Reviews
No review yet. Used dotsy? Be the first to help others choose.What it does
dotsy is an MCP server, a connector that lets an AI assistant use it as a tool. It is hosted: an assistant connects to it over the internet, nothing to install.
No capability identified yet from its description.
Facts come from the Official MCP Registry, as declared by the publisher. Capabilities are matched automatically (low confidence). None of this is a test of the tool.
At a glance
How to connect
As declared in the Official MCP Registry · hosted endpoint tested by Electra Index 19h ago (live check)Hosted endpoint
https://mcp.dotsy.ai/mcpstreamable-http
In Claude Code: claude mcp add --transport http dotsy https://mcp.dotsy.ai/mcp
MCP settings (Claude Desktop, Cursor and other MCP clients)
{
"mcpServers": {
"dotsy": {
"url": "https://mcp.dotsy.ai/mcp"
}
}
}Reliability
Re-tested about every 3 days · last check 19h agoObserved endpoint availability: the share of our conclusive checks that got an answer. A request for a key or sign-in counts as an answer (the server is up, its access is protected). Timeouts, unreachable endpoints, server errors and invalid MCP replies count as failures; rate-limited checks and checks during our own incidents are not counted. This is what we observed at each check, not continuous uptime: an outage between two checks may go unseen. The 90-day figure will appear once 90 days of checks exist (checks since 19 Oct 2026). How we measure
Tool changes
Tool tracking since 13 Nov 2026 · test history since 19 Oct 2026PARTIAL TOOL COVERAGE This server lists more than 100 tools and we read the first 100, so we cannot confirm additions or removals and report none.
Changes are confirmed by comparing complete tool lists only, read about every 3 days, and dated by the day we saw them. A renamed tool appears as one removal and one addition.
Live check
Electra Index connected to the hosted endpoint 19h agoONLINE dotsy answered an MCP connection on 20 Nov 2026 and introduced itself as dotsy 0.9.24 (MCP protocol 2025-06-18).
120 tools offered to AI assistants
create_site· Create 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· Site 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/get_site_manifest. Lupdate_brief· Update `_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-only workspace plan and pooled usage; pass slug for this site's add-ons. Call before a large build.get_analytics· Read-only traffic overview (default) or full breakdowns via include[]; optional bot id for crawler page drill-down.set_analytics_provider· Connect 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 snippet. Other tags (get_custom_code· Read 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_code· Set 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 code). Never runs iset_site_icon· Set the favicon from a square image asset. Draft until publish.update_site· Update site settings: title, keyConvention, editingMode, signature ("Made with dotsy" badge; live immediately), trailingSlash, ownSeoFiles, aiTrain, acceptIssues and the language settings. Slug is the hostname — use rename_site. Set editingrename_site· Rename 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 or rename-back. Nevpublish_site· Publish 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 publish those errors:
Show 88 more
get_site_tasks· What needs fixing on a site, from stored checks. Call after writes, before publish_site.get_draft_status· Pending draft changes: content keys and routes with status. May include requiredDecision (publish_confirm) before publish_site.review_changes· Review 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) → mark_ready / unmark (≤5discard_drafts· Discard 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_site· Permanently delete site; confirmSlug must equal slug.bulk_put_content· Stage 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 the inline threshold.get_site_manifest· Content 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_replace· Case-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· Find pages containing a phrase (grep without reading bodies). Requires do-sqlite — graduate_site first if search_unavailable.graduate_site· Enable 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 — unsupported sourceapply_changeset· Stage 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 stale key write nothiimport_site_from_url· Import URL to draft. On complete, response may include requiredDecision — preview then ask mirror vs editable before structure_*.get_structure_status· Flat 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_analyze· Propose shared layout + fragments; persist:false first. Wait for mirror-vs-editable answer if requiredDecision pending.structure_site_apply· Rewrite 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_section with no argget_structure_result· Last structure apply job result (structuredKeys, conflicts, partial).adapt_site_analyze· Propose 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). Wait for mirror-vs-edadapt_site_apply· Apply 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). Queued applies are poladapt_site_revert· Atomically 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 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· List 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 they're ABSENT (never `get_content· Read 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_content· Stage 