CodeQR MCP server
Commit 24. Okt. 2026Erstelle und verwalte Short Links, dynamische QR-Codes und Klick-Analysen direkt über einen AI-Client.
Auch bekannt als codeqr-io/codeqr-mcp-remote, codeqr-mcp-remote
- Stars
- 0
- Tools
- 14
- Downloads, 30 Tage
- —
- Neueste Version
- 0.1.0
- Letzter Commit
- 24. Okt. 2026
- Lizenz
- —
Was ist CodeQR MCP?
Erstelle und verwalte Short Links, dynamische QR-Codes und Klick-Analysen direkt über einen AI-Client. Er stellt 14 Tools bereit, etwa create_link, list_links, get_link_info.
Zusammenfassung generiert aus dem README des Projekts
Über CodeQR MCP server
Mit CodeQR kannst du Short Links, dynamische QR-Codes und Klick-Analysen direkt über einen AI-Client verwalten. Dieser Remote MCP server ermöglicht es Entwicklern, über Tools wie create_link, create_qrcode und get_analytics mit der CodeQR API zu interagieren. Er ist für die Nutzung mit ChatGPT, OpenAI Agents SDK, Grok und jedem Client konzipiert, der Streamable HTTP transport unterstützt.
Die Sicherheit wird über OAuth 2.0 Authentifizierung geregelt, sodass keine API-Keys manuell vom Nutzer verwaltet werden müssen. Stattdessen nutzt der Client einen Consent-Screen, auf dem du ein spezifisches Projekt auswählst, um den Zugriff zu gewähren. Der Server unterstützt langlebige Sessions, die sich transparent erneuern, sodass die Verbindungen bis zu einem Jahr lang aktiv bleiben. Für Production-Deployments auf Plattformen wie Vercel wird die Nutzung von Upstash Redis empfohlen, um Autorisierungscodes und Tokens über serverlose Aufrufe hinweg zu persistieren.
Über die einfache Erstellung hinaus unterstützt der Server fortgeschrittene Funktionen wie Smart Rules für bedingtes Routing und Traffic Splitting für A/B-Tests. Wenn der Host MCP Apps unterstützt, können Nutzer interaktive Item-Cards und Analytics-Dashboards direkt innerhalb des Chat-Interfaces ansehen.
Was du damit machen kannst
- 1Dynamische QR-Codes generierenErstelle QR-Codes für URLs, WLAN-Zugangsdaten, Visitenkarten oder Krypto-Transaktionen.
- 2A/B-Tests durchführenRichte Traffic Splitting über mehrere Ziele hinweg mithilfe von Smart Rules ein.
- 3Link-Performance überwachenFrage Klick-Analysen ab, um zu sehen, wie deine Short Links und QR-Codes performen.
- 4Bestehende Assets verwaltenÄndere das Ziel eines QR-Codes, ohne den physischen Code neu drucken zu müssen.
Geschrieben aus dem README des Projekts. Jeder Use Case wurde gegen ein Zitat daraus geprüft.
So installierst du CodeQR MCP
Formate geprüft am 10. Nov. 2026Zu Cursor hinzufügenZu Goose hinzufügenCodeQR MCP in Claude Code installieren
$ claude mcp add --transport http codeqr-mcp-remote https://mcp.codeqr.io/mcpCodeQR MCP in Cursor installieren
~/.cursor/mcp.json
{
"mcpServers": {
"codeqr-mcp-remote": {
"url": "https://mcp.codeqr.io/mcp"
}
}
}CodeQR MCP in VS Code installieren
.vscode/mcp.json
{
"servers": {
"codeqr-mcp-remote": {
"type": "http",
"url": "https://mcp.codeqr.io/mcp"
}
}
}CodeQR MCP in VS Code CLI installieren
$ code --add-mcp '{"name":"codeqr-mcp-remote","type":"http","url":"https://mcp.codeqr.io/mcp"}'CodeQR MCP in Codex installieren
$ codex mcp add codeqr-mcp-remote --url https://mcp.codeqr.io/mcpCodeQR MCP in Codex config.toml installieren
~/.codex/config.toml
[mcp_servers.codeqr-mcp-remote] url = "https://mcp.codeqr.io/mcp"
CodeQR MCP in Gemini CLI installieren
$ gemini mcp add -s user --transport http codeqr-mcp-remote https://mcp.codeqr.io/mcpCodeQR MCP in Gemini settings.json installieren
~/.gemini/settings.json
