Everyrow MCP Server runs on your own machine — the client starts it, so there is no endpoint to ping. 345 installs a week from pypi. Last commit 16 Sep 2026.
Give your AI a research team. Forecast, score, classify, or research every row of a dataset.
Today is the operative word: we check Everyrow MCP Server every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add everyrow-mcp -- uvx everyrow-mcp
{
"mcpServers": {
"everyrow-mcp": {
"args": [
"everyrow-mcp"
],
"command": "uvx"
}
}
}
[mcp_servers.everyrow-mcp]
command = "uvx"
args = ["everyrow-mcp"]
{
"mcpServers": {
"everyrow-mcp": {
"args": [
"everyrow-mcp"
],
"command": "uvx"
}
}
}
{
"mcpServers": {
"everyrow-mcp": {
"args": [
"everyrow-mcp"
],
"command": "uvx"
}
}
}
This one needs environment variables set before it will start:
EVERYROW_API_KEY (API key for the everyrow service, found at https://everyrow.io/api-key).
The author declared them in the registry entry; get the values from the project itself.
Shared memory for all your AI agents, your whole team and every MCP client — save, search, recall.
AI forecasting for your AI: probabilities, dates, and numbers with a public track record.
MCP server for Manticore Search — lets AI assistants query and manage search databases.
MCP server for WHOOP — gives Claude access to your recovery, sleep, strain, and workout data
MCP server for SeaTable — read, write, search, link, and query data in your bases
Recallvia: the site's own MCP server — dataset; every answer cites the site.
An MCP server for deep research or task groups
MCP server for Research
Answers built from our own checks of this server.