Agents Index

dotsy

Online

Build and publish static sites on dotsy with draft-first MCP tools, OAuth Connect, and API keys.

Visit publisherConnectJSON

What it can do: 80 tools

  • create_siteCreate empty site; seeds brief. Globally taken slugs auto-suffix to `{slug}-{adjective}-{noun}` (default); pass onSlugTaken:"fail" to get a 409 instead of a renamed site.
  • get_site read-onlySite detail, stats, publicUrl, brief head (default-on), and readiness flags. pages[] is a ~25-entry head by default (stats.pages has the true count); pass pages: true for the full array (capped at 1000), or list_content/
  • update_briefUpdate `_intent/site.md` (site brief) or a page brief when `page` is set. See field descriptions for rules, notes, and head enums.
  • get_plan read-onlyRead-only workspace plan and pooled usage; pass slug for this site's add-ons. Call before a large build.
  • get_analytics read-onlyRead-only traffic overview (default) or full breakdowns via include[]; optional bot id for crawler page drill-down.
  • set_analytics_providerConnect an analytics provider (GA4, Plausible, Fathom, Umami) or remove it (provider 'none'). dotsy adds its script to every live page's <head>, no publish needed. One provider per site. Use this, not a pasted GA4 gtag s
  • get_custom_code read-onlyRead the site-wide custom code: `draft` (what the next publish puts live) and `published` (what visitors get now) for both boxes — head (before </head>) and body (before </body>) — plus `pending`, `runOn` and `maxChars`.
  • set_custom_codeSet site-wide custom code: `head` goes before </head> and `body` before </body> on every page, on every layout. Saved as a draft; goes live with the next publish_site (on a live-mode site the dashboard publishes only the
  • set_site_iconSet the favicon from a square image asset. Draft until publish.
  • update_siteUpdate site settings: title, keyConvention, editingMode, signature ("Made with dotsy" badge; live immediately), trailingSlash, ownSeoFiles, aiTrain, and the language settings; each field's own description has the details
  • rename_siteRename the site slug (hostname {slug}.dotsy.site). Owner-only; use the returned slug afterwards. Published site: the old slug redirects on the API (301 reads, 308 writes) and the old host 301s, both reserved until delete
  • publish_sitePublish draft to live. handoff required; feedback optional. Warnings (form_unwired, store, SEO) are advisory: tell the user. Site-check errors return a publish_issues decision. A request to publish is not agreement to pu
  • get_site_tasks read-onlyWhat needs fixing on a site, from stored checks. Call after writes, before publish_site.
  • get_draft_status read-onlyPending draft changes: content keys and routes with status. May include requiredDecision (publish_confirm) before publish_site.
  • review_changesReview queue: what changed and isn't live yet. list (counts first) → get one item (hidden changes, optional diff, bodyChanged: false means only title/meta/route fields changed — review hidden, not the visible page) → mar
  • discard_draftsDiscard unpublished drafts: all (omit key/keys/routes/menus), one content key (key), menu draft only (menus:true), or a selection (keys, routes). Destructive — check get_draft_status first.
  • delete_sitePermanently delete site; confirmSlug must equal slug.
  • bulk_put_contentStage many content keys (pages, layouts, fragments). Content only — not routes or assets. Each body ≤60KB and the whole call ≤80KB; larger pages use stage_content_chunk, dotsy push, or PUT content-raw. May queue above th
  • get_site_manifest read-onlyContent keys + hashes only (optional routes=true) — static files live in list_assets, not manifest. Diff keys+hashes before apply_changeset; stage only changed bodies.
  • find_replaceCase-insensitive find→replace across pages in one staged commit. Batch all replacements into ONE call — never parallelize find_replace on the same key (concurrent edits surface as per-key conflict). find/replace ≤60KB.
  • search_content read-onlyFind pages containing a phrase (grep without reading bodies). Requires do-sqlite — graduate_site first if search_unavailable.
  • graduate_siteEnable site search & collections (kv → do-sqlite), one-way. Unlocks search_content, collection indexes, visitor /__paige/search, and moves any R2 form-submission ledger into SiteDb. 409 blocked: `reason` names the gate —
  • apply_changesetStage writes[] + deletes[] in one call; attach routes via writes[].route. writes[].ifMatch (hash from get_site_manifest; "" = must not exist) guards each key (a delete takes { key, ifMatch } too); atomic:true makes one s
  • import_site_from_urlImport URL to draft. On complete, response may include requiredDecision — preview then ask mirror vs editable before structure_*.
  • get_structure_status read-onlyFlat vs structured page counts; chromeCoverage = real per-fragment page counts + missedPages (check before promising sitewide edits). Informs user — do not auto-run analyze/apply while requiredDecision pending.
  • structure_site_analyzePropose shared layout + fragments; persist:false first. Wait for mirror-vs-editable answer if requiredDecision pending.
  • structure_site_applyRewrite flat pages to layout + fragments (draft). Do not call while requiredDecision pending — user must pick editable first. It extracts header/footer only; report chromeCoverage counts, not 'sitewide'. Afterwards share
  • get_structure_result read-onlyLast structure apply job result (structuredKeys, conflicts, partial).
  • adapt_site_analyze read-onlyPropose nav wiring + blog collectionization for an imported mirror (draft, opt-in). Read-only; returns per-adapter reports + proposalEtag. Nav decline may include nextStep (e.g. mega-menu → edit fragments/header.html). W
  • adapt_site_applyApply the adapt proposal (draft): wire nav into the menu store and/or rewrite the blog index to a live <dotsy-collection>. One undo covers the whole apply; a second apply is refused until adapt_site_revert (or force). Qu
  • adapt_site_revertAtomically restore everything the last adapt_site_apply wrote (fragments, the menu doc when the op touched it, index, member configs, routes).
  • get_adapt_status read-onlyRead adapt state: proposal summary + proposalEtag (+ applied/consumed flag), undo-record presence, active or queued job progress. Use to resume in a fresh session.
  • list_content read-onlyList content keys (HTML/md); not assets — use list_assets. Defaults to 50 keys per page: raise limit (max 1000) or pass cursor (nextCursor). Per-row `size`/`missing` are measured only on pages of ≤100 rows; past that the
  • get_content read-onlyRead one content key; optional selector (region) or published=true (live body). Bodies over 40KB without a selector return a truncated summary — use selector, batch_patch_content, or dotsy pull.
  • put_contentStage one content key. Body ≤60KB. Larger pages: stage_content_chunk + apply_changeset bodyStaging, dotsy push, or PUT content-raw. Edits to an existing large page: batch_patch_content.
  • stage_content_chunkAppend one ≤60KB chunk of a large new page. Omit stagingId on seq 0; pass the returned stagingId on later seq. Set finalize:true on the last chunk, then apply_changeset with writes[].bodyStaging.
  • patch_contentEdit one content key via ops[] (selector ops or replace-string; wrap/unwrap/move restructure siblings). Stages draft; op shapes in schema.
  • batch_patch_contentpatch_content on multiple keys; all-or-nothing validation. Preferred edit path for pages over 60KB. replace-string value/replace ≤60KB; whole call ≤80KB.
  • delete_contentDelete content key (tombstone if published). A fragments/* section that pages still place is refused with section_in_use (lists the pages) — detach it or remove it first.
  • rename_contentRe-key a page by slug (draft or published static), server-side hash copy. Default deletes static routes; movePath:true repoints the route, rewrites menu refs, redirects and root-relative / {slug}.dotsy.site hrefs in draf