{
"mcpServers": {
"codeqr-mcp-remote": {
"url": "https://mcp.codeqr.io/mcp",
"type": "http"
}
}
}CodeQR MCP tools 14
Erkannt aus dem READMEcreate_linklist_linksget_link_infoupdate_linkdelete_linkcreate_qrcodelist_qrcodesupdate_qrcodedelete_qrcodeget_analyticslist_domainslist_tags
| create_link | — | |
| list_links | — | |
| get_link_info | — | |
| update_link | — | |
| delete_link | — | |
| create_qrcode | — | |
| list_qrcodes | — | |
| update_qrcode | — | |
| delete_qrcode | — | |
| get_analytics | — | |
| list_domains | — | |
| list_tags | — |
Alle 14 Tools anzeigenWeniger Tools anzeigen
create_tagget_workspace
| create_tag | — | |
| get_workspace | — |
Konfiguration
PRIVATE_KEY
| Name | Beschreibung | Typ |
|---|---|---|
| PRIVATE_KEY | — |
Automatisierte Checks
Geluften am 14. Nov. 2026Vollständiger Bericht →Noch nicht verifiziert. Ein Server benötigt einen Score von 80, keine kritischen Befunde und genug Daten für unsere Prüfung. Wie die Checks funktionieren · Was du für mehr Punkte verbessern kannst
- Source Repository verknüpft und erreichbarcodeqr-io/codeqr-mcp-remote is public and reachablegithub.com/codeqr-io/codeqr-mcp-remote ↗Bestanden
- Paket nennt dieses Repository als QuelleNicht geprüft
- Build-Provenienz (Sigstore-Attestierung)Nicht geprüft
- Open Source Lizenz (OSI)No licenseBefund
- Commit oder Release im letzten JahrLast commit or release 2026-10-24github.com/codeqr-io/codeqr-mcp-remote ↗Bestanden
- OpenSSF ScorecardNicht geprüft
- Package-Name ähnelt keinem populären PackageNicht geprüft
- Keine kritischen Advisories im Paket oder seinen AbhängigkeitenNicht geprüft
- Keine versteckten Anweisungen an das Modell14 tool descriptions and the README read; no override phrases, credential paths or hidden charactersBestanden
- Destruktive Tools sind markiertNicht geprüft
- Remote-Endpoint beantwortet den MCP-HandshakeHTTPS endpoint answered 401 (sign-in required)Bestanden
README
Auf GitHub ansehenCodeQR Remote MCP Server
Remote MCP server for CodeQR with OAuth 2.0 authentication. Compatible with ChatGPT, OpenAI Agents SDK, Grok (xAI), and any MCP client supporting Streamable HTTP transport.
How It Works
┌──────────┐ ┌─────────────────────┐ ┌──────────┐
│ ChatGPT │ │ CodeQR MCP Remote │ │ CodeQR │
│ or any │─────▶│ │─────▶│ API │
│ MCP │◀─────│ OAuth 2.0 + MCP │◀─────│ │
│ client │ │ Streamable HTTP │ │ │
└──────────┘ └─────────────────────┘ └──────────┘
- Client discovers auth endpoints via
/.well-known/oauth-protected-resource - Client registers dynamically via
POST /oauth/register GET /oauth/authorizeshows this server's consent screen — the app's self-declared name, marked unverified unless its exact redirect URI is listed insrc/oauth/verified-clients.ts, and the host that redirect URI points at. On approval the user goes to CodeQR, where they log in, choose which project to grant access to, and approve — no API key is ever handled. The callback only completes in the browser that approved.- CodeQR returns them to
GET /oauth/callback, which trades the code for an access + refresh token pair - Client exchanges authorization code for access token (PKCE)
- Client sends MCP tool calls with Bearer token to
POST /mcp
The CodeQR access token lasts 7 days and is renewed transparently. Each
renewal gives the session another 120 days, so a connection in use does not
expire on a fixed date; an idle one ends 120 days after its last renewal, and
none outlives one year from when it was made (the expires_in the client is
given).
