Prototyp · Vorschau: alle Server aus der offiziellen Registry, alle 30 Minuten synchronisiert. Bewertungen und Benutzerkonten folgen in einem späteren Schritt.
PopNx MCPMCP-Server für alle, die KI nutzen · in einfachen Worten erklärt

Fictura

von Apex-Byte-TechnologiesVersion 0.1.2i★ –iComputer oder Cloud
Name in der Registryco.fictura/mcp

Installieren

Überblick

Beschreibung vom Entwickler (englisches Original)

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

Die drei Säulen von PopNx MCP

Diese drei werden nie zu einer Punktzahl zusammengefasst: Meinungen, Messungen und Beliebtheit sind verschiedene Dinge.

Was du damit machen kannst

Für diesen Server haben wir noch keine Zusammenfassung in einfacher Sprache geschrieben. Unten stehen die Fakten, die wir aus der Registry gelesen haben.

  • Verbindung: Computer oder Cloud
  • Transport: stdio, Streamable HTTP
  • Kategorie: Marketing & Social Media
  • Das musst du eintragen: FICTURA_MCP_KEY, X-API-Key

Installation

Wähle die KI-App, die du nutzt, und kopiere die Einstellungen.

Bevor du installierst

  • Basischecks: 3 von 3 bestanden
  • Läuft auf dem Server des Entwicklers: Was du fragst, läuft über dessen Server.
  • Kann 47 Dinge (Tools) search_docs, list_docs, read_doc, get_app_setup …
  • Das trägst du selbst ein: FICTURA_MCP_KEY, FICTURA_API_BASE, X-API-Key

Als geheim markierte Werte sind Schlüssel zu deinem Konto. Gib sie nie weiter und füge sie nie in einen Chat ein.

Du brauchst

  • Läuft in der CloudNichts zu installieren; die Verbindung läuft übers Internet
  • npmNode.js installiert (für den Befehl npx)

Welche App nutzt du?

Wähle oben deine App. Wir merken sie uns, damit der Button beim nächsten Mal „In … installieren“ anzeigt.

Diese Adresse braucht einen Schlüssel in einem Header der Anfrage, und das Menü zum Hinzufügen von Connectors kann ihn nicht setzen. Nutze stattdessen Claude Code, Cursor oder VS Code.

Oder führ ihn auf deinem Computer aus

Öffne Claude Desktop → Settings → Developer → Edit Config und füge dies in claude_desktop_config.json ein

{
  "mcpServers": {
    "fictura": {
      "command": "npx",
      "args": [
        "-y",
        "@fictura/mcp"
      ],
      "env": {
        "FICTURA_MCP_KEY": "your-value",
        "FICTURA_API_BASE": "your-value"
      }
    }
  }
}

Führe das in deinem Terminal aus

claude mcp add --transport http fictura https://mcp.fictura.co/mcp --header 'X-API-Key: your-value'

Oder führ ihn auf deinem Computer aus

claude mcp add fictura --env FICTURA_MCP_KEY=your-value --env FICTURA_API_BASE=your-value -- npx -y @fictura/mcp

Trag die leeren Werte ein, bevor du ihn startest.

In Cursor öffnen

Oder kopier die Einstellungen selbst

In .cursor/mcp.json in deinem Projekt oder in ~/.cursor/mcp.json einfügen

{
  "mcpServers": {
    "fictura": {
      "url": "https://mcp.fictura.co/mcp",
      "headers": {
        "X-API-Key": "your-value"
      }
    }
  }
}

Oder führ ihn auf deinem Computer aus

In Cursor öffnen

Oder kopier die Einstellungen selbst

In .cursor/mcp.json in deinem Projekt oder in ~/.cursor/mcp.json einfügen

{
  "mcpServers": {
    "fictura": {
      "command": "npx",
      "args": [
        "-y",
        "@fictura/mcp"
      ],
      "env": {
        "FICTURA_MCP_KEY": "your-value",
        "FICTURA_API_BASE": "your-value"
      }
    }
  }
}

Dein Browser fragt, ob er die App öffnen darf, dann zeigt die App die Einstellungen und bittet dich um Bestätigung. Schlüsselwerte bleiben leer, damit du sie selbst einträgst.

