignore. The Extensions section lists what each one gives your server, the rules they all follow, and the full registry.
Related
Section titled “Related”- Extensions: what a server can do on NimbleBrain that plain MCP cannot
- Protocol support: specification revisions, transports, and advertised capabilities
- MCP Apps: what an app is and how it renders
- The MCP endpoint: connecting an external client to a workspace