Contrie
Extract structured data from a web page, read it as markdown, verify values against the source.
Install
Add this to your client's MCP configuration (Claude Desktop: claude_desktop_config.json; Cursor: .cursor/mcp.json; VS Code and others use the same "mcpServers" shape).
claude mcp add --transport http contrie 'https://www.contrie.com/mcp'
{
"mcpServers": {
"contrie": {
"type": "http",
"url": "https://www.contrie.com/mcp"
}
}
}
@contrie/mcpclaude mcp add contrie -e 'CONTRIE_API_KEY=<your contrie_api_key>' -- npx -y @contrie/mcp@0.1.1
{
"mcpServers": {
"contrie": {
"command": "npx",
"args": [
"-y",
"@contrie/mcp@0.1.1"
],
"env": {
"CONTRIE_API_KEY": "<your contrie_api_key>"
}
}
}
}
Environment variables
CONTRIE_API_KEYrequired secret Contrie API key from https://www.contrie.com/dashboard/keys. The hosted endpoint needs none (OAuth sign-in).
Frequently asked questions
What is Contrie?
Extract structured data from a web page, read it as markdown, verify values against the source.
How do I install Contrie?
It runs as a remote server. In Claude Code: claude mcp add --transport http contrie 'https://www.contrie.com/mcp'. For other clients, paste the JSON configuration from this page into their MCP settings.
Does Contrie need an API key?
Yes. It expects CONTRIE_API_KEY, which you set in its configuration.
Who maintains Contrie?
It is published by com.contrie. AI.tn lists it but does not maintain or endorse it.
From the official MCP Registry. Listing is not an endorsement: review a server's code and permissions before giving it access to your data.