Add the server
Devin Local and the Devin CLI share one config. A URL is Streamable HTTP. Devin Local's customizations.
devin mcp add spekkr --url https://spekkr.com/mcp
The default scope is local, which writes .devin/mcp_config.local.json and leaves it out of git. -s project writes .devin/mcp_config.json. -s user writes ~/.config/devin/mcp_config.json. On Windows that user file is %APPDATA%\\devin\\mcp_config.json.
devin mcp add spekkr --url https://spekkr.com/mcp -s user
{
"mcpServers": {
"spekkr": {
"url": "https://spekkr.com/mcp"
}
}
}
In Devin Local, open Customize, then MCPs. The files are the same. Spekkr does not require a token to search, read or pull, so do not sign in for those tools.
Cascade
Cascade reads ~/.config/devin/mcp_config.json, or $XDG_CONFIG_HOME/devin/mcp_config.json when that variable is set. On Windows the default is %AppData%/devin/mcp_config.json. Open it from Cascade's MCP menu, Open MCP config file, or add a server under Settings, then Tools, then Windsurf Settings, then Add Server. A remote HTTP server uses serverUrl or url. The user-scoped CLI entry above is a url in that file. This is the other shape:
{
"mcpServers": {
"spekkr": {
"serverUrl": "https://spekkr.com/mcp"
}
}
}
The Windsurf editor's own discovery file is separate: ~/.codeium/windsurf/mcp_config.json, or ~/.codeium/windsurf-next/mcp_config.json for Next. In the editor settings, search for chat.mcp.discovery.enabled and enable the Devin configurations source to read the Devin file. Press refresh after adding a server. On an Enterprise account, MCP is turned on in settings. A team allowlist that names one server blocks every other server.
Checked 20 November 2026. Devin CLI's MCP docs and Cascade's MCP docs.
Without connecting
An agent that can open a web address does not need the server. Paste one line. The address is that spec's start note.
Build the spec at https://spekkr.com/juno/waitlist/start.md.
juno/waitlist is a waitlist spec. The note tells the agent to fetch the files, record the choices and build.
Search, then pull
With the server connected, paste this:
Search Spekkr for a waitlist spec, then pull juno/waitlist with database=sqlite.
Spekkr tells the agent to search with search_specs, read get_spec, then call pull_spec with the person's choices. Write the files into a folder and follow BUILD.md.
juno/waitlist lists database as postgres or sqlite. The default is postgres, so the prompt sets sqlite. A choice the spec does not offer is refused. Anything left out keeps the spec's default.
Search, get and pull need no sign-in. Publishing, unpublishing and whoami do: the agent opens a Spekkr page, and Spekkr emails a code. There is no password. Questions: support@spekkr.com.
The other tools, and the limits, are on the docs page. Every agent is listed on the setup index.