useqr-mcp
Generates QR codes as SVG markup or writes them to .svg files (via the generate_qr_code tool or the generate --format svg CLI), letting agents produce scalable vector QR codes for any URL or text.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@useqr-mcpmake me a QR code PNG for https://example.com"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
useqr-mcp
Generate a static QR code from any AI agent. No account. No API key.
npx -y useqr-mcp generate --data https://example.com --out qr.pngThis repository is the agent-facing QR generator for useqr.co. It writes PNG or SVG locally. Styled dots, logos, and dynamic /r/{code} short links stay on the product site.
Install and discovery
npm:
useqr-mcpOfficial MCP registry name:
io.github.aaronte/useqr-mcpHosted remote:
https://useqr.co/api/mcpSearch:
curl "https://registry.modelcontextprotocol.io/v0.1/servers?search=useqr"
npx -y useqr-mcpNo arguments (or mcp) starts the stdio MCP server. Source install still works: npx -y github:aaronte/useqr-mcp.
Related MCP server: QRzap MCP Server
MCP
Stdio (works in Cursor, Claude, Copilot, and other clients that spawn a command):
{
"mcpServers": {
"useqr": {
"command": "npx",
"args": ["-y", "useqr-mcp"]
}
}
}Hosted Streamable HTTP (same tools, nothing to install):
{
"mcpServers": {
"useqr": {
"url": "https://useqr.co/api/mcp"
}
}
}stdio-only clients can wrap the hosted server with mcp-remote:
{
"mcpServers": {
"useqr": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://useqr.co/api/mcp"]
}
}
}Tools
Tool | What it returns |
| PNG image or SVG markup for any URL or text |
| Link to the free designer at useqr.co, optionally prefilled |
| Instructions only. Does not mint a tracked short link |
CLI
npx -y useqr-mcp generate --data https://example.com --format svg --out qr.svg
npx -y useqr-mcp helpnpx -y useqr-mcp with no arguments starts the MCP stdio server.
What this is not
This is not the UseQR product app. Accounts, billing, public pages, and destination edits live at useqr.co. See useqr.co/mcp for the hosted server card and product brief.
The live product card uses namespace co.useqr/mcp. This OSS listing uses the GitHub namespace io.github.aaronte/useqr-mcp and points at the same hosted remote.
License
MIT
Available Tools
3 toolscreate_dynamic_qr_codeHow to create a dynamic QR codeAInspect
Explain how to create a trackable dynamic QR on useqr.co. This tool does not mint codes.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full behavioral burden, and it does disclose one important trait: this tool is informational and produces no side effects, unlike a code-minting tool. It says nothing about what the response contains (steps, link, explanation text) or whether any account/site state is required.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two short sentences, zero padding, with the core action first and the critical disambiguation second. Nothing could be removed without losing routing information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a zero-parameter informational tool this is close to adequate, but with no output schema the description should say what the caller gets back (guidance text? a link? steps?). The agent knows what the tool does and doesn't do, but not what it returns.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The tool takes zero parameters, so per the rubric the baseline is 4. There is no parameter semantics to clarify and the schema (vacuously 100% covered) leaves nothing undocumented.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description gives a specific verb ('Explain') and resource ('a trackable dynamic QR on useqr.co'), and it explicitly carves out what it is NOT ('does not mint codes'), which functionally separates it from generate_qr_code. It stops short of naming the sibling tool that actually mints codes, so an agent still has to infer the mapping.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
There is a genuine when-not signal ('This tool does not mint codes'), which implies generate_qr_code is the right choice for actually producing a code. However, no alternative is named and no positive when-to-use condition (e.g. 'call this when the user asks how tracking works') is stated, leaving the routing implicit.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
generate_qr_codeGenerate a static QR codeAInspect
Encode text or a URL as a local static QR image (PNG) or SVG markup. Does not create a dynamic or trackable code.