In VS Code öffnen

Oder kopier die Einstellungen selbst

In .vscode/mcp.json in deinem Projekt einfügen

{
  "servers": {
    "fictura": {
      "type": "http",
      "url": "https://mcp.fictura.co/mcp",
      "headers": {
        "X-API-Key": "your-value"
      }
    }
  }
}

Oder führ ihn auf deinem Computer aus

In VS Code öffnen

Oder kopier die Einstellungen selbst

In .vscode/mcp.json in deinem Projekt einfügen

{
  "servers": {
    "fictura": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@fictura/mcp"
      ],
      "env": {
        "FICTURA_MCP_KEY": "your-value",
        "FICTURA_API_BASE": "your-value"
      }
    }
  }
}

Dein Browser fragt, ob er die App öffnen darf, dann zeigt die App die Einstellungen und bittet dich um Bestätigung. Schlüsselwerte bleiben leer, damit du sie selbst einträgst.

Diese Adresse braucht einen Schlüssel in einem Header der Anfrage, und das Menü zum Hinzufügen von Connectors kann ihn nicht setzen. Nutze stattdessen Claude Code, Cursor oder VS Code.

Deine Auswahl bleibt in einem Cookie auf diesem Gerät; kein Konto nötig.

Werte, die du selbst einträgst

  • FICTURA_MCP_KEY geheim env
    Fictura MCP key (fk_mcp_...) from Dashboard > Setup > Coding agents (MCP). Leave it out to sign in with your Fictura account in the browser instead. The documentation tools work either way.
  • FICTURA_API_BASE env
    Override the Fictura API base URL. Leave unset unless Fictura support asks you to change it.
  • X-API-Key geheim HTTP header
    Optional Fictura MCP key (fk_mcp_...) from Dashboard > Setup > Coding agents (MCP). Leave it out to sign in with your Fictura account (OAuth) instead.

Diese Einstellungen werden aus dem Registry-Eintrag des Entwicklers erzeugt. Wenn in der README etwas anderes steht, folge der README.

Was er kann

Tool-Namen und -Beschreibungen genau so, wie der Server sie am 7. Nov. 2026 gemeldet hat. Geschrieben hat sie der Entwickler, nicht wir; wir zeigen sie als reinen Text.

  • search_docs

    Full-text search across the Fictura docs, grouped by page. Use this before answering any 'how do I…' question about the SDK, API, paywalls, entitlements, links or webhooks — the docs are the source of truth and are regenerated on every code change. Returns page paths; pass one to

  • list_docs

    The full documentation index — every page path, grouped by section, with a one-line description. Use it to find the right page when a search term is hard to guess. No API key required.

  • read_doc

    The complete markdown of one documentation page. Accepts a site-relative path such as '/implementation/welcome/sdk-quickstart' (a full docs.fictura.co URL works too). If the path is wrong, the closest real paths come back as suggestions. No API key required.

  • get_app_setup

    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. ALWAYS call this before generating integration code — never leave a placeholder API key in what you write. The SDK key is publi

  • get_setup_step

    What to do for one of Fictura's six setup steps, ready to follow: the instructions, this app's real values (so there is nothing to fill in), the full text of that step's docs pages, and how to check it worked. Call this when a person pastes a setup prompt, and follow what it retu

  • get_setup_status

    Where this app has got to: the six setup steps and which are really done, worked out from data that has arrived, then the billing state, every Fictura feature toggle and whether it is on, and which third-party integrations (Stripe, RevenueCat, Slack, App Store Connect, …) are con

  • update_app_identity

    Saves what the app IS to Apple, Google and the web: the iOS bundle ID and Apple Team ID (which build the Universal Links file), the Android package and signing fingerprints (which build the App Links file), both store addresses and the website. Send only the fields you know. Ever

  • create_tracking_link

    Creates a tracking link and returns its shareable URL. A tap is logged as a click, then redirected to destination_url with the click's id, which is how an install is credited to the link. Use the store address for a real campaign, or the app's own scheme (myapp://) for a link tha

  • get_analytics

    This app's real numbers. `overview` gives headline metrics (users, trials, trial→paid rate, events by name, cancel reasons, 14-day activity). `funnel` gives the ordered conversion funnel with per-step drop-off. `cohorts` compares behaviour across billing outcomes — what converted

  • get_attribution_report

    Where installs and revenue actually came from. `summary` is the headline attribution picture (installs, organic vs non-organic, revenue). `kpis` breaks the same window down by source, campaign, link or day. `installs` lists individual installs with their attribution. Defaults to

  • list_users

    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, expired, billing_issue, grace_period, paused, refunded, none). Capped so a large app does not flood the context; `total` rep

  • get_user

    One user's identity (every stitched device / account / RevenueCat id), event breakdown, churn state and recent activity. Accepts the Fictura master user id, or any identifier the app knows them by — a device id, account id or RevenueCat id.