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_chunk· Append 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_content· Edit one content key via ops[] (selector ops or replace-string; wrap/unwrap/move restructure siblings). Stages draft; op shapes in schema.batch_patch_content· patch_content on multiple keys; all-or-nothing validation. Preferred edit path for pages over 60KB. replace-string value/replace ≤60KB; whole call ≤80KB.delete_content· Delete 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_content· Re-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 draft HTML (as rename_paput_post· Stage a blog post via structured meta+body (?format=post). Key e.g. blog/my-post.html. Declared membership: meta.collections; schedule: meta.visibleAt; SEO title override: meta.seoTitle (card always shows meta.title); custom fields: meta.cuinspect_collection· Collection state — count, server.mode, sample entries, tag (membershipKind, match=) when discovered, name, noun, URL pattern, layout, where listed, post fields used. Pass status/q/cursor/limit (any one, even empty) for a full items[] page ilist_collections· Collections on the site — name, noun, item count (or 'not published yet'), URL pattern, and whether any member is staged. Includes a collection only a draft page lists. Returns a bare array (not wrapped in an object) — pass each row's key vupdate_collection· Rename a collection's display name and/or noun (e.g. the generic 'posts' key shown as 'Recipes' / 'recipe') — cosmetic only, stored separately from the tag that defines membership; doesn't need publish. Provide at least one of name/noun. nunew_post_template· Read-only scaffold for a new post — suggested key/path, membership meta, blank or duplicate body. Then put_post (+ optional put_route).get_collection_schema· Read the site's collection field definitions (`_data/collections.json`, draft view): { schema: { v: 1, collections: { "<key>": { fields[], settings? } } }, hash }. hash is null when no schema exists yet — pass it as put_collection_schema ifput_collection_schema· Replace the whole field schema (draft; publish makes it live). Edit get_collection_schema's output; keys as list_collections gives them ("blog/" or an id). Field: { key, type, label?, help?, required?, unique?, inCard?, default? } — type teset_item_status· Change a roadmap/board item status (stamps dates; on release drafts the changelog post and links both ways). Never hand-edit *At, daysToRelease, or votes.get_board· List board items with status, stamp fields, and baked vote counts (draft overlay included). Live vote totals: site host GET /__dotsy/votes.list_votes· List voters on one board item (voter id + source only — no email).remove_votes· Remove one voter's vote and drop their release subscription for that item.list_suggestions· List form suggestions to moderate (duplicate hints); `about` filters by tool id.moderate_suggestion· Decide one form suggestion from list_suggestions: approve (new draft board item; stages content, does not publish), merge (into an existing board item, subscribes the voter/email) or decline.add_idea· Add an idea from outside the site (draft board item or inbox suggestion). Idempotent on externalRef.list_ideas· Search draft/published board items and open suggestions by title token overlap.infer_collection_schema· Suggest fields for one collection from a sample of its items' meta.custom values (published data, else drafts) — writes nothing. Returns { sampled, suggestions: [{ field: { key, type, options? }, count, samples, defined }], skipped }. Reviereindex_collection· Build/finish collection indexes after publish returns collectionDataPending or collectionSqlPending.preview_page· Verify-only composed HTML check; home preview may include requiredDecision — ask mirror vs editable before structure_*.verify_page· Pre-publish lint (tags, assets, layout, SEO, speed and accessibility). Summary first: health issues grouped by code, each with fix:{tool,args,fill?} — supply the fill args, then call. health.summary counts are whole-site (groups/codes filtepreflight_site· Plan check before publish or large build (counts, plan page cap, seo suggestions; imports: form_unwired advisory, webflow_store blocking). When ok is false, blocking lists the failed suggestion codes. Read-only.start_edit_session· Open a draft session. Returns preview/edit URLs for the person (see linkGuidance). draftEditorUrl only when the site gives AI agents Full access. path defaults to '/'.get_site_outline· Site shape: every layout and shared section (`sections`: fragments/* by name, with page count, whether the file exists and staged-change flag), whether a layout is missing, redirects count, menus grouped by where they show, and collectionsshare_section· Share a repeated block, or move/hide a shared section. No arguments: lists blocks on 3+ pages (likeSection: matches a shared one). sourceKey + selector (selectors: a sibling run): dry run lists pages; dryRun:false shares it. name + suggestidetach_section· Give one page its own copy of a shared section; every other page keeps the shared one. A draft — publish_site to go live. A section the layout places is hidden on that page instead (share_section name + hide).get_route· Get one route by path (home is '/').put_route· Create/replace route; contentKey derived from path if omitted. On a field that accepts null (contentKey, redirectTo, redirectStatus, preserveQuery), sending null clears it back to its default.patch_route· Partial route update (only sent fields change; an OMITTED field is left alone). On a nullable field (contentKey, redirectTo, redirectStatus, preserveQuery), null CLEARS it to its default — unlike omitting it. To set redirectTo/redirectStaturename_page· Change a page's URL: moves route `from` to `to`. Menu links and redirects to the old path retarget; a 301 stays at the old path (leaveRedirect). Root-relative and https://{slug}.dotsy.site/ hrefs in draft HTML are rewritten (linksRewritten;delete_route· Remove a route by path.list_goals· List site conversion goals (pageview paths and form submits). Required before start_test.put_goals· Create or replace all site conversion goals (≤50). Required before start_test when no goal exists.estimate_test· Estimate days to reach promote readiness for a page (traffic baseline). Read-only.start_test· Start a same-URL A/B test (draft or live source). Rules → get_skill('verify') § A/B.promote_experiment· Promote a winning A/B variant to live — explicit user instruction only; see get_skill('verify') § A/B.delete_draft_test· Remove a draft A/B test (releases variant bodies; does not publish).set_experiment_note· Record what was learned from an ended A/B test (≤500 chars; null clears).get_menu· Read a menu's draft items and etag; menu rules → get_skill('nav').put_menu_item· Partial upsert one menu item: send only the fields to change; omitted fields keep their stored value and parent: null moves it to the top level. data/attrs merge per key (data: {desc} keeps data.icon; a null value removes that key). A new idelete_menu_item· Remove one item from a menu (page stays live).reorder_menu· Set final menu order. Pass ifMatch from get_menu; stale → 409 with current items.get_menu_doc· Read the whole menu doc (all menus + shell/template), etag for put_menu_doc, and issues (by item id) — page_not_routable, page_missing, page_dead_link, page_is_redirect — computed from the draft routes, so a link that won't show or leads noput_menu_doc· Replace the whole menu doc (ifMatch from get_menu_doc required). Each item may omit menu — the enclosing menu key in doc is used.list_assets· CMS uploads under assets/ only — not mirrored clone CDN (get_site mirroredAssets or import warmJob). Not content — use list_content. Live in the editor and preview at once; on the live site after the next publish.get_asset· Read one asset (metadata + base64 + stored sha256). sha256 is the stored blob; may differ from upload bodySha256 when IMAGES re-encodes rasters. Live in the editor and preview at once; on the live site after the next publish.bulk_put_assets· Upload 1–200 CMS assets; key = path after /assets/, or sitePath for an exact URL path (e.g. /ads.txt). Each item: exactly one of bodyBase64, bodyText (plain text for .css/.js/.mjs/.json/.svg/.txt/.xml only, not .html), or importFromUrl. Updelete_asset· Delete a static asset by key. The editor and draft preview drop it at once; the published site drops it at the next publish.optimize_assets· Shrink heavy images in place (0.98): JPEG/PNG/still GIF → WebP at the same address, so no HTML changes. keys = site paths from verify_page health.assets[].ref — /assets/… uploads or clone paths like /wp-content/… (1–50 per call). Skips animtranslate_page· Stage draft copies of pages in another language: copied as is, language set, linked to the original as a translation (menus not copied). Then translate the bodies, write them in one apply_changeset, and publish_site. Target path = languagestart_site· Start one draft site with no dotsy account. Returns slug + guestToken — pass guestToken on every later tool call until claim_site.claim_site· Move the guest draft onto your signed-in dotsy account. Requires OAuth Connect; pass the guestToken from start_site.list_skills· Paige build skills (id + whenToUse). Pull get_skill on demand — do not duplicate in tool text.get_skill· Skill body + optional questions[]. Accepts an id OR a synonym (e.g. 'list', 'menu') — resolves aliases and suggests near-misses. Start with intake when ambiguous.submit_feedback· Optional mid-session feedback (required feedback rides with publish_site).get_activity· List site activity or fetch one change diff (pass id). Filters: who, state, actor (me), since, until, limit≤20. Notes from context are visible to everyone on the site — no secrets.list_versions· List the site's published versions, newest first (who, when, pages, live, restorable). Use before restore_version.restore_version· Bring an earlier published version back as unpublished changes (page content only — routes, menus, images and settings stay). version: a number from list_versions, or "previous". dryRun: show what would change. Then review and publish_site,undo_publish· Take back the last publish at once: restores the previous version of the pages it changed and publishes them; the undone changes stay as unpublished changes (`restaged`). On a live-mode site nothing is kept (its next save would republish itrevert_change· Undo one activity event by staging the prior version as draft only — call publish_site to go live. Respects AI access.get_account_context· Account, user, memberships[]. Pass workspace on writes when memberships.length > 1.report_bug· Report a dotsy bug, or ask a support question (kind question — AI answer from the help centre). Bugs attach recent errors and return a ticket id.
