Flowise talks to Agent Update over MCP. The server is https://api.tryagentupdate.com/v1/mcp, the transport is Streamable HTTP, and the credential is one header.
Where it goes: Custom MCP node -> MCP Server Config field
Setup
{
"url": "https://api.tryagentupdate.com/v1/mcp",
"headers": { "Authorization": "Bearer au_live_..." }
}{ "url": "https://api.tryagentupdate.com/v1/mcp",
"headers": { "Authorization": "Bearer {{$vars.agentUpdateToken}}" } }Before you file a bug
No type, no transport, no command. The object is just url and headers, and the value carries the full Bearer prefix. Flowise tries StreamableHTTPClientTransport first and only falls back to SSE when that fails, so ignore the string 'sse' in the source and the /sse URL in the in-node hint. The config shape is identical either way. Variable syntax is strict: {{$vars.name}}, no hyphens and no spaces, so {{$vars.agent-update-token}} will not substitute. An unresolved variable ships verbatim as your header value instead of erroring, which reads as a 401 from a valid-looking config. "No Available Actions" after a refresh means the connection failed and the real error was swallowed; check the server logs. On self-hosted installs, leave CUSTOM_MCP_PROTOCOL unset.
Check it worked
Ask the agent to text you. A 401 means the token is wrong, or the word Bearer is in there twice. No tool at all means the transport string is wrong. Both are covered in troubleshooting.
Next
The five tools and their arguments are on the MCP page. The same tools over plain HTTP are on the REST page. Every other tool is on the docs index.