  • check_entitlement

    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} returns to a server. Note: `environment` is SANDBOX when the verdict rests on test purchases, so always check it before

  • get_tracking_plan

    Every event this app has ever sent, with volume, last-seen, and whether capture is switched off. Use it before adding instrumentation so you reuse the existing event name instead of introducing a near-duplicate — the name chosen here is the same string an experiment later names a

  • list_surfaces

    Every paywall and onboarding flow, what is actually being served at each placement (running experiment > live > none), and the valid placement names. IMPORTANT: read `placements` before writing a placement string into code. The list is configured ∪ observed, so a name that appear

  • get_surface

    The full configuration of one paywall or onboarding flow, plus its version history. Note that configs never contain price strings — prices resolve at render time from the PurchasesAdapter's packages, so never copy a price literal out of (or into) a config.

  • list_templates

    The one-click starter templates available for paywalls or onboarding flows, with the template key and what each looks like. Use this when asked to add a paywall so you pick a real template key rather than inventing one.

  • list_experiments

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

  • get_experiment

    One experiment with its variants and full Bayesian results.

  • get_acquisition_report

    `roas` gives per-campaign spend, attributed installs/trials/paying users, revenue, CPI, CAC and ROAS, plus blended totals and explicitly-unattributed revenue — always keep attributed and blended figures apart when reporting these. `spend` gives raw daily ad-spend rows. `links` li

  • get_store_analytics

    Store-reported numbers synced from Appfigures: downloads, re-downloads, updates, uninstalls, store revenue after the store's cut (subscriptions, in-app purchases, ads), top countries, the ratings snapshot, recent reviews with text, and category chart positions. Money is in micros

  • list_campaigns

    Campaigns read live from a connected ad platform: status, daily budget and ad sets. Returns a not_connected result rather than failing when the provider is not set up. This calls the provider's API, so prefer get_acquisition_report for historical numbers.

  • list_creators

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

  • get_link_infrastructure

    How links reach the app. `app_links` is the most important for integration work: it returns the iOS team id, bundle id, Android package and SHA-256 fingerprints that Fictura serves in the Universal Links / App Links association files, plus ios_ready and android_ready. Get these w

  • get_push_config

    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. Returns counts and configuration only — never device tokens or individual recipients.

  • list_store_products

    This app's auto-renewable subscriptions in App Store Connect: product id, billing period and Apple review state. Use it to check that a paywall references a product that actually exists. Pass subscription_id to also fetch Apple's price ladder for that one product (Apple scopes pr

  • list_error_issues

    The error feed: grouped issues with level, status, event and user counts, a 14-day sparkline, plus the app's uptime summary. Defaults to unresolved issues only. `synthetic: true` marks console lines the SDK captured, not crashes.

  • get_error_issue

    One issue in full: the group, its 50 most recent occurrences with stack traces, release and environment, and 30 days of daily counts. This is the tool to reach for when asked to fix a production error. When the app uploaded source maps, each occurrence also has `stack_resolved` a

  • search_error_issues

    Find issues by text in the title or culprit, platform, or release (first or last seen in). Returns the same rows as list_error_issues, filtered.

  • get_error_issue_brief

    One issue condensed for fixing it: latest stack (resolved when source maps exist), in-app frames, breadcrumbs before it, facets (release, OS, device, screen), cause chain, and a ready-to-use fix prompt.

  • update_error_issue

    Resolve, ignore or reopen an issue, assign it, set its priority, or add a note. Only works when the app allows MCP writes (Issues settings → Let MCP keys change issues).

  • get_trace

    Every span of one trace (app → backend → dependencies) as a tree: names, services, start offsets, durations, HTTP status and errors, plus the error events linked to the trace. Take the trace_id from an occurrence in get_error_issue. Use it to see where the time went or what faile

  • get_paywall_doc

    The JSON document a Studio (visual editor) paywall is made of, with its status and version, plus the reference to the document model. Read this before save_paywall_doc, and edit the document you got rather than writing one from scratch — keep node ids, change only what was asked.

