Analytics
arvx.ai
An MCP server for ARVX that manages access, generates readings between two people from their emails, and summarizes saved records.
ENDPOINT 1
https://mcp.arvx.ai/mcp
MCP server metadata
- Name
- arvx
- Version
- 1.0.0
ARVX reads two people from the emails between them: the person you work for (user) and a person they work with (other). It returns colors area by area, up to three predictions, what moved since the last Reading on the pair, and up to two lines on what is acting on the other person this week. Getting access: a person must sign up, accept the terms and create the key. You cannot do it for them. If there is no key, call arvx_get_access and give the person the signup link. Memory of a pair: every Reading returns a sealed record. Save it exactly as returned, with the two people it belongs to, and send it as record in the next Reading on the same two people. If it is lost, the next Reading starts the pair over and loses what ARVX learned about them. ARVX keeps nothing, so the record exists only where you save it. Explaining a Reading to the person: - Show the statement line with every Reading. - Say what each color means for this exchange: green on target, yellow drifting, red off. Name the area in plain words (clarity, cadence, responsiveness, bench strength, meaningful moments). - Predictions are what ARVX expects next, based on what it sees today. Present them as expectations, with what to do if they happen. - Never turn a Reading into a score, a rating, a trait or a personality label on the other person, and never guess at sensitive matters about anyone (health, money, family, beliefs and the like). - The person decides what to say and do. Offer advice; leave the final call to them. Refusals: a refused Reading costs nothing and counts nothing. Pass the refusal sentence to the person as it is.
Known tools 3
arvx_get_accessHow to get access to ARVX: the signup link to give the person, what they must do themselves, the price, and how to add their key to this connector.
Inferred read-onlyarvx_record_summaryWhen someone asks what is held about them: returns every item in a saved record in plain words.
Inferred read-onlyCONNECT WITH APPROVAL
Client installation
Review this server and its permissions before adding it. Secret placeholders must be set locally.
Codex
~/.codex/config.toml
[mcp_servers.arvx]
url = "https://mcp.arvx.ai/mcp"
enabled = true
Claude Code
.mcp.json
{
"mcpServers": {
"arvx": {
"type": "http",
"url": "https://mcp.arvx.ai/mcp"
}
}
}
Claude Desktop
Settings → Connectors → Add custom connector
Name: arvx
Remote MCP URL: https://mcp.arvx.ai/mcp
Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.
Cursor
.cursor/mcp.json
{
"mcpServers": {
"arvx": {
"url": "https://mcp.arvx.ai/mcp"
}
}
}
Visual Studio Code
.vscode/mcp.json
Add to Visual Studio Code{
"servers": {
"arvx": {
"type": "http",
"url": "https://mcp.arvx.ai/mcp"
}
}
}
Generic MCP
Client-specific MCP configuration
{
"name": "arvx",
"transport": "streamable-http",
"url": "https://mcp.arvx.ai/mcp"
}
MCP Inspector
Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.
TRUST AND VERIFICATION EVIDENCE
Trust Data Available
BuiltWith Trust API v2 evidence for arvx.ai was fetched 2026-10-21T23:24:39.215Z.
arvx.ai is assessed as Neutral: No suspicious signals found, but no strong positive signal either
Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.