Kitecraft documentation

Connect your agent and turn saved project evidence into researched writing packets.

Kitecraft prepares content context and research for your own writing agent. Your agent starts with a compact current-work handoff, then reads the relevant saved context and sources for its next decision. Your agent writes; a separate editor reviews it. Kitecraft retains exact files and progress so work can resume across agents. You can publish through your own tools or connect an optional article destination for an explicitly approved delivery package.

Examples use https://kitecraft.ai. For local verification or a supplied preview origin, set KITECRAFT_API_URL to that origin, such as http://127.0.0.1:3100. Replace the production origin in examples with your configured KITECRAFT_API_URL.

Connect ChatGPT or Claude through a supported custom MCP connection, or use Set up your agent for a coding-agent handoff and secure developer-key setup. Both paths start with a verified read of your saved project.

The browser console, API, CLI and MCP share the same project operations. ChatGPT and Claude use supported OAuth connections; Codex and other local agents use private developer keys. Recurring writing runs in your own agent host after a bounded test and separate schedule setup.

Start here

Sign up at /signup from the current app or the supplied preview origin, confirm your email, and follow /onboarding to start the seven-day trial. After the trial ends, writes need an active subscription while saved reads stay available.
Add your website URL and optional business name. Kitecraft saves the site and reads its homepage first.
Kitecraft saves your business and voice profile automatically. You can review and edit it afterward.
Optionally connect Google Search Console, Analytics or PostHog inside onboarding. Choose your properties and import evidence, or continue without analytics. Select customer questions and run optional visibility checks before the final plan.
Create an editable content plan: ranked opportunities, existing coverage, clusters and a credible customer action. Research can investigate missing public evidence within account limits.
Request a writing brief, poll its status, then retrieve the complete researched packet through download, API, CLI or MCP.
Optionally add interview answers, recordings or notes to that article. Your agent can ask focused questions and read the saved transcripts alongside the research.
Give the packet and editing skill to your own agent for one draft and one integrated edit. Retain the exact draft and independent review, then approve the next step. Use your own publishing tools or the supported destination delivery flow.

Market research, questions to monitor and visibility checks provide additional evidence when useful. They are not a mandatory checklist before every article.

For agent access, issue an account-scoped key under Account → Developer keys. Prefer read-only keys for inspection. Keep keys out of URLs, source control, screenshots, and chat transcripts.

Give this to your agent

Provide your key privately as KITECRAFT_API_KEY, then paste this handoff into your agent. It connects and reads your existing project before proposing work.

MCP agent handoff

Connect my agent to Kitecraft and resume my existing project.

Read https://kitecraft.ai/docs/mcp for connection details and tool schemas.

1. Add a remote Streamable HTTP MCP server named kitecraft at https://kitecraft.ai/mcp. Use the Bearer token from KITECRAFT_API_KEY in my environment or secret store. Never print the key or put its literal value in prompts, source files, URLs or committed configuration. Preserve my other MCP servers. Use this client's supported secret substitution. Kitecraft developer keys do not use OAuth. If a key or client configuration is missing, tell me exactly what I must supply. If this client cannot use a remote server with a Bearer header, explain that limitation and offer the documented CLI connection instead. For an explicitly supplied preview/local origin, use that origin with /mcp appended.

2. Initialize the connection and discover its tools. Call project_context and verify the returned account, MCP server contract version and projects. Check that its advertised calendar_handoff, calendar_setup and artifact_save/list/read tools exist in this host, and brief_request declares recoverOperationId. If a tool or argument is missing, refresh the supported host connection and repeat discovery. A local agent can use the documented authenticated CLI/API with its existing private key; a hosted chat must refresh its connection. Report the precise mismatch instead of claiming the new workflow passed. Never ask me to paste credentials into chat. Verify the returned account and projects. Use my existing project. If several projects exist, ask which one I mean. Retain its project ID for every project-scoped call. Do not recreate my account, restart my trial or overwrite saved setup. If no project exists, report the next setup action from onboarding_status before changing anything.

3. Read calendar_handoff for a compact queue, then calendar_handoff with one returned itemId. Inspect the current status and next action. Preserve existing reviewed work and retrieve its exact saved article/review with artifact_list and artifact_read. Full profile_read, content_list and plan_read archives are explicit supporting reads for a particular missing fact, not default startup context. When I ask you to run one saved article workflow, use calendar_run and follow its bounded instructions, stopping for my review. For recurring setup use calendar_setup after verifying a single bounded run; creating or reading setup does not enable a schedule.

4. For an eligible writing item, read the brief_read overview, then its writer input and exact source/material reads. Follow nextOffset until null for required text, pin identities and verify the complete content hash. A summary is not sufficient writing evidence. Follow the exact free recovery call returned by brief_status; do not replace it with a fresh purchase. Ask before missing/stale research or hosted evaluation. Retain the operation ID and poll with a deadline; queued work is unfinished. Save completed article/review bytes with artifact_save, read back their hashes and report current work using returned revisions. A local path alone cannot be read by a cloud agent.

5. Return the verified project, connection result, next article, packet readiness and one clear next action. When I ask you to write, follow the packet's draft and edit instructions in my own tools. Flag unsupported claims. Do not publish, start research, enable schedules, change billing or delete data without my instruction.

Prove the connection with an actual project_context response. A saved MCP configuration alone is not a successful connection.

Your API key is never included.

Kitecraft documentation

Start here

On this page