  • validate_paywall_doc

    Runs a document through the same parser and renderer a save uses and reports what is wrong, if anything. Changes nothing.

  • save_paywall_doc

    Replaces a draft paywall's document with the one given, as a new version (History in the dashboard shows it as `mcp: ` and can roll it back). Refused for a live paywall — copy it in the dashboard first. Needs an MCP key that can edit. Products, translations and other settings are

  • create_paywall_draft

    Creates a draft paywall from a Studio template (template_key, from list_templates — the webview ones) or from a document you wrote. It is never made live: going live is done in the dashboard. Needs an MCP key that can edit.

  • pair_editor

    Connects to the paywall editor a person has open, using the 6-character code shown under “Pair an agent” in the Studio. Returns a pairing_id for the editor_* tools. The code works once and for 10 minutes; a pairing lasts 24 hours or until either side stops it.

  • editor_get_doc

    The document exactly as it is on the person's screen (unsaved changes included), which paywall it is, the screen they are on and the node they have selected, plus the document model reference. Read this before editor_set_doc and edit what you got — keep node ids, change only what

  • editor_set_doc

    Replaces the document in the person's open editor with the one given. It is NOT saved: the person sees the change, can undo it, and saves it themselves. The document is validated first and refused with the problems if it does not parse. Needs an MCP key that can edit.

  • unpair_editor

    Stops this pairing. The editor shows that the agent left.

  • get_onboarding_doc

    The JSON document a builder-made onboarding flow is made of, with its status and version, plus the reference to the document model. Read this before save_onboarding_doc, and edit the document you got rather than writing one from scratch — keep step keys and node ids, change only

  • validate_onboarding_doc

    Runs a document through the same parser, step-key check and renderer a save uses and reports what is wrong, if anything. Changes nothing.

  • save_onboarding_doc

    Replaces a draft flow's document with the one given, as a new version (the dashboard's history shows it as `mcp: ` and can roll it back). Refused for a live flow. Needs an MCP key that can edit. Translations, overrides and the exit setting are kept.

  • create_onboarding_draft

    Creates a draft onboarding flow from a document you wrote (see get_onboarding_doc's reference). It is never made live: going live is done in the dashboard. Needs an MCP key that can edit.

  • start_appsflyer_import

    Import everything AppsFlyer holds for this app: installs and the channel, campaign, adset and ad behind each one, in-app events and purchases, uninstalls, reinstalls, ad revenue and retargeting traffic. All twelve raw-data reports are walked; ones the AppsFlyer plan lacks are ski

  • get_appsflyer_import_status

    Whether AppsFlyer is connected, the latest import run (status, progress, rows imported, duplicates skipped, people created, date range covered, error if it stopped), and whether an import has ever finished. Call before start_appsflyer_import so a finished import is not offered ag

  • get_appsflyer_attribution_summary

    What the AppsFlyer import brought in about where people came from: people with an imported attribution, split by media source (organic included) and acquisition vs retargeting, plus the top campaigns. Filters on the install date. Imported verdicts never overwrite an attribution F

Basischecksi

Wir prüfen Informationen, die jeder sehen kann; den Code haben wir nicht gelesen. Checks, die nicht zutreffen, werden nicht mitgezählt. · Geprüft am 7. Nov. 2026

  • ✓ Bestanden

    Entwickler passt zum Repo

    Der Registry-Name wurde über die Domain fictura.co bestätigt (die Registry prüft, wem die Domain gehört)

  • … Noch nicht geprüft

    Wird noch gepflegt

    Dieses Repo haben wir noch nicht von GitHub gelesen

  • … Noch nicht geprüft

    Hat eine Lizenz

    Dieses Repo haben wir noch nicht von GitHub gelesen

  • ✓ Bestanden

    Endpunkt antwortet

    Antwort in 246 ms (HTTP 200)

  • – Nicht zutreffend

    Anmeldung mit OAuth

    Keine Anmeldung nötig

  • ✓ Bestanden

    Keine versteckten Anweisungen in Tool-Beschreibungen

    Wir haben 47 Tool-Beschreibungen gelesen und keine versteckten Anweisungen an die KI gefunden

Im Vergleich mit anderen in Marketing & Social Mediai

  • Mehr Sterne als 0 % der anderen 2984 Server in dieser Kategorie
  • Neuer in der Registry veröffentlicht als 80 % der anderen 2984 Server in dieser Kategorie
  • Basischecks gleich gut wie oder besser als bei 100 % der anderen 2984 Server in dieser Kategorie

Verglichen mit allen aktiven Servern dieser Kategorie in der Registry. Sterne zählen nur, wenn dem Herausgeber das Repo gehört.