The first 100 are shown.
What "online" means: the server answered an MCP connection at the time of the check. It is not a guarantee of security, quality or continuous uptime. How we test: we open an MCP session and ask for the tool list, as an AI assistant would. We never run a tool and never send a key. Re-tested about every 3 days. Method
Is this your server? Monitoring Pro: a check every 30 minutes and an email within the hour when it stops answering. Launch offer: $39.99 once, for life.
Facts & evidence
Each fact shows where it was seen and when.| Fact | Value | Evidence | Source | Last confirmed |
|---|---|---|---|---|
| Version | 0.9.24 | DECLARED | SRC-001 Official MCP Registry | 22h ago |
| Hosted endpoint | https://mcp.dotsy.ai/mcp | DECLARED | SRC-001 Official MCP Registry | 22h ago |
| Local install (package) | no | DECLARED | SRC-001 Official MCP Registry | 22h ago |
| Remote access (hosted) | yes | DECLARED | SRC-001 Official MCP Registry | 22h ago |
| Website | https://dotsy.ai | DECLARED | SRC-001 Official MCP Registry | 22h ago |
| Registry status | active | DECLARED | SRC-001 Official MCP Registry | 22h ago |
| MCP server | yes | DECLARED | SRC-001 Official MCP Registry | 22h ago |
Change history
- VERSION20 Nov 20260.9.23 → 0.9.24
- VERSION20 Nov 20260.9.22 → 0.9.23
- VERSION19 Nov 20260.9.21 → 0.9.22
- VERSION19 Nov 20260.9.20 → 0.9.21
- VERSION18 Nov 20260.9.19 → 0.9.20
- VERSION17 Nov 20260.9.17 → 0.9.19
- VERSION14 Nov 20260.9.16 → 0.9.17
- VERSION14 Nov 20260.9.15 → 0.9.16
- VERSION14 Nov 20260.9.14 → 0.9.15
- VERSION13 Nov 20260.9.13 → 0.9.14
- VERSION13 Nov 20260.9.12 → 0.9.13
- VERSION13 Nov 20260.9.11 → 0.9.12
- VERSION12 Nov 20260.9.8 → 0.9.11
- VERSION12 Nov 20260.9.7 → 0.9.8
- VERSION12 Nov 20260.9.6 → 0.9.7
- VERSION12 Nov 20260.9.5 → 0.9.6
- VERSION12 Nov 20260.9.4 → 0.9.5
- VERSION12 Nov 20260.9.3 → 0.9.4
- VERSION11 Nov 20260.9.2 → 0.9.3
- VERSION10 Nov 20260.9.1 → 0.9.2
- VERSION10 Nov 20260.9.0 → 0.9.1
- VERSION10 Nov 20260.8.17 → 0.9.0
- VERSION10 Nov 20260.8.16 → 0.8.17
- VERSION09 Nov 20260.8.15 → 0.8.16
- VERSION07 Nov 20260.8.14 → 0.8.15
- VERSION06 Nov 20260.8.13 → 0.8.14
- VERSION06 Nov 20260.8.12 → 0.8.13
- VERSION06 Nov 20260.8.11 → 0.8.12
- VERSION06 Nov 20260.8.10 → 0.8.11
- VERSION06 Nov 20260.8.9 → 0.8.10
Is this page accurate?
Flag it and our robot re-checks the official source. Reports never change a score.Is dotsy still online?
Free alerts · no account▲ 0Do you run dotsy? Know when it stops answering
For publishers · optionalIts hosted endpoint can be monitored. Monitoring Pro connects every 30 minutes like an AI assistant, emails you within the hour when it stops answering, keeps a 90-day availability history and adds your answer rate to your badge.
Monitoring never changes a score or a rank.
Questions about dotsy
How do I connect dotsy?
Use the hosted endpoint https://mcp.dotsy.ai/mcp in your assistant's MCP settings. The exact settings are in "How to connect" above, as declared in the Official MCP Registry.
What tools does dotsy offer?
When Electra Index connected on 20 Nov 2026, it listed 120 tools: create_site, get_site, update_brief, get_plan, get_analytics, set_analytics_provider, get_custom_code, set_custom_code and more. The full list is in "Live check" above.
Is dotsy online?
Yes. Its hosted endpoint answered an MCP connection from Electra Index 19h ago.