FutureSearch MCP Server

by futuresearch·io.github.futuresearch/futuresearch-mcp·v0.27.0·57 stars

No reviews yet

Forecast questions about the future, including the outcome under each option.

A85/100grade A

Write a review Install

What users say

No reviews yet

Be the first

Safety scan

A85/100

full report

Adoption

Established

57 stars660 downloads/wk

Reviews

Write one

Nobody has reviewed FutureSearch MCP Server yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

FutureSearch MCP Server tools (21, 4 write)

write = sends, deletes, buys or posts

Read from the package source without running it. The installed server may list more.

futuresearch_agentwrite action
Run web research agents on each row of a CSV file.
futuresearch_balance
Check the current billing balance for the authenticated user.
futuresearch_browse_lists
Browse available reference lists of well-known entities.
futuresearch_cancelwrite action
Cancel a running futuresearch task. Use when the user wants to stop a task that is currently processing.
futuresearch_classify
Deprecated: Classify each row of a dataset into one of the provided categories.
futuresearch_decision
Forecast a decision: the outcome under each option, the user's or anyone else's.
futuresearch_dedupe
Deprecated: Remove duplicate rows from a CSV file using semantic equivalence.
futuresearch_forecast
futuresearch_list_session_tasks
List all tasks in a session with their IDs, statuses, and types.
futuresearch_list_sessions
List futuresearch sessions owned by the authenticated user (paginated).
futuresearch_merge
Deprecated: Join two CSV files using intelligent entity matching.
futuresearch_multi_agent
Deep parallel research: deploys multiple agents on different angles, then synthesizes.
futuresearch_progress
Check progress of a running task. Blocks briefly to limit the polling rate.
futuresearch_rank
Deprecated: Score and sort rows in a CSV file based on any criteria.
futuresearch_request_upload_urlwrite action
Request a presigned URL to upload a local CSV file.
futuresearch_status
Check task status and display a live progress widget.
futuresearch_task_cost
Get the billed cost of a completed task.
futuresearch_task_data
Widget-only. Not for use by an agent.
futuresearch_task_download
Widget-only. Not for use by an agent.
futuresearch_upload_datawrite action
Upload data from a URL or local file. Returns an artifact_id for use in processing tools.
futuresearch_use_list
Import a reference list into your session and make it available via artifact_id for other futuresearch tools.

Public scan report

scanner v0.1.10 · 2026-11-03 · same rubric, same numbers if you re-run it

no findings

Code scan38 source files scanned25/25
–Live reliabilityno gateway calls yet and no remote to proben/a
–Tool poisoningtools not inspected (local package is not executed); not countedn/a
Auth qualitystatic API keys via environment variables6/15
Maintenancelast push 6 days ago15/15
Maintainer identityregistry namespace matches repository owner; GitHub account older than a year9/10

Overall 85/100. Components that don't apply are left out of the denominator. Any critical finding is an F.Rubric Appeal a finding JSON

How FutureSearch MCP Server compares

Against every graded MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score: 85/100; higher than 70% of 48,255 servers
Tools: 21; the typical server has 7
Tools that change things: 19%; typical: 0%. Fewer write tools means less an agent can break
GitHub stars: 57; more than 95% of 28,688 servers
Downloads a week: 660; more than 91% of 12,191 servers with a package

What its tools let an agent do: 17 read · 4 change

Release history: 2 versions in the registry since 2026-08-12, latest 2026-10-05, typically one every 54 days.

Install FutureSearch MCP Server in Claude Code, Cursor or VS Code

claude mcp add futuresearch-mcp -- uvx futuresearch-mcp

Add to Cursor

What the publisher says

From the FutureSearch MCP Server repository's README, as published. We do not edit it. Read it on GitHub

FutureSearch Python SDK

An API for frontier forecasting.

FutureSearch predicts the future. Accuracy is verifiable via our public track record on stocks, prediction markets, public benchmarks, and forecasting tournaments: the forecaster leads Metaculus's Summer 2026 FutureEval tournament, sits above the superforecaster median on ForecastBench, and holds the best pooled score on BTF-3, our 1,907-question pastcasting benchmark. Those are live standings, so the link carries the current positions. Every forecast draws on a shared world model that reconciles related questions against each other; it improved all nine base forecasters we tested, four of them significantly.

Try it yourself in the app, or give advanced forecasting and multi-agent capabilities to your AI wherever you use it (Claude.ai, Claude Code, or Gemini/Codex/other AI surfaces), or point them to this Python SDK.

Installation

Claude.ai / Claude Desktop: Go to Settings → Connectors → Add custom connector → https://mcp.futuresearch.ai/mcp

Claude Code:

claude mcp add futuresearch --scope project --transport http https://mcp.futuresearch.ai/mcp

Then sign in the same way you do in the FutureSearch web app and pick the account the connection should use.

Forecasting

forecast() takes a table of questions about the future and returns a forecast for each row, with a rationale column explaining each answer. Five modes cover the shapes a question can take.

Effort level is "LOW" or "HIGH": roughly $0.15 per question at low effort and $2 at high effort. Left unset, a single question runs at high effort and a batch runs at low. Categorical, thresholded, and conditional forecasts always require "HIGH".

Binary

The probability, 0 to 100, that a YES/NO question resolves YES. Output columns: probability and rationale.

import asyncio
from pandas import DataFrame
from futuresearch.ops import forecast

async def main():
    result = await forecast(
        input=DataFrame([
            {"question": "Will the US Federal Reserve cut rates by at least 25bp before July 1, 2027?"},
            {"question": "Will SpaceX land Starship on the Moon before 2030?"},
        ]),
        forecast_type="binary",
    )
    print(result.data[["question", "probability", "rationale"]])

asyncio.run(main())

Numeric

Percentile estimates (p10 through p90) for a continuous quantity. Requires output_field and units.

result = await forecast(
    input=DataFrame([
        {"question": "What will the price of Brent crude oil be on December 31, 2026?"},
    ]),
    forecast_type="numeric",
    output_field="price",
    units="USD per barrel",
)
print(result.data[["price_p10", "price_p50", "price_p90"]])

Date

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

FutureSearch MCP Server: common questions

Is FutureSearch MCP Server safe?: Yes, by our scan: it is graded A (85/100). Read the FutureSearch MCP Server safety report
How do I install FutureSearch MCP Server?: It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does FutureSearch MCP Server need an API key?: Yes. The registry entry asks for FUTURESEARCH_API_KEY.
Is FutureSearch MCP Server maintained?: The last commit was 7 days ago (2026-10-28). The latest release is v0.27.0.
How does FutureSearch MCP Server compare with other MCP servers?: safety score 85/100 (higher than 70% of 48,255 servers); tools 21 (the typical server has 7); tools that change things 19% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.