QAmcp

Copied. Paste it into Claude Code, Cursor or Codex: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

SoonYour score can change any day. QAmcp Monitor tests your server every hour and emails you when it breaks.See what Monitor does →

Directory / Fictura

Fictura

Q: Is Fictura MCP server safe?

QAmcp's test on 29 Oct 2026: No hidden instructions were found in its tool descriptions. Its error messages showed no secrets or internal details. 35 of its 44 tools are labeled read-only; the others may change or send things. Overall it scored 93/100 on 29 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 docs.fictura.co · https://mcp.fictura.co/mcp

Paywalls, onboarding, subscription analytics, A/B tests, attribution and errors for mobile apps.

44 tools✓ no account neededPricing: not listed

Visit website

93 /100

PASS · WITH NOTES

12 of 12 checks · 29 Oct 2026

Is Fictura MCP server safe?

No hidden instructions were found in its tool descriptions.
Its error messages showed no secrets or internal details.
35 of its 44 tools are labeled read-only; the others may change or send things.
Overall it scored 93/100 on 29 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

44 tools, in the server's own words.

search_docsread-only

Full-text search across the Fictura docs, grouped by page.

list_docsread-only

The full documentation index — every page path, grouped by section, with a one-line description.

read_docread-only

The complete markdown of one documentation page.

get_app_setupread-only

The real values needed to wire the Fictura SDK into a codebase: the API base URL, this app's publishable SDK key (gk_…), and the RevenueCat webhook URL.

get_setup_statusread-only

What is actually configured for this app: the setup checklist, every Fictura feature toggle and whether it is on, and which third-party integrations (Stripe, R…

get_analyticsread-only

This app's real numbers.

get_attribution_reportread-only

Where installs and revenue actually came from.

list_usersread-only

The app's users, most recently active first — each with an identity label, event count, last seen, and derived churn state (in_trial, converted, cancelled, exp…

get_userread-only

One user's identity (every stitched device / account / RevenueCat id), event breakdown, churn state and recent activity.

check_entitlementread-only

The authoritative paid/not-paid verdict for one user, unified across Stripe, RevenueCat, App Store and Play — the same answer GET /api/v1/entitlements/{user_id…

get_tracking_planread-only

Every event this app has ever sent, with volume, last-seen, and whether capture is switched off.

list_surfacesread-only

Every paywall and onboarding flow, what is actually being served at each placement (running experiment > live > none), and the valid placement names.

get_surfaceread-only

The full configuration of one paywall or onboarding flow, plus its version history.

list_templatesread-only

The one-click starter templates available for paywalls or onboarding flows, with the template key and what each looks like.

list_experimentsread-only

Every experiment with status and, for running or finished ones, full Bayesian results — exposures, conversions, and the probability each variant is best.

get_experimentread-only

One experiment with its variants and full Bayesian results.

get_acquisition_reportread-only

`roas` gives per-campaign spend, attributed installs/trials/paying users, revenue, CPI, CAC and ROAS, plus blended totals and explicitly-unattributed revenue —…

get_store_analyticsread-only

Store-reported numbers synced from Appfigures: downloads, re-downloads, updates, uninstalls, store revenue after the store's cut (subscriptions, in-app purchas…

list_campaignsread-only

Campaigns read live from a connected ad platform: status, daily budget and ad sets.

list_creatorsread-only

Creator records with a 28-day funnel per creator (clicks, installs, trials, paying users) and the tracking links tagged to each.

get_link_infrastructureread-only

How links reach the app.

get_push_configread-only

Whether push is set up and who could receive it: registered-device counts per billing cohort (all / paid / trial / free) and whether OneSignal is configured.

list_store_productsread-only

This app's auto-renewable subscriptions in App Store Connect: product id, billing period and Apple review state.

list_error_issuesread-only

The error feed: grouped issues with level, status, event and user counts, a 14-day sparkline, plus the app's uptime summary.

and 20 more

Test results

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

!
Every tool is described
5 warnings
- !search_error_issues: Inputs with no description: status, platform, release, limit
- !update_error_issue: Inputs with no description: issue_id, status, resolved_in_release, assignee, priority, note
- !validate_paywall_doc and validate_onboarding_doc have nearly the same description (81% of their words are shared; the only difference: nothing vs "step", "key", "check"), so an AI may not know which to pick
- !save_paywall_doc and save_onboarding_doc have nearly the same description (72% of their words are shared; the only difference: "paywall", "copy", "first" vs "flow", "override", "exit"), so an AI may not know which to pick
- !get_paywall_doc and get_onboarding_doc have nearly the same description (60% of their words are shared; the only difference: "paywall", "studio", "visual" vs "onboarding", "builder", "flow"), so an AI may not know which to pick
note
!
Follows MCP best practices (not scored yet)
2 tips (not scored)
- !7 tools not labeled read-only don't say whether running them twice is safe (idempotentHint): save_paywall_doc, create_paywall_draft, pair_editor, editor_set_doc, unpair_editor, save_onboarding_doc and 1 more
- !2 tools answer with structured data but don't declare its shape (outputSchema): search_docs, list_docs. If those answers change shape, nothing can catch it; with a schema, every answer is checked.
note
✓
ConnectsConnected in 163 ms
pass
✓
Ready for the newest MCP versionUses the latest MCP version (2026-07-28)
pass
✓
Lists its toolsFound 44 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
- ✓search_docs: Worked (179 ms)
- ✓list_docs: Worked (26 ms)
- ✓read_doc: Answered with an error, probably because of our sample input: No documentation page at “test”. Call list_docs to see every page.
- –get_app_setup: Needs you to sign in, so it was not tested (not counted against the server)
- –get_setup_status: 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_attribution_report: Needs you to sign in, so it was not tested (not counted against the server)
- –list_users: 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
- ✓search_docs: Refused missing required input "query" with a clear error
- ✓search_docs: Refused wrong type for "query" with a clear error
- ✓read_doc: Refused missing required input "path" with a clear error
- ✓read_doc: Refused wrong type for "path" with a clear error
- –get_analytics: Needs you to sign in, so bad inputs were not tested
- –get_attribution_report: Needs you to sign in, so bad inputs were not tested
- –list_users: Needs you to sign in, so bad inputs were not tested
- –get_user: Needs you to sign in, so bad inputs were not tested
- and 20 more
pass
✓
Fast enough
All good
- ✓Connecting took 163 ms
- ✓Listing tools took 124 ms
- ✓Average tool answer: 78 ms
- ✓search_docs: Slowest tool: search_docs (179 ms)
pass
✓
No secrets leakedChecked 79 error messages: no secrets or internal details
pass
✓
Resources and prompts workOpened 1 of 1 prompts
pass
–
Tools work togetherNo tool's answer could be fed into another tool, so there were no chains to test (not counted either way)
not tested

Test it yourself

Free and open source. Same checks, same score.

npx qamcp-cli https://mcp.fictura.co/mcp

Show 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.

[![QAmcp score](https://qamcp.dev/s/co-fictura-mcp.svg)](https://qamcp.dev/s/co-fictura-mcp.html)

Score over time

29 Oct 202693

One test so far. New tests will show here.

Reviews

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

Is this your server? Get an alert the moment it breaks.

QAmcp Monitor (coming soon) tests it every hour and emails you when it goes down, the score drops, a tool changes or a secret leaks. You'll also be able to claim this page and get a verified owner mark. Founding price: $19/month for life for the first 50 teams.

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