Arcai
io.arcaiv1.1.0Updated Oct 8, 2026
Crypto intelligence: rug/scam scans for any token, verified whale flows, AI signals + track record
Overview
AI-generated overview
Arcai gives an assistant crypto intelligence: rug and scam scans for tokens, verified whale flows, and AI trading signals with a track record.
- What it does
- Arcai is a remote crypto intelligence service exposed to an assistant over the Model Context Protocol. According to its registry description, it offers rug and scam scans for any token, verified whale flows, and AI signals together with a track record. No individual tools are listed in the manifest, so the exact operations available are not documented here.
- When to use it
- Consider it when an assistant needs to check a token for rug or scam risk, look at whale movement, or review AI-generated crypto signals before acting on them. It is aimed at crypto research and due-diligence workflows rather than general tasks.
- Requirements
- A remote MCP endpoint at using streamable HTTP. The manifest declares no authentication, no environment variables, and no headers, and no package or local runtime is needed. Network access to the endpoint is required.
Before you install
The manifest declares no authentication, so it is unclear what account, quota, or access controls apply; confirm this with the provider before relying on it. The service returns crypto intelligence and signals, which are not financial advice and can be wrong. No tools are listed, so what data the server sends to the provider and whether any action writes or changes anything cannot be verified from the input.
Installation
In SourceWeft
- Open Arcai in the dashboard and add it to a workspace.
- Enable the server for the chats that should use its tools.
Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.
Other MCP clients
Add this to your client's mcpServers config.
{
"mcpServers": {
"arcai": {
"type": "http",
"url": "https://arcai.io/mcp"
}
}
}Tools
0Tool metadata has not been indexed yet.
Version history
1- v1.1.0LatestOct 8, 2026
