Using IntentDocs with Claude Code
Claude Code is excellent at building; what it can't do is know what you meant to build. IntentDocs supplies that: an interview turns your idea into a structured spec, and Claude Code connects to it over MCP (Model Context Protocol) — reading stories, the data model, and per-story implementation plans as it works, and reporting progress back so the spec stays reconciled with the code.
To use IntentDocs with Claude Code: create your spec via the AI interview, run the setup shown in your project dashboard to register the IntentDocs MCP server, then build story by story — Claude Code reads the spec over MCP and syncs progress back into a built-versus-planned audit trail.
What is Claude Code?
Claude Code is Anthropic's agentic coding tool — a CLI (and desktop/IDE surface) where Claude reads your codebase, edits files, runs commands, and ships changes. (Anthropic)
How the integration works
1. Create your spec in IntentDocs
Start from the AI interview (or import an existing GitHub repo). You'll end up with a story map, data model, and build order — the spec Claude Code will build against.
2. Run the two setup commands from your project dashboard
Your project's Start Building panel shows two copy-paste CLI commands: an init that links your repository to the project with a sync token, and a setup that registers the IntentDocs MCP server with Claude Code and installs slash commands into .claude/commands/. Run them in your project directory — the dashboard detects the connection automatically.
3. Build story by story
Ask Claude Code for the next story (the installed slash commands make this one step). It pulls the story's implementation plan and context over MCP, builds, and syncs progress back — so the story map shows what's actually shipped versus what's planned.
What Claude Code gets from the spec
- Read the full spec — stories, acceptance notes, data model, build order — as structured context, not pasted prose.
- Pick up the next unbuilt story with one slash command.
- Write build progress back to the spec, keeping the built-vs-planned audit trail live.
- Re-sync after the spec changes — edits to the story map reach the agent on its next read.
What IntentDocs is
IntentDocs is a spec-driven development platform: an AI interview turns your idea into a structured spec — a visual story map, data model, and build order — and your coding agent (Claude Code, Cursor, or any MCP client) builds from it over MCP, with an audit trail of what was built versus what was planned. 7-day free trial, no card required. Pro is £12/month (or £120/year, equivalent to £10/month). Team is £15 per seat/month (or £144/seat/year), minimum 2 seats. Enterprise is custom. See the pricing page for details.
Frequently asked questions
Do I need the MCP connection, or can I just paste the spec into Claude Code? Pasting works as one-shot context, but it's static — Claude Code can't pull per-story plans as it goes, and nothing records what was built. The MCP connection is what makes the spec live in both directions.
Which Claude Code surfaces does this work with? Anywhere Claude Code supports MCP servers and slash commands — which includes the standard CLI installation working in your repository.
Does IntentDocs replace CLAUDE.md? No — they're complementary. CLAUDE.md carries repo conventions; IntentDocs carries the product spec and build state, served over MCP. Use both.
What does IntentDocs cost? There's a 7-day free trial (no card required), then Pro at £12/month or £120/year. Full details at intentdocs.com/pricing.
Keep reading
Ready to build what you intended?
Turn your idea into a structured spec and hand it to Claude Code or Cursor over MCP — with an audit trail of built versus planned.
Start free →7-day free trial · no card required