…and 40 more.

Connect it

Claude Code
claude mcp add --transport http dotsy https://mcp.dotsy.ai/mcp
Claude.ai / ChatGPT
Settings → Connectors → Add custom connector
URL: https://mcp.dotsy.ai/mcp
Cursor (~/.cursor/mcp.json)
{
  "mcpServers": {
    "dotsy": {
      "url": "https://mcp.dotsy.ai/mcp"
    }
  }
}
VS Code (.vscode/mcp.json)
{
  "servers": {
    "dotsy": {
      "type": "http",
      "url": "https://mcp.dotsy.ai/mcp"
    }
  }
}

Questions

What does dotsy do?

Build and publish static sites on dotsy with draft-first MCP tools, OAuth Connect, and API keys. It exposes 80 tools to AI assistants.

What tools does dotsy provide?

80 tools, including create_site, get_site, update_brief, get_plan, get_analytics, set_analytics_provider, get_custom_code, set_custom_code, set_site_icon, update_site, rename_site, publish_site….

How do I connect dotsy to Claude, ChatGPT or Cursor?

Add the remote MCP endpoint https://mcp.dotsy.ai/mcp as a custom connector or MCP server. Copy-paste setup is on this page.

Does dotsy require an account or API key?

No sign-in was needed to list its tools. Individual tools may still need an account or API key.

Is dotsy online?

As of 2026-11-19 our probe found it online. It answered 100% of our last 3 checks.

Who publishes dotsy?

dotsy.ai. The official MCP Registry verified that the publisher controls this domain before accepting the listing.

Similar in News & Content