Arca
Arca is a private data vault where your AI stores your structured data, semantic memory and skills.
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 arca 'https://mcp.arca.build' --header 'Authorization: <Supports Bearer Token or oAuth. Get API Key on arca.build>'
{
"mcpServers": {
"arca": {
"type": "http",
"url": "https://mcp.arca.build",
"headers": {
"Authorization": "<Supports Bearer Token or oAuth. Get API Key on arca.build>"
}
}
}
}
claude mcp add --transport sse arca 'https://mcp.arca.build' --header 'Authorization: <Supports Bearer Token or oAuth. Get API Key on arca.build>'
{
"mcpServers": {
"arca": {
"type": "sse",
"url": "https://mcp.arca.build",
"headers": {
"Authorization": "<Supports Bearer Token or oAuth. Get API Key on arca.build>"
}
}
}
}
Frequently asked questions
What is Arca?
Arca is a private data vault where your AI stores your structured data, semantic memory and skills.
How do I install Arca?
It runs as a remote server. In Claude Code: claude mcp add --transport http arca 'https://mcp.arca.build' --header 'Authorization: <Supports Bearer Token or oAuth. Get API Key on arca.build>'. For other clients, paste the JSON configuration from this page into their MCP settings.
Does Arca need an API key?
Yes. It expects Authorization, which you set in its configuration.
Who maintains Arca?
It is published by build.arca.mcp. 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.