LiftMCP's own server: company and product info, a website AI-readiness check, and site onboarding.
Maintain this server? Claim it
Call this server's tools from your browser. Nothing to install.
Requests go through mcptry because browsers can't call most MCP servers directly. Header values are sent to the server for that request only and are never stored or logged.
Tool list from our last check. Connect live to refresh it.
Check how ready a website is for AI agent interaction. Returns an AI readiness score and breakdown.
The website URL to check (e.g. https://example.com)
This tool isn't marked read-only, so it may change something on the server or in an account you connected.
Pick your client. Values in capitals, like YOUR_TOKEN, are yours to fill in.
Run in a terminal
claude mcp add --transport http company https://mcp.liftmcp.com/
Check how ready a website is for AI agent interaction. Returns an AI readiness score and breakdown.
| Argument | Type | Description |
|---|---|---|
| url* | string | The website URL to check (e.g. https://example.com) |
{
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"url"
],
"properties": {
"url": {
"type": "string",
"format": "uri",
"description": "The website URL to check (e.g. https://example.com)"
}
}
}Get information about LiftMCP Ltd — the company behind the LiftMCP platform.
No arguments.
{
"type": "object",
"properties": {}
}Get information about the LiftMCP platform — what it does, how it works, and key concepts.
No arguments.
{
"type": "object",
"properties": {}
}Add a website to your LiftMCP organisation as a Property and get the server card to publish on it. Needs your organisation API key in the Authorization header. Safe to repeat: a site already added is found, not added twice. Next: publish the card exactly as given at the address given, then call verify_site.
| Argument | Type | Description |
|---|---|---|
| domain* | string | The site, e.g. example.com or https://www.example.com |
{
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"domain"
],
"properties": {
"domain": {
"type": "string",
"description": "The site, e.g. example.com or https://www.example.com"
}
}
}The status of one Property in your LiftMCP organisation, or of all of them if no propertyId is given.
| Argument | Type | Description |
|---|---|---|
| propertyId | string | A Property id; leave out to list all |
{
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"properties": {
"propertyId": {
"type": "string",
"description": "A Property id; leave out to list all"
}
}
}Check the server card published on a site and, if it matches, verify the Property and switch on its MCP endpoint. Returns the endpoint and, on the first successful verify only, the MCP API key agents use to call it. Safe to repeat.
| Argument | Type | Description |
|---|---|---|
| propertyId* | string | The Property id from register_site |
{
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"propertyId"
],
"properties": {
"propertyId": {
"type": "string",
"description": "The Property id from register_site"
}
}
}We read every tool's name, description and inputs the way the model will, looking for instructions hidden from you. A clean result means no warning signs, not a guarantee. Scanned Nov 17, 2026.
No readOnlyHint / destructiveHint annotations, so clients can't tell a read from a write without asking.
Fix: Add annotations to each tool, e.g. { readOnlyHint: true } for tools that only read.