Quick Start
# Install dependencies
npm install
# Set environment variables
cp .env.example .env
# Edit .env with your SERVER_URL
# Development
npm run dev
# Production
npm run build
npm start
Deploy
Vercel (Recommended)
The project is configured for Vercel serverless functions:
# Install Vercel CLI
npm i -g vercel
# Deploy
vercel
# Set environment variables in Vercel dashboard:
# - SERVER_URL — Your public server URL (e.g., https://mcp.codeqr.io)
# - UPSTASH_REDIS_REST_URL — From your Upstash Redis database (REST API)
# - UPSTASH_REDIS_REST_TOKEN — From your Upstash Redis database
# - CODEQR_OAUTH_CLIENT_ID — client_id of the OAuth app registered in CodeQR
# - CODEQR_OAUTH_CLIENT_SECRET — its client_secret
# - CODEQR_APP_URL — Dashboard origin (default: https://app.codeqr.io)
# - MCP_UI_ENABLED — Set to 1 to show the item card in hosts that render MCP Apps (off when unset)
# - STAINLESS_API_KEY — Optional Stainless API key
# - LOG_LEVEL — Log level (default: info)
The app will be available at https://your-project.vercel.app. All routes are handled by the serverless function at api/server.ts.
OAuth storage: Set Upstash Redis (UPSTASH_REDIS_REST_URL and UPSTASH_REDIS_REST_TOKEN) so authorization codes, access tokens, and registered clients persist across serverless invocations. If these variables are omitted, the server falls back to an in-memory store (fine for local development only).
Docker
docker build -t codeqr-mcp-remote .
docker run -p 3000:3000 -e SERVER_URL=https://mcp.codeqr.io codeqr-mcp-remote
Railway / Render / Fly.io
Set environment variables:
SERVER_URL— Your public server URL (e.g.,https://mcp.codeqr.io)UPSTASH_REDIS_REST_URL/UPSTASH_REDIS_REST_TOKEN— Recommended for multi-instance or restartsPORT— Port (usually set automatically by the platform)
Connect to ChatGPT
- Deploy this server to a public URL
- In ChatGPT, go to Settings > Advanced > Developer Mode
- Go to the Connectors tab
- Click Add Connector
- Enter your server URL (e.g.,
https://mcp.codeqr.io/mcp) - ChatGPT will auto-discover the OAuth endpoints and prompt you to authorize
Connect to OpenAI Agents SDK
from openai import OpenAI
client = OpenAI()
response = client.responses.create(
model="gpt-4o",
tools=[{
"type": "mcp",
"server_label": "codeqr",
"server_url": "https://mcp.codeqr.io/mcp",
"require_approval": "never",
}],
input="Create a short link for https://codeqr.io",
)
Available Tools
| Tool | Description |
|---|---|
create_link |
Create a shortened link |
list_links |
List all short links |
get_link_info |
Get link details |
update_link |
Update a link |
delete_link |
Delete a link |
create_qrcode |
Create a dynamic QR code encoding a URL, Wi-Fi credentials, a contact card, WhatsApp, email, SMS, a phone number, text or a crypto request |
list_qrcodes |
List all QR codes |
update_qrcode |
Change where an existing QR code points, without reprinting it |
delete_qrcode |
Delete a QR code; printed copies stop resolving |
get_analytics |
Query click analytics |
list_domains |
List custom domains |
list_tags |
List tags |
create_tag |
Create a tag |
get_workspace |
Read the authorized workspace: name, slug and plan |
Conversion event tools are not offered. track_lead and track_sale need the
conversions.write scope, which CodeQR grants to workspace owners only, and
requesting it makes CodeQR reject the whole authorization for everyone else.
The per-link trackConversion toggle is a links.write field and IS exposed
on create_link/update_link (plans that include conversion tracking only).
Smart rules are exposed on create_link/update_link as rules: conditional
routing by any of the twelve attributes the API implements, and traffic
splitting across 2-4 destinations, which is how an A/B test is expressed — one
rule with no condition and a split. Where the workspace doesn't have smart
rules enabled, the API rejects the whole call — the create or update fails
outright, so no link or QR code is created without the rules it asked for —
and the server doesn't forward that rejection as-is: it reports that smart
rules aren't enabled on this workspace, with a link to details.
src/plan-limit-message.ts recognizes plan wording it knows: a capability
gate like this one becomes "isn't enabled on this workspace", a quota becomes
"has reached its limit of N …"; anything it doesn't recognize passes through
unchanged. Four of the field's invariants cannot be stated in JSON Schema
(weights totalling 100, url xor split, the all-or-nothing condition, the
unconditional rule coming last), so they are checked in src/smart-rules.ts
before the request is sent — which saves a round-trip and answers in a
sentence, rather than the serialized error body the SDK surfaces.
