# FutureSearch MCP Server

Produces probabilities, dates and numbers for questions about the future, and forecasts what each option in a decision leads to. Useful when a choice needs backing.

- 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/futuresearch-mcp
- Updated: 2026-10-13
- HTML: https://affpapa.org/en/nevibecode/mcp/futuresearch-mcp-server

## What it does

The server hands your assistant forecasting tools. `futuresearch_forecast` covers five modes: binary probability, numeric and date percentiles, categorical, and thresholded. `futuresearch_decision` forecasts the same outcome under every listed alternative — what happens if a project gets one budget or another. A third tool, `futuresearch_multi_agent`, spins up parallel research agents across the rows of a table.

Every call is asynchronous. Starting a task returns an ID right away; you poll `futuresearch_progress(task_id)` for status and pull the finished output with `futuresearch_results(task_id, output_path)`, which writes a CSV. Rows go inline as `data` or by reference to an uploaded `artifact_id`. Run the server yourself over stdio and the tools also take absolute paths to local CSV files.

Self-hosting needs a FutureSearch API key and either `uv` or the `futuresearch-mcp` package installed with pip. No key in `FUTURESEARCH_API_KEY` means the server will not start. The hosted endpoint at `https://mcp.futuresearch.ai/mcp` authenticates over OAuth and needs no key at all, which covers most people.

## Requirements
- Needs: Python and uv (commands run via uvx)
- Environment variables: `FUTURESEARCH_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 futuresearch-mcp -e FUTURESEARCH_API_KEY=<FUTURESEARCH_API_KEY> -- uvx futuresearch-mcp
```
Replace <…> with your own values. uvx runs the command named after the package; if the README names another one, use uvx --from futuresearch-mcp <command>

### Codex

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

### Cursor

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

### GitHub Copilot

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

### Gemini CLI

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

## When to use it
- size up how likely an event is before committing
- compare what one decision yields at different funding levels
- get a date or a number as percentiles instead of a single figure
- split a question into categories and score each one
- run deep research down every row of a table

## Example prompts
- Forecast with futuresearch whether the team ships the release this quarter
- Run a decision forecast on what happens at each funding level we could pick
- Use futuresearch_multi_agent to research every row in `companies.csv`

## 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