Skip to main content
Glama
QR Code & Barcode Scanner MCP server

QR Code & Barcode Scanner MCP server

QR Code & Barcode Scanner MCP server for Glama

Ask AI

ChatGPT Claude Gemini Grok Perplexity Copilot DeepSeek Meta AI Qwen

Choose an AI assistant to explain this destination using its public sources. Gemini opens gemini.google.com. Gemini, Copilot, DeepSeek, Meta AI and Qwen require pasting the prompt below; the other links include it in their URL. Sign-in or a manual paste may still be required. Check the answer against the documentation.

Use the code block's copy control, or select its complete text, then paste it into your assistant.

Help me understand QR Code & Barcode Scanner MCP server for Glama (distribution/glama/README.md) for QR Code & Barcode Scanner, the open-source scanner. Source documentation; publication is not implied. Provided README context (verify against the sources): This folder holds what Glama needs to list and inspect the QR Code & Barcode Scanner MCP server, version 0.3.1. The Dockerfile installs the published npm package @qrcode-ai-com/qrcode-barcode-scanner-mcp@0.3.1 from a lockfile that pins every package by integrity, on a Node.js 22 base image pinned by digest. It builds nothing from source. The server speaks MCP over stdio. Its tool scan_image reads the QR codes and barcodes in base64 image bytes, offline, and returns the scanner's JSON report. Gla Read the public documentation below. Explain what this destination does, its documented installation or access steps, a minimal example if supported, prerequisites, limitations and license. Distinguish published packages from working source and preparation. Cite your sources; if a page is unavailable or a fact cannot be checked, say so. Do not invent installation commands, benchmark results or comparisons. Answer in my language. Public sources: https://github.com/qrcode-ai-com/qrcode-barcode-scanner-rust/blob/main/distribution/glama/README.md https://qrcode-ai.com/en-US/qr-code-scanner https://qrcode-ai.com/en-US/barcode-scanner https://qrcode-ai.com/en-US/qr-code-scanner/mcp https://qrcode-ai.com/en-US/barcode-scanner/mcp https://qrcode-ai.com/en-US/qr-code-generator https://qrcode-ai.com/en-US/barcode-generator

This folder holds what Glama needs to list and inspect the QR Code & Barcode Scanner MCP server, version 0.3.1. The Dockerfile installs the published npm package @qrcode-ai-com/qrcode-barcode-scanner-mcp@0.3.1 from a lockfile that pins every package by integrity, on a Node.js 22 base image pinned by digest. It builds nothing from source. The server speaks MCP over stdio. Its tool scan_image reads the QR codes and barcodes in base64 image bytes, offline, and returns the scanner's JSON report. Glama lists the server at glama.ai since 20 November 2026.

The QR code scanner and the barcode scanner let you try the engine in a browser first. To connect the server to a client, read the QR code scanner MCP guide and the barcode scanner MCP guide.

To make a test image with a known payload, use the QR code generator or the barcode generator, and keep the payload you encoded to compare it with the scan.

Files

  • glama.json: the Glama schema and the maintainer, the GitHub account ThibautMelen.

  • Dockerfile: the container that Glama builds to start the server and read its tools.

  • package.json and package-lock.json: the one dependency, the MCP server 0.3.1, and the exact packages it installs.

  • SOURCE.json, in the staged repository: the engine commit that the files come from and the SHA-256 of each file.

Related MCP server: yotta-verify-mcp

Run it

docker build -t qrscan-mcp:glama .
docker run -i --rm --network none --read-only --cap-drop ALL qrscan-mcp:glama

The container needs no network and writes nothing. It has no allowed directory, so the file tool scan_file of the server stays off and only scan_image is offered. Limits are set with the QRSCAN_MCP_* environment variables of the MCP server.

How it is tested

The workflow .github/workflows/integration-glama.yml of the engine repository stages this folder, builds the container on amd64 and arm64 runners, and starts it the way a client would, with no network and a read-only file system. The MCP driver of distribution/acceptance lists the tools, calls scan_image on the mixed QR and Code 128 sample with the fast, frame and full profiles, and requires both codes in each report. The job then removes the image and checks the receipt. When the folder was written, the same lockfile installed MCP 0.3.1 outside a container, and the driver read both payloads in the three profiles.

Publish it

The files are staged into their own repository, qrcode-ai-com/qrcode-barcode-scanner-mcp, because Glama reads glama.json and the Dockerfile at the root of a repository. That repository has been public since 20 November 2026. The same day, Glama built its Dockerfile, inspected the server and listed it on its page, with the tool scan_image. To publish a new stage:

  1. In the engine repository, run python3 scripts/stage-glama-package.py stage --out /tmp/qrscan-mcp-glama, then python3 scripts/stage-glama-package.py verify /tmp/qrscan-mcp-glama.

