# Everyrow MCP Server

Connects FutureSearch forecasting to your AI coding assistant. It generates probability distributions, date ranges, and numerical estimates with rationales.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI · ★ 57
- Author: futuresearch
- License: MIT · policy=link-only · description only; the file stays with the author
- Source: https://github.com/futuresearch/futuresearch-python/tree/HEAD/everyrow-mcp
- Updated: 2026-10-13
- HTML: https://affpapa.org/en/nevibecode/mcp/everyrow-mcp-server

## What it does

This MCP server links your development environment to the FutureSearch engine, formerly known as Everyrow. The service forecasts question outcomes across distinct formats: binary yes/no probabilities, continuous numeric values with p10 to p90 percentile spreads, estimated dates, and multi-option categorical distributions. Every result includes an explanatory rationale column clarifying the underlying factors.

Beyond standalone questions, the server handles choice evaluations. You can provide scenario details alongside several alternative actions to estimate how each choice shifts the outcome. Execution relies on `uvx everyrow-mcp`. You must set `EVERYROW_API_KEY` in your environment. Without a valid token, forecasts will fail to resolve.

## Requirements
- Needs: Python and uv (commands run via uvx)
- Environment variables: `EVERYROW_API_KEY` — keys and tokens: ask the human for the values, never commit them or put them in shared files.

## Install

### Claude Code (native platform)

**Platform CLI**
```bash
claude mcp add everyrow-mcp -e EVERYROW_API_KEY=<EVERYROW_API_KEY> -- uvx everyrow-mcp
```
Replace <…> with your own values. uvx runs the command named after the package; if the README names another one, use uvx --from everyrow-mcp <command>

### Codex

**Platform CLI**
```bash
codex mcp add everyrow-mcp --env EVERYROW_API_KEY=<EVERYROW_API_KEY> -- uvx everyrow-mcp
```
Replace <…> with your own values. uvx runs the command named after the package; if the README names another one, use uvx --from everyrow-mcp <command>

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "everyrow-mcp": {
            "command": "uvx",
            "args": [
                "everyrow-mcp"
            ],
            "env": {
                "EVERYROW_API_KEY": "<EVERYROW_API_KEY>"
            }
        }
    }
}
```
Replace <…> with your own values. uvx runs the command named after the package; if the README names another one, use uvx --from everyrow-mcp <command>

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "everyrow-mcp": {
            "type": "stdio",
            "command": "uvx",
            "args": [
                "everyrow-mcp"
            ],
            "env": {
                "EVERYROW_API_KEY": "<EVERYROW_API_KEY>"
            }
        }
    }
}
```
Replace <…> with your own values. uvx runs the command named after the package; if the README names another one, use uvx --from everyrow-mcp <command>

### Gemini CLI

**Platform CLI**
```bash
gemini mcp add -e EVERYROW_API_KEY=<EVERYROW_API_KEY> everyrow-mcp uvx everyrow-mcp
```
Replace <…> with your own values. uvx runs the command named after the package; if the README names another one, use uvx --from everyrow-mcp <command>

## When to use it
- Calculate the probability of an upcoming event resolving yes or no
- Forecast numerical values with p10 through p90 percentile estimates
- Project completion dates for future milestones
- Compare predicted outcomes across several decision alternatives

## Example prompts
- Estimate the probability of the central bank lowering benchmark rates before next summer.
- Forecast our expected user count under three distinct budget allocations.
- Project the date range for an upcoming product launch with p10 and p90 milestones.

## Similar
- [MCP Toolbox for Databases](https://affpapa.org/en/nevibecode/mcp/googleapis-mcp-toolbox-for-databases.md) — MCP server · ★ 16717
- [labelhead-artist-momentum](https://affpapa.org/en/nevibecode/mcp/labelhead-artist-momentum.md) — MCP server · ★ 107423
- [Agent Skills Search Server](https://affpapa.org/en/nevibecode/mcp/agent-skills-search-server.md) — MCP server · ★ 26559
- [Skyvern](https://affpapa.org/en/nevibecode/mcp/skyvern.md) — MCP server · ★ 23263
- [Nhost](https://affpapa.org/en/nevibecode/mcp/nhost.md) — MCP server · ★ 9366
- [PraisonAI](https://affpapa.org/en/nevibecode/mcp/praisonai.md) — MCP server · ★ 9289

From the same set: [futuresearch/futuresearch-python](https://affpapa.org/en/nevibecode/by/futuresearch/futuresearch-python.md) — 2 cards

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md