Häufige Fragen

Ist Fictura sicher?

Er hat 3 von 3 zutreffenden Basischecks bestanden. Den Code haben wir nicht gelesen. Bevor du einen Schlüssel oder Token hinzufügst, sieh nach, welche Zugriffe der Server verlangt, und nutze einen Schlüssel, der nur die Berechtigungen hat, die du brauchst.

Welche Schlüssel oder Codes braucht er?

Das musst du eintragen: FICTURA_MCP_KEY, X-API-Key

Läuft er auf meinem Computer oder in der Cloud?

Beides geht: Installiere ihn auf deinem Computer oder verbinde dich mit der Cloud-Version.

Wird er noch gepflegt?

Das GitHub-Repo wurde zuletzt – geändert, und die neueste Version (0.1.2) kam vor 8 Tagen in die Registry.

Welche Apps können ihn nutzen?

Apps, die MCP unterstützen, etwa Claude Desktop, Claude Code, Cursor und VS Code. Er verbindet sich per URL, also funktionieren auch Apps, die Remote-MCP-Server akzeptieren, zum Beispiel ChatGPT im Entwicklermodus.

Was kann ich stattdessen nutzen?

In derselben Kategorie: MCP YouTube Transcript, Google Analytics MCP, BibiGPT YouTube Video Summarizer

Alternativen

Server derselben Kategorie von anderen Entwicklern, sortiert nach Sternen.

So liest du eine Karte:★ GitHub-SterneiDrei Säulen: Bewertungen · Checks · NutzungiAktualisiert = neueste Version in der Registry veröffentlichti

Google Analytics MCP

von surendranb

GA4 MCP server for AI agents: schema discovery, server-side aggregation, analysis-ready defaults.

Läuft auf deinem Computer★ 244MITAktualisiert vor 10 Tagen
Installieren

README vom Entwickler

README öffnen

Unverändert aus dem Repo des Entwicklers übernommen. PopNx MCP hat den Inhalt weder geprüft noch empfiehlt es ihn. HTML, Bilder und Skripte wurden entfernt. Links führen von dieser Website weg.

Fictura MCP server

Give your AI agent your mobile app's real paywalls, funnels, experiments, attribution and crashes, and let it build paywall and onboarding drafts you review before anything goes live.

Fictura is the growth platform for Expo and React Native apps: paywalls and onboarding flows built in the Studio editor, subscription analytics and funnels, A/B experiments, attribution and ad spend, deep links, App Store and Google Play analytics, and error tracking with stack traces. This server puts all of it in reach of Claude, ChatGPT, Codex, Cursor, VS Code, Windsurf, Gemini CLI and any other MCP client.

https://mcp.fictura.co/mcp

Streamable HTTP, stateless, JSON responses. https://api.fictura.co/mcp serves the same server.

What your agent can do

AskWhat happens
"Add Fictura to this Expo app and show the onboarding flow at the right placement."Reads the app's real SDK key and API base (get_app_setup), the docs (read_doc) and the placements that exist (list_surfaces), then writes the integration with no placeholders.
"Why did trial-to-paid drop last week? Show me where people leave the funnel."Pulls the funnel with drop-off per step and compares cohorts (get_analytics).
"Fix the top crash in the latest release."Finds the issue, reads its source-mapped stack, breadcrumbs and a fix prompt (list_error_issues, get_error_issue_brief), then edits your code.
"Draft an annual-plan paywall from a template so I can review it in Studio."Picks a real template (list_templates) and creates a draft (create_paywall_draft). You publish it in the dashboard, or don't.

More: "Which campaigns paid back this month?" (get_acquisition_report), "Which experiment is winning, and how sure are we?" (list_experiments), "Are Universal Links set up right?" (get_link_infrastructure).

