Fetch and follow the instructions at https://qamcp.dev/setup.md to test my MCP server.Your AI finds your server in your project, tests it with QAmcp, explains what's wrong in plain words, fixes it with your OK, and tests again. Read the instructions
Directory / Skyelight
Skyelight
by skyelight.ai · https://app.skyelight.ai/mcp
Give your AI assistant feedback pinned to the exact element, with its code, so it can fix and reply.
Partial: 10 of 12 checks · 5 Nov 2026
At a glance
- Runs where
- On their server. What you send to it goes to them.
- What you need
- Nothing: it answered without a login
- Tools
- 18 tools
- Its own safety labels
- 10 read-only, 1 labeled as deleting or destroying, 7 labeled as changing things
- Memory it takes
- About 4,200 tokens of your AI's memory, just for its tool descriptions
Tokens are an estimate: the characters in its tool names, descriptions and inputs, divided by 4. The exact number depends on your AI model. Safety labels are what the server says about itself. From our latest test, 5 Nov 2026.
Is Skyelight MCP server safe?
- None of the hidden-instruction wordings we know were found in its 18 tool descriptions.
- Its error messages showed no secrets or internal details.
- 10 of its 18 tools are labeled read-only; the others may change or send things.
- Overall it scored 86/100 on 5 Nov 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 this test does not check
- Its source code and packages.
- What a tool quietly does behind the scenes, such as writing a file or calling another service.
- Instructions hidden inside live tool answers. We only look for those in tool descriptions.
- Hidden instructions worded in a way our list doesn't know yet.
- Tools that could change something. Those are read, never run.
What QAmcp can and can't see · How to tell if an MCP server is safe · Hidden instructions · Prompt injection
Known security advisories
None found in GitHub Security Advisories and OSV.dev on 5 Nov 2026.
That means none were published there, not that there are no problems. QAmcp tests how a server behaves. It does not scan source code.
What it can do
18 tools, in the server's own words.
list_workspacesread-onlyWorkspaces you can reach, with the role you hold in each, and who you are.
list_projectsread-onlyProjects you can reach, newest activity first, across every workspace unless one is named.
list_itemsread-onlyList feedback items (bugs, ideas, comments) people left on a Skyelight project.
search_itemsread-onlyFind items whose thread mentions some text.
post_updateReport back on an item: what you found, what you changed, a link to the PR.
create_itemOpen a new thread on a page, as the person whose connection you are using.
publish_review_linkShare something with Skyelight for review, and get a link people can pin feedback on.
list_membersread-onlyThe people in a workspace: name, email, role and id.
assignHand an item to a person, who is notified the way an assignment in the app notifies them.
set_statusMove an item to open, deferred or resolved.
get_itemread-onlyEverything needed to work one item: the whole thread in order, the page and URL it is on, the anchor identifying the element the person pointed at, and the pic…
project_reviewread-onlyEverything needed to write an accurate project review or hand-off document: the shape of the work, every resolved thread and how it ended, what was deferred an…
whats_newWhat changed on a project since you last looked: new threads, new replies grouped by thread, what was resolved or deferred, and what was assigned to you or men…
find_by_sourceread-onlyFeedback by the code that rendered it, from the file and line the Skyelight build plugin stamps on each element.
find_similarread-onlyHas this already been reported?
merge_itemsFold duplicate items into one, the way merging works in the app: the duplicates leave the list and count as extra reports on the item they were merged into.
decision_logread-onlyThe decisions a project made in its threads, quoted: every thread resolved or deferred after a discussion, with the conversation, plus types people corrected a…
save_ruleKeep a rule the team agreed on ("sentence case in every button", "the brand gray stays, do not raise contrast bugs on it") in the project's context, under Rule…
Test results
Safe mode: only tools labeled read-only were run. How the test works
- !Every tool is describednote
4 warnings
- !search_items: Inputs with no description: status, limit
- !create_item: Inputs with no description: pageTitle
- !set_status: Inputs with no description: status
- !find_by_source: Inputs with no description: status, limit
- !Follows MCP best practices (not scored yet)note
1 tip (not scored)
- !find_by_source: Labeled read-only, but its "file" input is a file path with no pattern, length limit or fixed choices. Make sure the server first resolves the real path (following links and encoded dots like %2e%2e), then refuses anything outside its folde
- !Resources and prompts worknote
1 warning (1 resource)
- !Listing resource templates failed: Error POSTing to endpoint: {"jsonrpc":"2.0","id":24,"error":{"code":-32601,"message":"Unknown method: resources/templates/list"}}
- and 2 more
- ✓ConnectsConnected in 1.1 spass
- ✓Ready for the newest MCP versionUses the latest MCP version (2026-07-28)pass
- ✓Lists its toolsFound 18 toolspass
- ✓Tools are labeled safe or dangerousEvery tool has a safety labelpass
- ✓No known hidden instructionsNone of the hidden-instruction wordings we know were found in tool descriptions. New wordings can get past this check.pass
- ✓Fast enoughpass
All good
- ✓Connecting took 1.1 s
- ✓Listing tools took 436 ms
- ✓No secrets leakedChecked 21 error messages: no secrets or internal detailspass
- –Tools work with good inputsnot tested
Not tested
- –list_workspaces: Needs you to sign in, so it was not tested (not counted against the server)
- –list_projects: Needs you to sign in, so it was not tested (not counted against the server)
- –list_items: Needs you to sign in, so it was not tested (not counted against the server)
- –search_items: Needs you to sign in, so it was not tested (not counted against the server)
- –list_members: Needs you to sign in, so it was not tested (not counted against the server)
- –get_item: Needs you to sign in, so it was not tested (not counted against the server)
- –project_review: Needs you to sign in, so it was not tested (not counted against the server)
- –find_by_source: Needs you to sign in, so it was not tested (not counted against the server)
- and 10 more
- –Bad inputs give a clean errornot tested
Not tested
- –list_projects: Needs you to sign in, so bad inputs were not tested
- –list_items: Needs you to sign in, so bad inputs were not tested
- –search_items: Needs you to sign in, so bad inputs were not tested
- –list_members: Needs you to sign in, so bad inputs were not tested
- –get_item: Needs you to sign in, so bad inputs were not tested
- –project_review: Needs you to sign in, so bad inputs were not tested
- –find_by_source: Needs you to sign in, so bad inputs were not tested
- –find_similar: Needs you to sign in, so bad inputs were not tested
- and 1 more
- –Tools work togetherNo safe tool returned data to start a chain from, so chains were not tested (not counted either way)not tested
Test it yourself
Free and open source. Same checks, same score.
npx qamcp-cli https://app.skyelight.ai/mcpShow this score on GitHub
Free for every server in the directory. Paste this into your README: the badge shows the score from our latest test.
[](https://qamcp.dev/s/ai-skyelight-mcp.html)Score over time
- 5 Nov 202686
One test so far. New tests will show here.
Reviews
Coming soon: reviews from people who use Skyelight, signed in with GitHub, one per person. Reviews never change the score.
QAmcp Monitor tests it every hour and emails you when it goes down, the score drops, a tool changes or a secret leaks. Free for 1 server, no card.
Have a concern, or want it removed? Ask us and we'll take it off the list. How the directory works