The trap worth knowing: value is compared whole and case-insensitively
against what the request carries, which for three attributes is narrower than
the name suggests. device is the operating system (iOS, Android,
Windows, Mac OS, Linux — never mobile), language a two-letter code,
referrer a bare domain. A wrong value is not an error anywhere: the API
accepts any string and the rule silently never matches.
create_qrcode/update_qrcode also take title and walletPass. title
sets the QR code's display title and is printed in large type on the
Google/Apple Wallet pass saved from the code (replacing "QR Code"). Within
walletPass, name and logo override the workspace name and logo shown on
that pass, and barcodeText sets the text shown under the QR code, e.g. a
member name or card number; when it is absent, CodeQR sends no text for that
line — the title is never repeated there. Custom branding is only available
on plans that include it, and never during a trial: a new non-null
walletPass is rejected with 403 on any other plan or during a trial, while
null (clearing it) is always accepted. Outside those plans, or during a
trial, a stored value is ignored when the pass is built, so passes fall back
to the workspace name and logo. logo is
an https URL: the API downloads it and stores its own copy, so the response
returns that copy's URL, not the one sent. barcodeText is 1-40 characters
after trimming. On update_qrcode, an object replaces the stored value as a
whole (a field left out of it is cleared, not merged) — send name, logo
and barcodeText together to keep all three; null clears the override and
reverts to the workspace branding, the same way rules: null ends a running
smart-rules test.
Interactive cards (MCP Apps)
With MCP_UI_ENABLED=1, hosts that render MCP Apps
(ChatGPT, Claude) show a card for the QR code or short link returned by
create_qrcode, update_qrcode, create_link, update_link and
get_link_info: its image, short link with a copy button, whether it is
dynamic, the destination and the scan or click count, plus a button to open it
in the CodeQR dashboard and one that asks how many scans or clicks it had.
- The tools'
_meta.ui.resourceUripoints atui://codeqr/item-card.v1.html, served throughresources/read(src/widgets/). Each read is logged asmcp.resource_read. - The result carries
structuredContent(an allowlist of fields; hosts show it to the model too) and_meta["io.codeqr/card"](image and dashboard URLs, for the card only).contentis unchanged, for clients without UI. get_analyticsgets an analytics card (ui://codeqr/analytics.v1.html): what is counted and for which period, the total, a trend line or the top five rows, and a button to open the analytics in the dashboard. Its 24h / 7d / 30d chips re-run the call from inside the card through the host (tools/call), only when the host says it can, and only with intervals every plan can read.- The pages live in
web/item-card/andweb/analytics/, with the bridge to the host inweb/shared/.yarn widgets:buildbundles them intosrc/widgets/generated/, which is committed;yarn verifyfails when it is stale. To look at them in a browser, runnode scripts/build-widgets.mjs --html, serveweb/dev/and openharness.html?fixture=qr&theme=dark&locale=pt-BR&width=375orharness.html?widget=analytics&fixture=countries&interval=30d.
Unset, the tool list, the resource list and every result are what they were.
API Endpoints
| Method | Path | Auth | Description |
|---|---|---|---|
| GET | /health |
No | Health check |
| GET | /.well-known/oauth-protected-resource |
No | OAuth resource metadata (RFC 9728) |
| GET | /.well-known/oauth-authorization-server |
No | OAuth server metadata (RFC 8414) |
| POST | /oauth/register |
No | Dynamic client registration (RFC 7591) |
| GET | /oauth/authorize |
No | Consent screen: which app, and where access is sent |
| POST | /oauth/authorize |
No | Consent decision; on approval redirects to CodeQR |
| GET | /oauth/callback |
No | Return leg from CodeQR |
| POST | /oauth/token |
No | Token exchange |
| POST | /mcp |
Bearer | MCP Streamable HTTP endpoint |
Architecture
src/
├── index.ts # Express app & server startup
├── config.ts # Environment configuration
├── oauth/
│ ├── store.ts # OAuth state: Upstash Redis or in-memory fallback
│ └── pkce.ts # PKCE S256 verification
├── middleware/
│ └── auth.ts # Bearer token validation middleware
└── routes/
├── well-known.ts # OAuth discovery metadata endpoints
├── oauth.ts # Authorization & token endpoints
└── mcp.ts # MCP tool definitions & handlers
Production Considerations
- OAuth persistence: Configure Upstash Redis (see
.env.example) for serverless and multi-instance deployments. Without it, the in-memory store is used (single process only). - Add rate limiting to the OAuth and MCP endpoints
- Add HTTPS (usually handled by your reverse proxy / platform)
- Add monitoring (the
/healthendpoint is ready for probes) - Consider token rotation for long-lived sessions
Publishing to the MCP Registry
This server is listed in the official registry as io.codeqr/codeqr. The registry
stores only the metadata in server.json — never the code.
