MCP server

Connect Claude, Cursor or any MCP client to SetFork — lists, runs and expert gnomes as tools.

SetFork ships a remote MCP server (Streamable HTTP), so AI agents can work with lists, run them step by step, and even call in expert gnomes for help — all as first-class tools.

Endpoint

https://setfork.com/api/mcp
Authorization: Bearer sf_…

Create a token in Settings → API & MCP access — see API tokens.

Connect from Claude Code

claude mcp add --transport http setfork https://setfork.com/api/mcp \
  --header "Authorization: Bearer sf_YOUR_TOKEN"

Or in any MCP client that supports remote servers: URL https://setfork.com/api/mcp, header Authorization: Bearer sf_….

Tools

A read-scope token unlocks the read tools; creating and changing lists needs write scope (see API tokens).

Lists

Tool	Scope	What it does
`search_lists`	read	Search public lists (and your own private ones) by keywords/meaning — returns `owner/slug` refs
`get_list`	read	Fetch a full list: all blocks with their type — steps, text, images, polls, videos and quizzes
`get_script`	read	Render a list as a ready-to-run script (`sh` / `ps1` / `py`) with progress echoes
`create_list`	write	Create a list — it appears as a private draft; supports step / text / image / poll / video / quiz blocks
`update_list`	write	Replace the blocks of a list you own (a published one gets a new version)

Runs

Tool	Scope	What it does
`start_run`	write	Start (or resume) your run of a list — a personal pass with progress
`check_step`	write	Report a run step by number: done / not done / blocked with a reason
`get_run`	read	Fetch a run by id: steps with their state and overall progress

Gnome workshop

Tool	Scope	What it does
`list_gnomes`	read	The roster of expert gnomes: id, name, domains and what each is good at — call this first
`ask_gnome`	read	Ask one gnome in their specialty (advice, outline, critique); optionally attach a list as context
`gnome_review`	read	A guild master reviews an existing list against his guild code and returns concrete fixes
`council_draft`	write	Convene a full council (steward → experts → critic → elder); returns a `draftId`
`get_council_draft`	read	Poll the council: status, the conversation (which gnome said what) and candidate lists

ask_gnome, gnome_review and council_draft spend your AI quota — like generating on the site. For a quick single-expert answer use ask_gnome; for a full list built from a debate use council_draft (1–4 minutes, poll get_council_draft every ~20s).

The same safety model as the UI applies: agents create drafts, humans publish; only the owner or a collaborator can modify a list.

Why this matters

Agents can consume canonical lists ("fetch the team's deploy runbook and follow it"), execute them with progress tracking (start_run → check_step), produce new ones ("turn this incident post-mortem into a reusable checklist and save it as a draft"), and consult the right expert gnome without leaving their working environment.