Dotsy

Q: Is Dotsy MCP server safe?

QAmcp's test on 22 Oct 2026: No hidden instructions were found in its tool descriptions. Its error messages showed no secrets or internal details. 23 of its 60 tools are labeled read-only; the others may change or send things. Overall it scored 90/100 on 22 Oct 2026. A test can only see what the server shows from outside, not what it does with your data behind the scenes. Connect servers from makers you trust.

by dotsy.ai · https://mcp.dotsy.ai/mcp

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

97 tools✓ no account neededPricing: not listed

Visit website

90 /100

PASS · WITH NOTES

12 of 12 checks · 22 Oct 2026

Is Dotsy MCP server safe?

No hidden instructions were found in its tool descriptions.
Its error messages showed no secrets or internal details.
23 of its 60 tools are labeled read-only; the others may change or send things.
Overall it scored 90/100 on 22 Oct 2026.

A test can only see what the server shows from outside, not what it does with your data behind the scenes. Connect servers from makers you trust.

What it can do

60 tools, in the server's own words.

create_site

Create empty site; seeds brief.

get_siteread-only

Site detail, stats, publicUrl, brief head (default-on), and readiness flags.

update_brief

Update `_intent/site.md` (site brief) or a page brief when `page` is set.

get_analyticsread-only

Read-only traffic overview (default) or full breakdowns via include[]; optional bot id for crawler page drill-down.

update_site

Update site settings: title, keyConvention, or editingMode ('live' = each editor save publishes immediately; 'staged' = saves stay drafts until publish_site).

rename_site

Rename the site slug (public hostname {slug}.dotsy.site).

publish_site

Publish draft to live.

get_draft_statusread-only

Pending draft changes: content keys and routes with status.

discard_drafts

Discard unpublished drafts: all (omit key/keys/routes), one content key (key), or a selection (keys, routes).

delete_site

Permanently delete site; confirmSlug must equal slug.

bulk_put_content

Stage many content keys (pages, layouts, fragments).

get_site_manifestread-only

Content keys + hashes only (optional routes=true) — static files live in list_assets, not manifest.

find_replace

Case-insensitive find→replace across pages in one staged commit.

search_contentread-only

Find pages containing a phrase (grep without reading bodies).

graduate_site

Enable site search & collections (kv → do-sqlite), one-way.

apply_changeset

Stage writes[] + deletes[] in one call; attach routes via writes[].route.

import_site_from_url

Import URL to draft.

get_structure_statusread-only

Flat vs structured page counts; informs user — do not auto-run analyze/apply while requiredDecision pending.

structure_site_analyze

Propose shared layout + fragments; persist:false first.

decompose_analyze

Deprecated — use structure_site_analyze.

structure_site_apply

Rewrite flat pages to layout + fragments (draft).

get_structure_resultread-only

Last structure apply job result (structuredKeys, conflicts, partial).

adapt_site_analyzeread-only

Propose nav wiring + blog collectionization for an imported mirror (draft, opt-in).

adapt_site_apply

Apply the adapt proposal (draft): wire nav into the menu store and/or rewrite the blog index to a live .

and 36 more

Test results

Safe mode: only tools labeled read-only were run. How the test works

!
Ready for the newest MCP version
1 warning
- !Uses an older MCP version (2025-11-25). It works today, but it isn't on the July 2026 version (2026-07-28) yet.
note
!
Every tool is described
41 warnings
- !create_site: Inputs with no description: slug, title, keyConvention, purpose, onSlugTaken
- !update_site: Inputs with no description: title, keyConvention
- !discard_drafts: Inputs with no description: key, keys, routes
- !delete_site: Inputs with no description: confirmSlug
- !bulk_put_content: Inputs with no description: title, content
- !get_site_manifest: Inputs with no description: mode, routes, limit, cursor
- !find_replace: Inputs with no description: find, replace, keys, expectPerKey
- !search_content: Inputs with no description: q, limit
- and 32 more
note
✓
ConnectsConnected in 916 ms
pass
✓
Lists its toolsFound 97 tools
pass
✓
Tools are labeled safe or dangerousEvery tool has a safety label
pass
✓
No hidden instructionsNo hidden instructions found in tool descriptions
pass
✓
Tools work with good inputs
All good
- –get_site: Needs you to sign in, so it was not tested (not counted against the server)
- –get_analytics: Needs you to sign in, so it was not tested (not counted against the server)
- –get_draft_status: Needs you to sign in, so it was not tested (not counted against the server)
- –get_site_manifest: Needs you to sign in, so it was not tested (not counted against the server)
- –search_content: Needs you to sign in, so it was not tested (not counted against the server)
- –get_structure_status: Needs you to sign in, so it was not tested (not counted against the server)
- –get_structure_result: Needs you to sign in, so it was not tested (not counted against the server)
- –adapt_site_analyze: Needs you to sign in, so it was not tested (not counted against the server)
- and 32 more
pass
✓
Bad inputs give a clean error
All good
- –get_site: Needs you to sign in, so bad inputs were not tested
- –get_analytics: Needs you to sign in, so bad inputs were not tested
- –get_draft_status: Needs you to sign in, so bad inputs were not tested
- –get_site_manifest: Needs you to sign in, so bad inputs were not tested
- –search_content: Needs you to sign in, so bad inputs were not tested
- –get_structure_status: Needs you to sign in, so bad inputs were not tested
- –get_structure_result: Needs you to sign in, so bad inputs were not tested
- –adapt_site_analyze: Needs you to sign in, so bad inputs were not tested
- and 30 more
pass
✓
Tools work togetherlist_skills → get_skill: get_skill found what list_skills returned (id = "intake")
pass
✓
Fast enough
All good
- ✓Connecting took 916 ms
- ✓Listing tools took 77 ms
- ✓Average tool answer: 34 ms
- ✓get_skill: Slowest tool: get_skill (43 ms)
pass
✓
No secrets leakedChecked 109 error messages: no secrets or internal details
pass
✓
Resources and prompts work
All good (8 resources)
- ✓Opened 8 of 8 resources
- ✓An address that does not exist gets a clean "not found" error
pass

Test it yourself

Free and open source. Same checks, same score.

npx qamcp-cli https://mcp.dotsy.ai/mcp

Score over time

22 Oct 202690

One test so far. New tests will show here.

Reviews

Coming soon: reviews from people who use Dotsy, signed in with GitHub, one per person. Reviews never change the score.

Is this your server?

Soon you can claim this page: re-test it from here, reply to results, and show a "Tested by QAmcp" badge.

Have a concern, or want it removed? Ask us and we'll take it off the list. How the directory works