# ChatBlocks

> An infinite canvas of vibe-coded blocks, connected to live data. Authored by people and agents.

## Docs

- [In-app editor](https://docs.chatblocks.ai/authoring/in-app-editor.md): Monaco-based editor for hand-authoring a block — file tree, live preview, save vs publish.
- [Manifest](https://docs.chatblocks.ai/authoring/manifest.md): The chatblocks.json schema — formats, sizes, widget, binding, permissions.
- [Runtime](https://docs.chatblocks.ai/authoring/runtime.md): How blocks render in the iframe — render paths, sandbox model, data injection, the isRenderable predicate.
- [Authoring via an agent](https://docs.chatblocks.ai/authoring/via-agent.md): The MCP authoring loop — your coding agent drives blocks.init, setFiles, build, and publish end-to-end.
- [Widget](https://docs.chatblocks.ai/authoring/widget.md): A small, native projection of your block — six templates, five themes, scheduled refreshes.
- [Plans](https://docs.chatblocks.ai/billing/plans.md): Free, Builder ($9/mo or $89/yr), and Enterprise (contact-only). What's in each, and what you give up on Free.
- [Trial and Customer Portal](https://docs.chatblocks.ai/billing/trial-and-portal.md): 14-day trial, no refunds, hosted Stripe Customer Portal for plan switching, cancel, and card update.
- [CLI commands](https://docs.chatblocks.ai/cli/commands.md): Full command reference for the chatblocks terminal CLI.
- [Install the CLI](https://docs.chatblocks.ai/cli/install.md): Install @chatblocks/cli for terminal access and an stdio MCP proxy.
- [Audit log](https://docs.chatblocks.ai/concepts/audit-log.md): Every privileged write is logged with actor and action. Reads are not audited.
- [Canvas and blocks](https://docs.chatblocks.ai/concepts/canvas-and-blocks.md): The spatial model — canvases hold placements, placements pin blocks at positions, blocks render in sandboxed iframes.
- [Plans and limits](https://docs.chatblocks.ai/concepts/plans-and-limits.md): Three plans (Free, Builder, Enterprise), hard per-resource caps, and a workspace.get MCP tool that surfaces your current usage.
- [Workspaces](https://docs.chatblocks.ai/concepts/workspaces.md): Every resource that costs money or can be shared lives in a workspace, not on a user.
- [BYOK keys](https://docs.chatblocks.ai/connecting-data/byok-keys.md): Bring your own LLM API key — used by scheduled runs and on-platform AI generation.
- [Outbound MCP](https://docs.chatblocks.ai/connecting-data/outbound-mcp.md): Point ChatBlocks at a third-party MCP server — Linear, GitHub, Notion, or your own internal MCP.
- [Postgres](https://docs.chatblocks.ai/connecting-data/postgres.md): Bind a block to a read-only SQL query against your own Postgres database.
- [Stripe](https://docs.chatblocks.ai/connecting-data/stripe.md): Read MRR, balance, and recent charges from your Stripe account into a block.
- [Inbound webhook](https://docs.chatblocks.ai/connecting-data/webhook.md): Receive HMAC-signed JSON from your own systems and bind blocks to the most recent payloads.
- [ChatBlocks](https://docs.chatblocks.ai/index.md): An infinite canvas of vibe-coded blocks, connected to live data. Authored by people and agents.
- [Errors and limits](https://docs.chatblocks.ai/mcp/errors-and-limits.md): JSON-RPC error codes, HTTP statuses, per-plan rate limits, and how plan-gated tools fail on Free.
- [MCP setup](https://docs.chatblocks.ai/mcp/setup.md): Connect your coding agent to the hosted ChatBlocks MCP server at /api/mcp/v1.
- [Tool reference](https://docs.chatblocks.ai/mcp/tool-reference.md): All MCP tools exposed by the ChatBlocks server at /api/mcp/v1.
- [Quickstart](https://docs.chatblocks.ai/quickstart.md): Sign up and ship your first block in under 5 minutes.
- [Scheduled runs](https://docs.chatblocks.ai/scheduled-runs/concepts.md): Cron-triggered agent loops that decrypt a workspace BYOK key, connect over MCP, and write back to your blocks.
- [Creating a schedule](https://docs.chatblocks.ai/scheduled-runs/creating.md): The /settings/schedule UI — list, create, edit, and inspect run history.
- [Preview and run-now](https://docs.chatblocks.ai/scheduled-runs/preview-and-run-now.md): Two manual paths for testing a scheduled prompt — schedule.preview (one-off, ephemeral) and schedule.runNow (existing saved row).

## OpenAPI Specs

- [openapi](https://docs.chatblocks.ai/api-reference/openapi.json)