| Name | Required | Description | Default |
|---|---|---|---|
| data | Yes | Text or URL to encode, max 2000 characters | |
| size | No | Pixel size 128-2048, default 512 | |
| format | No | png (default) or svg | |
| background | No | Background color as #RRGGBB, default #ffffff | |
| foreground | No | Module color as #RRGGBB, default #0a0a0a | |
| error_correction | No | QR error correction L, M (default), Q, or H |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden, and it does disclose meaningful traits: output is local, static, and not trackable, and the result is either a PNG image or SVG markup. It says nothing about permissions, side effects, or rate limits, but for a pure generation utility the static-vs-dynamic distinction is the trait that matters most.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences, zero filler, and the scoping constraint (static, not trackable) is front-loaded alongside the core action. Nothing could be cut without losing meaning.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With no output schema, the description must hint at the return, and 'local static QR image (PNG) or SVG markup' does indicate the artifact type. It stops short of saying whether the result is returned as image content, base64, or a file path, which is the one remaining gap for a six-parameter tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the schema already documents all six parameters including ranges, defaults, and enums. The description adds only the PNG/SVG duality, which the format enum already conveys; baseline 3 applies when the schema does the heavy lifting.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a specific verb (encode) and resource (text/URL into a static QR image or SVG markup), and explicitly distinguishes itself from the dynamic-code sibling with 'Does not create a dynamic or trackable code.' An agent can route between this and create_dynamic_qr_code without opening either schema.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The exclusion of dynamic/trackable codes implicitly tells the agent to use create_dynamic_qr_code when tracking is wanted, which is clear usage context. However, the sibling is not named explicitly and get_qr_designer_link is not addressed at all, so routing is left partly to inference.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
get_qr_designer_linkGet a UseQR designer linkBInspect
Return a link to the free designer at https://useqr.co. Prefills ?url= when data is an http(s) URL.
| Name | Required | Description | Default |
|---|---|---|---|
| url | No | Optional http(s) URL to prefill in the designer. |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden. It usefully discloses conditional behavior ('Prefills ?url= when data is an http(s) URL'), but says nothing about authentication needs, whether the returned link is stable/expiring, or what happens when the input is not an http(s) URL.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two short sentences with zero waste; the primary behavior (returning the link) is front-loaded and the conditional detail follows.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a one-optional-parameter tool with no output schema, the description is nearly sufficient: it identifies the returned artifact (a designer link) and the prefill rule. It would be complete with a sentence on the non-http(s) case or the link's stability.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% and the single parameter's description already explains it is an optional http(s) URL to prefill. The description adds only the conditional detail that prefill happens only for http(s) values, which is marginal value over the schema. Note a small terminology mismatch: it says 'data' while the parameter is named 'url'.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a specific verb and resource ('Return a link to the free designer at https://useqr.co'), which is clearly distinct in kind from the sibling QR-generating tools. It stops short of explicitly contrasting itself with generate_qr_code or create_dynamic_qr_code, so an agent must infer the distinction.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
There is no statement of when to use this versus the sibling tools that actually produce QR codes, nor any prerequisites or exclusions. The agent is left to infer that this is for handing a user off to a manual designer rather than generating a code.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
3 tool updates
v1.0.0- First observed
create_dynamic_qr_code - First observed
generate_qr_code - First observed
get_qr_designer_link
TDQS
Scored across 3 tools
The three tools target distinct outputs: local static QR generation, a prefilled designer link, and an explainer for dynamic codes. However, 'create_dynamic_qr_code' sounds like it produces a code while actually only explaining one, which invites misselection against generate_qr_code.
All three names follow a consistent snake_case verb_noun pattern (generate_qr_code, get_qr_designer_link, create_dynamic_qr_code). The verb chosen is accurate for two of three, and the convention is uniform throughout.
Three tools is thin but proportional to a single-purpose QR generation server. Each tool covers a distinct sub-task rather than padding, so the scope is reasonable.
Static generation and a designer link are covered, but the advertised dynamic/trackable QR workflow is a dead end—the tool only explains how to do it on the website. There is also no customization (colors, size, error correction), batch generation, or QR decoding.
Maintenance
Related MCP Connectors
Generate QR codes for URLs, PIX, Wi-Fi, vCards, WhatsApp and more. For AI agents.
Make, re-point and track QR codes and short links, and read QR images, from your AI assistant.
Manage your Hovercode QR codes, short links, landing pages, and forms by chatting. Create and restyle QR codes, retarget printed dynamic codes without reprinting, host PDFs behind a QR, build landing pages and forms, organise with folders and tags, and read scan analytics. Hosted, OAuth, works with Claude, ChatGPT, Cursor, and any MCP client.
Related MCP Servers
- AlicenseBqualityFmaintenanceEnables AI assistants to generate QR codes for URLs, text, vCard, WiFi, email, and phone numbers with customizable size, colors, and error correction.116 npm1MIT
- AlicenseNot gradedqualityDmaintenanceEnables AI agents to generate QR codes for URLs, WiFi, contacts, and more with structured parameters.4,567 npm4MIT
- AlicenseAqualityDmaintenanceEnables AI agents to create and manage trackable QR codes (URLs, Wi-Fi, WhatsApp, etc.) via the QR Forge API.25MIT
- FlicenseNot gradedqualityDmaintenanceEnables AI assistants to generate QR codes from text and scan QR codes from images, supporting multiple codes per image and customizable output paths.-