Publishing is authorized by DNS: a TXT record on the apex of codeqr.io holds
the public half of an Ed25519 key pair. Apex, not a selector — MCP DNS auth follows
SPF-style placement, and a record under _mcp-auth. fails with a generic signature
error that does not name the cause.
# 1. Bump the version in package.json, src/config.ts and server.json together.
# `yarn test` fails if they drift — the registry refuses to republish a
# version it already has.
#
# Then bump it in the CodeQR app too: the Server Card at
# app/.well-known/mcp/server-card.json/route.ts advertises this server's
# version, and no test can reach across repos to check. It already drifted
# once, to a release that never existed.
# 2. Authenticate with the private key (kept outside this repo).
PRIVATE_KEY="$(openssl pkey -in /path/to/codeqr-io.pem -noout -text | grep -A3 "priv:" | tail -n +2 | tr -d ' :\n')"
mcp-publisher login dns --domain codeqr.io --private-key "$PRIVATE_KEY"
# 3. Publish, then confirm the entry is live.
mcp-publisher publish
curl "https://registry.modelcontextprotocol.io/v0/servers?search=codeqr"
If the key is ever rotated, remove the old TXT record — a stale one is tried first and makes verification fail.
Directory listings
Aggregators crawl the ecosystem and list servers whether or not anyone claims them, so an unclaimed entry still exists — as a bot's guess at what this server does. Claiming replaces the guess and unlocks editing the name and description a reader sees. None of this is done by merging a file; each one is a one-time action on the aggregator's own site.
| Directory | How ownership is claimed | Status |
|---|---|---|
| Official MCP Registry | mcp-publisher + DNS, as above |
listed |
| Glama | glama.json in this repo, then run the claim flow once from an account listed in maintainers |
file in repo; claim pending |
| Smithery | smithery mcp publish https://mcp.codeqr.io/mcp -n <org>/<name> |
pending |
| PulseMCP | hand-reviewed submission on their site | pending |
| mcp.so | submission form / GitHub issue | pending |
The GitHub OAuth route Glama also offers only associates repos under a personal
account, which this repo is not — it belongs to the codeqr-io org. Hence the file.
License
MIT — CodeQR
CodeQR MCP Fragen
Wie füge ich CodeQR MCP zu Claude Code hinzu?
Führe claude mcp add --transport http codeqr-mcp-remote https://mcp.codeqr.io/mcp in deinem Terminal aus. Füge --scope user hinzu, damit der Server in jedem Projekt verfügbar ist.
Wie füge ich CodeQR MCP zu Cursor hinzu?
Öffne ~/.cursor/mcp.json und füge den Server unter mcpServers hinzu, mit der Cursor-Config aus dem Installationsabschnitt oben.
Welche Tools bietet CodeQR MCP?
Er stellt 14 Tools bereit, darunter create_link, list_links, get_link_info, update_link, delete_link.
Benötigt dieser Server einen API-Key?
Nein, er nutzt OAuth 2.0 Authentifizierung, bei der du den Zugriff über einen Consent-Screen bestätigst. Ein API-Key muss also nie manuell gehandhabt werden.
Kann ich einen bestehenden QR-Code aktualisieren, ohne ihn neu drucken zu müssen?
Ja, du kannst das Update-Tool nutzen, um das Ziel eines bereits existierenden QR-Codes zu ändern.
Was passiert, wenn ich Upstash Redis nicht für die Speicherung verwende?
Der Server nutzt dann einen In-Memory-Store als Fallback, was jedoch nur für die lokale Entwicklung geeignet ist.