qURL runs on your own machine — the client starts it, so there is no endpoint to ping. 587 installs a week from npm. Last commit 3 Nov 2026.
Mint, resolve, audit, and rotate scope-limited expiring access links (qURLs) for AI agents.
We read the source, 4 d ago · rules 995398eba69f
What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.
child = spawn(binary, argv, {
COPY package.json package-lock.json .npmrc ./
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add qurl-mcp -- npx -y @layervai/qurl-mcp
{
"mcpServers": {
"qurl-mcp": {
"command": "npx",
"args": [
"-y",
"@layervai/qurl-mcp"
]
}
}
}
[mcp_servers.qurl-mcp]
command = "npx"
args = ["-y", "@layervai/qurl-mcp"]
{
"mcpServers": {
"qurl-mcp": {
"command": "npx",
"args": [
"-y",
"@layervai/qurl-mcp"
]
}
}
}
{
"servers": {
"qurl-mcp": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@layervai/qurl-mcp"
]
}
}
}
Optional settings from the registry entry, left out of the block above:
QURL_API_KEY (Optional. Without it, the tools run through the local qURL CLI (qurl), which needs no account. With it, the tools use the qURL API: a key with qurl:read, qurl:write, and/or qurl:resolve scopes from https://layerv.ai), QURL_API_URL (qURL API base URL. Defaults to https://api.layerv.ai. Override only for testing against a non-production qURL backend), QURL_CONNECTOR_URL (Connector base URL used by local-file, file-data, and text-to-PDF upload tools before minting a qURL), QURL_LINK_HOSTS (Optional comma-separated exact hostnames or IPs for uploaded-file links. No schemes, ports, or wildcards. Blank values retain any file-configured policy), QURL_MCP_CONFIG (Optional path to a shared qURL MCP config file. Both stdio and HTTP modes can read SMTP, connector, and default API settings from this file), MCP_MAX_UPLOAD_FILE_DATA_BYTES (Maximum decoded/local upload size. Accepts bytes or units such as 10mb; capped at 100mb), QURL_SMTP_HOST (SMTP hostname for optional qURL link delivery), QURL_SMTP_PORT (SMTP port for optional qURL link delivery), QURL_SMTP_SECURE (Whether SMTP uses an implicit TLS connection (true/false)), QURL_SMTP_USERNAME (SMTP authentication username), QURL_SMTP_PASSWORD (SMTP authentication password or app-specific credential), QURL_SMTP_FROM_EMAIL (Validated sender email address for qURL delivery), QURL_SMTP_FROM_NAME (Optional sender display name for qURL delivery), QURL_SMTP_ALLOWED_RECIPIENTS (Optional comma-separated exact recipient allowlist), QURL_SMTP_ALLOWED_RECIPIENT_DOMAINS (Optional comma-separated recipient-domain allowlist), QURL_SMTP_MAX_RECIPIENTS_PER_MESSAGE (Maximum recipients in one delivery request (default 10)), QURL_SMTP_MAX_RECIPIENTS_PER_HOUR (Maximum attempted recipients per qURL key per fixed hourly window (default 100)), QURL_MCP_FEEDBACK (Set to off to hide and disable outbound LayerV product feedback. Default on. Feedback is sent only by an explicit submit_feedback tool call).
AEO scoring, llms.txt audit, and agent-readiness checks for AI agents.
Open federation for AI agents: identity, mentors, reputation and limited accession.
OAuth 2.1 short-link tools for AI agents with scoped tokens, approvals, audit logs, and revocation.
Scoped credential retrieval for AI agents, with audit events and revocable future access.
X.509 identity, risk scoring, and audit logging for AI agents. MiCA + EU AI Act compliant.
X.509 identity, risk scoring, and audit logging for AI agents. MiCA + EU AI Act compliant.
Permission gateway for AI agents: scoped MCP endpoints over 27 services, audited and revocable.
Credential broker for AI agents: scoped, revocable API access with policy enforcement and audit.
Answers built from our own checks of this server.