Independent trust scores for AI tools, with compliance, model providers, connectors and pricing.
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.
Compare two to five AI tools side by side on Lufi trust scores, compliance, model providers, MCP and pricing.
Pick your client. Values in capitals, like YOUR_TOKEN, are yours to fill in.
Run in a terminal
claude mcp add --transport http lufi https://uselufi.com/mcp
Compare two to five AI tools side by side on Lufi trust scores, compliance, model providers, MCP and pricing.
| Argument | Type | Description |
|---|---|---|
| slugs* | array |
{
"type": "object",
"required": [
"slugs"
],
"properties": {
"slugs": {
"type": "array",
"items": {
"type": "string"
},
"maxItems": 5,
"minItems": 2
}
}
}Get one AI tool's Lufi trust score, human and agent sub-scores, review counts, compliance labels with sources, data and rights answers, watch-outs, models, which AI companies it runs on, connectors, Zapier/Make listings and MCP server, pricing, and recent market news.
| Argument | Type | Description |
|---|---|---|
| slug* | string | Tool slug or name, e.g. 'anthropic' |
{
"type": "object",
"required": [
"slug"
],
"properties": {
"slug": {
"type": "string",
"description": "Tool slug or name, e.g. 'anthropic'"
}
}
}Find AI tools on Lufi with their independent trust scores. Filter by free text (name or task), intent (productivity, creative, analytical, agentic), compliance label (e.g. SOC 2, HIPAA, GDPR), the AI company a tool runs on (e.g. Anthropic), official MCP server, or free plan.
| Argument | Type | Description |
|---|---|---|
| limit | integer | |
| query | string | Tool name or task, e.g. 'image generation' |
| intent | string | |
| has_mcp | boolean | Only tools with an official MCP server |
| runs_on | string | AI company the tool is confirmed to run on, e.g. 'OpenAI' or 'Anthropic' |
| free_plan | boolean | Only tools with a free plan |
| compliance | string | Compliance label, e.g. 'HIPAA' |
{
"type": "object",
"properties": {
"limit": {
"type": "integer",
"default": 10,
"maximum": 25,
"minimum": 1
},
"query": {
"type": "string",
"description": "Tool name or task, e.g. 'image generation'"
},
"intent": {
"enum": [
"productivity",
"creative",
"analytical",
"agentic"
],
"type": "string"
},
"has_mcp": {
"type": "boolean",
"description": "Only tools with an official MCP server"
},
"runs_on": {
"type": "string",
"description": "AI company the tool is confirmed to run on, e.g. 'OpenAI' or 'Anthropic'"
},
"free_plan": {
"type": "boolean",
"description": "Only tools with a free plan"
},
"compliance": {
"type": "string",
"description": "Compliance label, e.g. 'HIPAA'"
}
}
}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 13, 2026.