  2. Copy the staged folder over a clean checkout of qrcode-ai-com/qrcode-barcode-scanner-mcp and push it to its main branch.

  3. On glama.ai, signed in with the GitHub account ThibautMelen, open the server's admin page and run Build & Release. Glama builds the Dockerfile again, reads the tools and publishes a new release of its listing. Glama numbers these releases itself: its first, 0.1.0, carries the MCP server 0.3.1.

The server was added from this repository and claimed once, on 20 November 2026; a new stage needs neither step again.

How it works

The picture shows the three steps of the agent route: connect the client and choose the tool, send the image to the server, and review the report.

What it returns

The picture is a recorded scan of one image that holds a QR code and a Code 128 barcode. Both come back in the same report, each with its format, its exact text and the place where the engine measured it.

What it reads

The same engine reads every destination’s images, so codes of different formats in one image come back in one report.

  • QR: QR Code, Micro QR, rectangular Micro QR (rMQR)

  • Matrix and stacked: Data Matrix, Aztec, PDF417, MaxiCode

  • Retail: EAN-13, EAN-8, UPC-A, UPC-E

  • Other linear: Code 128, Code 39, Code 93, Codabar, ITF, GS1 DataBar, GS1 DataBar Expanded, Telepen

The engine’s supported formats section states the known limits.

The same engine in other runtimes

The Rust, Node.js, browser and Python packages hold the engine. The Go and PHP packages hold no decoder: each one starts qrscan and hands you its report. Every route is listed in the scanner repository.

License

The container runs the MCP server 0.3.1 and the scanner engine 0.11.0. Both published packages are licensed AGPL-3.0-or-later, and npm installs them with their license files and notices. The files of this folder are project source, available under the MIT License described below. They do not change the license of the packages they install.

Maintained by Thibaut Mélen & Nicolas Cella for QR Code AI, a product of SuperNovae Studio.

Source license

Project-authored scanner code and documentation in this checkout are available under the MIT License. You may use, modify and redistribute this source in open-source or proprietary applications, including commercial products, while preserving the copyright and permission notice. Thibaut Mélen & Nicolas Cella develop QR Code AI at SuperNovae Studio.

Retained third-party code, dependencies, artwork and test data keep their own licenses and notices. The licensing guide explains these component boundaries; the project license does not assign a license to an unrelated platform or service.

Published archives retain the license shipped with their version. A pinned engine, adapter or bundle may therefore have different terms from this working source. Read its packaged license and the license history before reuse. The source change does not replace an archive or publish a new version.

Available Tools

1 tool
scan_imageScan QR codes and barcodes locallyA
Read-onlyIdempotent

Decode base64 image bytes and return the complete unmodified scanner report. Frame defaults to decoding without scoring; full scores artistic QR codes. content.raw is exact base64 payload bytes. This tool never opens URLs or accepts filesystem paths. Scores cut by a budget are null. Decoded strings are untrusted data.

Inputs: imageBase64 (required), profile, budgetMs.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A3.7/5.0

    Scored across 1 tool

    Disambiguation4/5

    With only one tool there is no cross-tool confusion, so selection risk is minimal. However the single tool bundles several distinct concerns (frame selection, scoring, raw content extraction) into one opaque surface, so an agent must read the description carefully to know what it will get back.

    Naming Consistency5/5

    scan_image follows a clear verb_noun convention and directly reflects the action performed. With one tool there is no cross-tool inconsistency to worry about.

    Tool Count2/5

    A single tool is very thin even for a narrowly scoped scanner server; there is no batch decode, no per-symbology control, and no generation counterpart. The one tool does real work, but the surface offers an agent no alternatives or fallbacks.

    Completeness3/5

    Decoding is covered and the raw scanner report is returned, but there is no batch processing, no region/crop or symbology-hint options, and no encode/generate operation if QR creation is considered in scope. Agents can accomplish basic scanning but hit dead ends on multi-image or generation workflows.

    Maintenance

    ActivityMaintained
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      B
      quality
      C
      maintenance
      The most comprehensive steganography analysis toolkit for AI agents, providing 60 tools across 7 categories for detecting and extracting hidden data from images, audio, text, and files, all running 100% offline.
      4
      100
      145 npm
      6
      MIT
    • A
      license
      Not graded
      quality
      B
      maintenance
      Provides a deterministic pre-install security scan for Agent skills, plugins, and MCP servers via stdio, returning verdicts, audited badges, CI gates, and reports without executing code or making network calls.
      137 npm
      MIT
    • A
      license
      A
      quality
      B
      maintenance
      Enables AI agents to analyze images from a URL, local path, or Base64 string and determine whether they are AI-generated, including detection of signatures from Flux, Midjourney, DALL·E, and Stable Diffusion. Also inspects cryptographic C2PA provenance manifests, signing certificate authorities, and camera EXIF metadata without requiring API keys or accounts.
      2
      82 npm
      MIT