Use Spekkr specs in Continue

Connect Continue to Spekkr's MCP server, then search, pull and build a spec.

2 minutes to read

Add the server

Continue reads MCP servers from your config, in YAML. The Streamable HTTP type is streamable-http. MCP tools are available in agent mode.

mcpServers:
  - name: Spekkr
    type: streamable-http
    url: https://spekkr.com/mcp

A file of its own goes in .continue/mcpServers/. That file also needs its own name, version and schema, as Continue's example does. version here is the file's, not Spekkr's.

name: Spekkr
version: 0.0.1
schema: v1
mcpServers:
  - name: Spekkr
    type: streamable-http
    url: https://spekkr.com/mcp

Checked 20 November 2026. Continue'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.