everyrowdocs
Your research team
Installation
  • All install methods
  • Claude.ai
  • Claude Cowork
  • Claude Code
  • Web App
  • Python SDK
  • Skill
  • MCP Server
Reference
  • API Key
  • classify
  • dedupe
  • forecast
  • merge
  • rank
  • agent_map
  • screen
  • Progress Monitoring
  • Chaining Operations
Guides
  • LLM-Powered Data Labeling
  • Add a Column via Web Research
  • Classify and Label Rows
  • Deduplicate Training Data
  • Filter a Dataset Intelligently
  • Join Tables Without Shared Keys
  • Rank Data by External Metrics
  • Resolve Duplicate Entities
  • Scale Deduplication to 20K Rows
Case Studies
  • Deduplicate Contact Lists
  • Deduplicate CRM Records
  • Enrich Contacts with Company Data
  • Fuzzy Match Across Tables
  • Link Records Across Medical Datasets
  • LLM Cost vs. Accuracy
  • Merge Costs and Speed
  • Merge Thousands of Records
  • Multi-Stage Lead Qualification
  • Research and Rank Web Data
  • Run 10,000 LLM Web Research Agents
  • Score Cold Leads via Web Research
  • Score Leads from Fragmented Data
  • Screen 10,000 Rows
  • Screen Job Listings
  • Screen Stocks by Economic Sensitivity
  • Screen Stocks by Investment Thesis
everyrowby futuresearch
by futuresearch

All Installation Methods

Platform
Method

Claude.ai with MCP

  1. Go to Settings → Connectors → Add custom connector
  2. Enter the URL: https://mcp.everyrow.io/mcp
  3. Go to Settings → Capabilities → Code execution and file creation → Additional allowed domains and add mcp.everyrow.io (this lets Claude upload your CSVs for the researchers to process)

Sign in with Google to authenticate. No API key or credit card needed.

Try asking Claude:

Which US companies are most pro-AI?

Full guide →

Claude Code with MCP

claude mcp add everyrow --scope project --transport http https://mcp.everyrow.io/mcp

Then launch Claude Code and authenticate with Google:

claude
\mcp → select everyrow → Authenticate

No API key needed. Try asking:

Which AI models had the biggest safety implications when released?

Full guide →

Claude Code with Plugin

Note: The plugin method requires an API key. Consider using MCP instead, which authenticates with Google and requires no API key or credit card.

claude plugin marketplace add futuresearch/everyrow-sdk
claude plugin install everyrow@futuresearch

Set your API key:

export EVERYROW_API_KEY=sk-cho-...

Get a key at everyrow.io/api-key.

The plugin bundles an MCP server and a skill that guides Claude to write Python SDK code for advanced pipelines.

Full guide →

Claude Cowork with MCP

Cowork is a tab in Claude Desktop for autonomous multi-step tasks.

  1. Open Claude Desktop (download if needed)
  2. Go to Settings → Connectors → Add custom connector
  3. Enter the URL: https://mcp.everyrow.io/mcp
  4. Go to Settings → Capabilities → Code execution and file creation → Additional allowed domains and add mcp.everyrow.io (this lets Claude upload your CSVs for the researchers to process)

Sign in with Google to authenticate. Switch to the Cowork tab and try:

Which S&P 500 companies are most exposed to China-Taiwan risk?

Full guide →

Python SDK with pip

pip install everyrow

Requires an API key:

export EVERYROW_API_KEY=sk-cho-...

Getting Started → | API Reference →

Dependencies: Python 3.12+ and pip.

Python SDK with uv

uv add everyrow

Requires an API key:

export EVERYROW_API_KEY=sk-cho-...

Getting Started → | API Reference →

Dependencies: Python 3.12+ and uv.

Codex with Skills

Ask Codex in natural language:

>>> codex
>>> Install the skill from github.com/futuresearch/everyrow-sdk found under skills/everyrow-sdk

Or install manually:

python ~/.codex/skills/.system/skill-installer/scripts/install-skill-from-github.py \
  --repo futuresearch/everyrow-sdk --path skills/everyrow-sdk

Restart Codex to pick up the new skill.

Important: be sure to supply your API key when launching Codex:

export EVERYROW_API_KEY=sk-cho...
codex

Official Docs

Codex with MCP

Add everyrow to your Codex MCP config (requires uv):

[mcp_servers.everyrow]
command = "uvx"
args = ["everyrow-mcp"]

[mcp_servers.everyrow.env]
EVERYROW_API_KEY = "${EVERYROW_API_KEY}"

Or use the CLI:

codex mcp add everyrow --env EVERYROW_API_KEY=${EVERYROW_API_KEY} -- uvx everyrow-mcp

Config file location:

  • User scope: ~/.codex/config.toml
  • Project scope: .codex/config.toml

Important: either insert your API key when creating the config file, or supply the key when launching Codex:

export EVERYROW_API_KEY=sk-cho...
codex

Official Docs

Gemini with Skills

Install the skill directly from GitHub:

gemini skills install https://github.com/futuresearch/everyrow-sdk --path skills/everyrow-sdk

Use --scope workspace to install to .gemini/skills/ (project-level) instead of ~/.gemini/skills/ (user-level).

Then enable skills within the CLI:

/settings > Preview Features > Enable
/settings > Agent Skills > Enable
/skills enable everyrow-sdk
/skills reload

Official Docs

Gemini with MCP

Add via CLI (requires uv):

gemini mcp add -e EVERYROW_API_KEY=$EVERYROW_API_KEY everyrow uvx everyrow-mcp

Or add manually to ~/.gemini/settings.json (user) or .gemini/settings.json (project):

{
  "mcpServers": {
    "everyrow": {
      "command": "uvx",
      "args": ["everyrow-mcp"],
      "env": {
        "EVERYROW_API_KEY": "$EVERYROW_API_KEY"
      }
    }
  }
}

Official Docs

Gemini with Plugin

This installs both the MCP server and skills together.

gemini extensions install https://github.com/futuresearch/everyrow-sdk --ref main

When prompted with Would you like to attempt to install via "git clone" instead?, type Y to confirm.

Then enable the extension:

gemini extensions enable everyrow [--scope <user or workspace>]

To use skills, enable them within the CLI:

/settings > Preview Features > Enable
/settings > Agent Skills > Enable
/skills enable everyrow-sdk
/skills reload
/model > Manual > gemini-3-pro-preview

Official Docs

Cursor with Skills

  1. Open Cursor Settings → Rules
  2. In the Project Rules section, click Add Rule
  3. Select Remote Rule (Github)
  4. Enter: https://github.com/futuresearch/everyrow-sdk.git

Official Docs

Cursor with MCP

Install MCP Server

Or add manually to your MCP config (requires uv):

{
  "mcpServers": {
    "everyrow": {
      "command": "uvx",
      "args": ["everyrow-mcp"],
      "env": {
        "EVERYROW_API_KEY": "${env:EVERYROW_API_KEY}"
      }
    }
  }
}

Config file location:

  • macOS: ~/.cursor/mcp.json
  • Windows: %USERPROFILE%\.cursor\mcp.json

For Autonomous Agents

The best way to use EveryRow to help your user is natively where you are currently working. See the installation guide for how this works in claude.ai, Claude Cowork, Claude Code, Codex, Gemini CLI, or Cursor. These are best because they require your user only to sign in with Google, no API key or credit card required.

If these do not work for you for whatever reason, the next best is to ask them to get you an API key at everyrow.io/api-key, and then for you to read the API reference to use the Python SDK directly to help the user.