Connect

One-click

Both buttons add the URL only; sign in with your Fictura account when the editor asks. If the buttons do nothing on your system, open these links directly:

cursor://anysphere.cursor-deeplink/mcp/install?name=fictura&config=eyJ1cmwiOiJodHRwczovL21jcC5maWN0dXJhLmNvL21jcCJ9

vscode:mcp/install?%7B%22name%22%3A%22fictura%22%2C%22type%22%3A%22http%22%2C%22url%22%3A%22https%3A%2F%2Fmcp.fictura.co%2Fmcp%22%7D

Claude (claude.ai, Claude Desktop, Cowork)
  1. Open Customize → Connectors, select + Add, then Add custom connector.
  2. Name it Fictura, paste https://mcp.fictura.co/mcp and select Continue.
  3. Keep the detected sign-in settings, select Add, then connect and sign in with Fictura. To use an MCP key instead, choose No sign in and add the key under Request headers as X-API-Key.

On Team and Enterprise plans an Owner adds the connector first under Organization settings → Connectors, then each member connects.

ChatGPT
  1. Go to chatgpt.com/plugins, select +, then Add custom MCP server.
  2. Enter https://mcp.fictura.co/mcp and choose OAuth for authentication.
  3. Select Create as a plugin, then sign in with Fictura.

Your account or workspace policy must allow custom MCP servers.

Claude Code

Install the plugin from this repository. It adds the server and a skill that makes Claude read your app's real setup before it writes integration code:

claude plugin marketplace add Apex-Byte-Technologies/fictura-mcp

claude plugin install fictura@fictura

Or add only the server:

claude mcp add --transport http fictura https://mcp.fictura.co/mcp

Then run /mcp, pick fictura and sign in. To use an MCP key instead:

claude mcp add --transport http fictura https://mcp.fictura.co/mcp \

--header "X-API-Key: $FICTURA_MCP_KEY"

Codex (CLI, IDE extension, ChatGPT desktop app)
codex mcp add fictura --url https://mcp.fictura.co/mcp

codex mcp login fictura

With an MCP key instead of sign-in, keep the key in an environment variable:

export FICTURA_MCP_KEY=fk_mcp_...

codex mcp add fictura --url https://mcp.fictura.co/mcp --bearer-token-env-var FICTURA_MCP_KEY

The same thing in ~/.codex/config.toml:

[mcp_servers.fictura]

url = "https://mcp.fictura.co/mcp" bearer_token_env_var = "FICTURA_MCP_KEY"

Cursor

Use the button above, or add this to .cursor/mcp.json (project) or ~/.cursor/mcp.json (global):

{

"mcpServers": { "fictura": { "url": "https://mcp.fictura.co/mcp" } } }

With an MCP key, add "headers": { "X-API-Key": "${env:FICTURA_MCP_KEY}" } to the fictura entry.

VS Code

Use the button above to sign in with Fictura. To use an MCP key instead, add this to .vscode/mcp.json; VS Code asks for the key once and stores it securely.

{

"inputs": [ { "type": "promptString", "id": "fictura-mcp-key", "description": "Fictura MCP key (fk_mcp_...)", "password": true } ], "servers": { "fictura": { "type": "http", "url": "https://mcp.fictura.co/mcp", "headers": { "X-API-Key": "${input:fictura-mcp-key}" } } } }

Windsurf

Open the Cascade panel's ... menu, then Open MCP config file, and add:

{

"mcpServers": { "fictura": { "serverUrl": "https://mcp.fictura.co/mcp", "headers": { "X-API-Key": "${env:FICTURA_MCP_KEY}" } } } }

Gemini CLI
gemini extensions install https://github.com/Apex-Byte-Technologies/fictura-mcp

The installer asks for an optional MCP key and keeps it in your system keychain. Change it later with gemini extensions config fictura.

Claude Desktop with a local bridge (npx)

For clients that only run local (stdio) servers, the @fictura/mcp package bridges to the hosted server. In Claude Desktop, open Settings → Developer → Edit Config and add:

{

"mcpServers": { "fictura": { "command": "npx", "args": ["-y", "@fictura/mcp"], "env": { "FICTURA_MCP_KEY": "fk_mcp_..." } } } }

The bridge reads FICTURA_MCP_KEY and, optionally, FICTURA_API_BASE (default https://api.fictura.co). Claude Desktop also supports the custom connector above, which needs no local install.

