Everyrow MCP Server

AI-powered dataframe ops: transform, dedupe, merge, rank, and screen with natural language

Remote serverstreamable-httpPython

What is the Everyrow MCP server?

Everyrow MCP server is a hosted integration for AI assistants that speak the Model Context Protocol. AI-powered dataframe ops: transform, dedupe, merge, rank, and screen with natural language.

What you get

FutureSearch predicts the future. Accuracy is verifiable via our public track record on stocks, prediction markets, public benchmarks, and forecasting tournaments. As of July 2026 that record shows the forecaster first in Metaculus's Summer 2026 FutureEval tournament, above the superforecaster median on ForecastBench, and holding the best pooled score on BTF-3, our 1,907-question pastcasting benchmark. Every forecast draws on a shared world model that reconciles related questions against each other; it improved all eight base forecasters we tested.

What the assistant can call

Once Everyrow is connected, these are the calls the assistant has available:

  • Binary — The probability, 0 to 100, that a YES/NO question resolves YES. Output columns: probability and rationale
  • Numeric — Percentile estimates (p10 through p90) for a continuous quantity. Requires output_field and units
  • Date — Percentile dates (p10 through p90, as YYYY-MM-DD) for timing questions. Requires output_field
  • Categorical — Multiple choice: one probability per outcome, forecast jointly so the probabilities sum to 100. Each row holds its own option list in the column
  • Thresholded — One probability per threshold condition on a single quantity. List each row's conditions from least strict to most strict; each condition is stricter
  • Conditional — Any mode can be made conditional on a stated scenario: pass condition (one condition applied to every row) or condition_field (a column of per-row
  • CursorOfficial docs

Setting it up

Being a remote server, there is no local install. You register the endpoint with your client, authorise it once, and the tools appear.

Configuration and credentials

You will need one environment variable: FUTURESEARCH_API_KEY. The server will not start without them, which is usually why the tools fail to appear on a first run. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.

Choosing this one

Among the developer tooling options, the useful question is rarely "what can it do" but "what does it cost you to run" — permissions, credentials, and how much of your context its toolset consumes. Everyrow's toolset — Binary, Numeric, Date and 4 more — is a fair guide to whether it matches your workflow. It is maintained by futuresearch; worth a glance at recent repository activity before you build anything load-bearing on it.

SyncDev reviews every entry in this directory against the project's own documentation before publishing, and revisits them as servers change.

Before you rely on it

  • Your data travels to the provider's service, so the usual questions apply about what you send and what they retain.
  • Missing credentials fail quietly in some clients — if no tools show up, check the environment block first.
  • MCP clients confirm each tool call by default. Leave that on until you have watched what the everyrow mcp server does with a few real requests.

Available tools

ToolWhat it does
BinaryThe probability, 0 to 100, that a YES/NO question resolves YES. Output columns: probability and rationale.
NumericPercentile estimates (p10 through p90) for a continuous quantity. Requires output_field and units.
DatePercentile dates (p10 through p90, as YYYY-MM-DD) for timing questions. Requires output_field.
CategoricalMultiple choice: one probability per outcome, forecast jointly so the probabilities sum to 100. Each row holds its own option list in the column named by categories_field. Make the set exhaustive; add an "Other" option w
ThresholdedOne probability per threshold condition on a single quantity. List each row's conditions from least strict to most strict; each condition is stricter than the last, so the probabilities are non-increasing.
ConditionalAny mode can be made conditional on a stated scenario: pass condition (one condition applied to every row) or condition_field (a column of per-row conditions). Both branches are forecast together, and each output column
Cursor[Official docs](https://cursor.com/docs/context/skills#installing-skills-from-github).

How to install the Everyrow MCP server

{
  "mcpServers": {
    "everyrow": {
      "command": "uvx",
      "args": ["futuresearch"],
      "env": {
        "FUTURESEARCH_API_KEY": "your-value"
      }
    }
  }
}

Add to claude_desktop_config.json, then restart Claude Desktop.

Configuration

VariableDescriptionRequired
FUTURESEARCH_API_KEYCredential the server authenticates with.Yes

Example prompts to try

  • Use Everyrow to Binary.
  • Use Everyrow to Numeric.
  • Use Everyrow to Date.

Frequently asked questions

It connects Everyrow to MCP-compatible AI assistants such as Claude and Cursor, exposing 7 tools (Binary, Numeric, Date, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Everyrow directly.