Authentication

OptionHowBest for
Sign in with Fictura (OAuth 2.1)Add the URL only. Your client opens Fictura's sign-in; on the consent screen you pick one app and an access level (read, or read and edit drafts).Claude, ChatGPT, Claude Code, Codex, Cursor, VS Code
MCP keyCreate one in the Fictura dashboard under Setup → Coding agents (MCP). Send it as Authorization: Bearer fk_mcp_... or X-API-Key: fk_mcp_....CI, scripts, clients without MCP sign-in
NoneConnect without signing in.Reading the Fictura docs before you have an account

Without sign-in or a key, only the three documentation tools work: search_docs, list_docs and read_doc. Every other tool answers with how to connect.

A key is read-only unless you tick Can edit draft paywalls when you create it (those keys start with fk_mcpw_). The AppsFlyer import needs a key created with Can connect and import data. App data over MCP needs an active Fictura subscription with AI access.

Tools

44 tools and one prompt. "Read" tools change nothing.

AreaToolWhat it doesAccess
Docssearch_docsSearch Fictura documentationNo sign-in
Docslist_docsList Fictura documentation pagesNo sign-in
Docsread_docRead a Fictura documentation pageNo sign-in
Setupget_app_setupGet this app's Fictura credentials and endpointsRead
Setupget_setup_statusGet integration and feature statusRead
Setuplist_store_productsList App Store subscription productsRead
Setupget_link_infrastructureGet deep link and tracking domain configurationRead
Setupget_push_configGet push notification configurationRead
Analyticsget_analyticsGet funnel, overview or cohort analyticsRead
Analyticsget_tracking_planGet the event tracking planRead
Userslist_usersList usersRead
Usersget_userGet one user's full historyRead
Userscheck_entitlementCheck whether a user is subscribedRead
Paywalls & onboardinglist_surfacesList paywalls, onboarding flows and placementsRead
Paywalls & onboardingget_surfaceGet one paywall or onboarding flow's configRead
Paywalls & onboardinglist_templatesList built-in paywall and onboarding templatesRead
Paywalls & onboardingget_paywall_docGet a Studio paywall's documentRead
Paywalls & onboardingvalidate_paywall_docCheck a paywall document without saving itRead
Paywalls & onboardingsave_paywall_docSave a DRAFT paywall's documentEdit drafts
Paywalls & onboardingcreate_paywall_draftCreate a new DRAFT Studio paywallEdit drafts
Paywalls & onboardingget_onboarding_docGet an onboarding flow's documentRead
Paywalls & onboardingvalidate_onboarding_docCheck an onboarding document without saving itRead
Paywalls & onboardingsave_onboarding_docSave a DRAFT onboarding flow's documentEdit drafts
Paywalls & onboardingcreate_onboarding_draftCreate a new DRAFT onboarding flowEdit drafts
Studio editorpair_editorPair with an open Studio editorRead
Studio editoreditor_get_docRead the document open in the paired editorRead
Studio editoreditor_set_docPut a document on the paired editor's canvas (not saved)Edit drafts
Studio editorunpair_editorEnd the pairing with the editorRead
Experimentslist_experimentsList experimentsRead
Experimentsget_experimentGet one experimentRead
Acquisitionget_attribution_reportGet attribution, install and KPI reportingRead
Acquisitionget_acquisition_reportGet paid acquisition performanceRead
Acquisitionlist_campaignsList live ad campaignsRead
Acquisitionlist_creatorsList creators and their performanceRead
Storeget_store_analyticsGet App Store and Google Play analytics (Appfigures)Read
Errorslist_error_issuesList error issuesRead
Errorssearch_error_issuesSearch error issuesRead
Errorsget_error_issueGet one error issue with stack tracesRead
Errorsget_error_issue_briefGet an issue brief and a fix promptRead
Errorsupdate_error_issueChange an error issueWrite, if the app allows it
Errorsget_traceGet one distributed traceRead
AppsFlyer importget_appsflyer_import_statusGet AppsFlyer import statusRead
AppsFlyer importstart_appsflyer_importStart the AppsFlyer importWrite, import key
AppsFlyer importget_appsflyer_attribution_summarySummarize imported AppsFlyer attributionRead

Prompt: integrate_fictura_sdk

Nur der Anfang wird gezeigt; den Rest findest du im Repo

PopNx fragen