Verified contact data from your terminal
The MoltSets CLI runs every MoltSets tool from the command line and enriches whole CSV files in one command. It is built to be run by AI coding agents like Claude Code and Codex, as well as by people.
install
# Run without installing
npx moltsets --help
# Or install globally
npm install -g moltsetsnode 18+ · json when piped · tables in a terminal
Every MoltSets tool, one command each
The CLI has one command per MoltSets tool, with the same data and limits as the API and MCP. Pipe it and you get JSON for scripts and agents; run it in a terminal and you get readable tables.
Run it without installing with npx moltsets --help, or install it globally with npm install -g moltsets. It needs Node.js 18 or later.
What you can do
- / 01Run any MoltSets tool as a command, with one flag per parameter
- / 02Enrich a CSV with
moltsets enrich - / 03Build lists: page through people and company search and write it straight to CSV
- / 04Check your account, billing and usage, for free
What people run it for
01 / Enrich a CSV
Point moltsets enrich at a file of LinkedIn URLs or emails. You get every original column back, plus verified emails, risk scores and a status for each row.
02 / Build a lead list
Page through people or company search with --max or --all, and write the results straight to CSV with --out.
03 / Bulk jobs for coding agents
Claude Code or Codex runs one command and reads the summary, so thousands of rows never pass through the conversation.
04 / Emails from names
Map your name and domain columns with --map and run search_business_email_by_name across a whole file.
05 / Run it on a schedule
Set MOLTSETS_API_KEY and run it from cron or CI. JSON output and documented exit codes make a failed run easy to catch.
06 / Check headroom first
whoami, billing and usage show your plan, token balance and fair use headroom before a big job, at no cost.
Installed in about a minute.
-
01 /
Get an API key
Sign up free at app.moltsets.com and create a key under API keys. Keys start with
ms_. -
02 /
Authenticate
Set
MOLTSETS_API_KEY, or runmoltsets loginin your own terminal to save the key. Scripts, CI and agents use the variable. -
03 /
Check it works
Run
moltsets whoami. It shows your plan, token balance and fair use headroom, and costs nothing.
From one lookup to a whole file
Check your setup, try a single lookup, then enrich a file in three passes: a dry run that makes no paid calls, a 10-row sample, and the full run.
Always dry-run first. If a run is interrupted, run the same command again and it resumes where it stopped.
Terminal
# Plan, token balance and fair use headroom (free)
moltsets whoami
# One lookup
moltsets linkedin_to_best_email \
--linkedin-url https://linkedin.com/in/john-smith-123
# Count rows and check headroom, no paid calls
moltsets enrich leads.csv --tool linkedin_to_best_email \
--column linkedin --dry-run
# First 10 rows only
moltsets enrich leads.csv --tool linkedin_to_best_email \
--column linkedin --limit 10 --out sample.csv
# The whole file
moltsets enrich leads.csv --tool linkedin_to_best_email \
--column linkedin --out enriched.csvTeach your agent the CLI
The CLI comes with an agent skill. It teaches the agent when to use the CLI and when to use MCP, to dry-run and sample before a full run, to use suppression lists, and how to read row statuses, plan notes and A-F risk scores.
Want more? Browse the skills library, or see every way to connect an AI agent.
Install the skill
# To ~/.claude/skills/moltsets-cli/
moltsets skill install
# Or anywhere else
moltsets skill install --dir ./skillsWhy use the CLI
01 / Bulk without the context cost
Files go through the CLI, not the conversation. Your agent runs one command and reads a summary, however many rows there are.
02 / Safe by default
--dry-run counts rows and checks your headroom with no paid calls, and --limit 10 runs a sample before you commit to the whole file.
03 / Handles the limits
Batches of 100, one lookup per duplicate, progress saved after every batch so a stopped run resumes, and a wait for the fair use window instead of a 429.
04 / Script and agent friendly
JSON on stdout when piped, logs on stderr, documented exit codes, and no prompts unless a person is at the terminal.
What it costs
The CLI is included on every plan, with the same data and limits as the API. Start free with 1,000 calls, then move to a flat-rate unlimited plan. Full detail on the pricing page.
free
Try before you commit, no card required.
get started- 1k data calls total
- 100 search records total
- Personal email included
solo
For solo builders and small lists.
get started- Unlimited data
- 500 search records / 5h
- Personal email included
pro MOST POPULAR
For teams enriching at scale.
get started- Unlimited data
- 7.5k search records / 5h
- Personal email included
team
For teams that have outgrown the $97 limits.
get started- Unlimited data
- 75k search records / 5h
- Personal email: 75k / week
Questions & answers about the MoltSets CLI
Running MoltSets from the terminal. Every command and flag is in the CLI docs.
A command-line tool for the MoltSets API, published on npm as @moltsets/cli. It has one command per MoltSets tool, an enrich command for CSV files, and free account commands. Run it without installing with npx moltsets --help, or install it globally with npm install -g moltsets.
Use the CLI for files, bulk jobs and coding agents that have a terminal, such as Claude Code and Codex. Use the MCP server for one-off lookups in a chat client like Claude or ChatGPT. Use the REST API to build MoltSets into your own product or a workflow tool. All three use the same data and plan.
An API key, the same kind the REST API uses (ms_...), created under API keys in the MoltSets app. The CLI reads --api-key first, then the MOLTSETS_API_KEY environment variable, then the key saved by moltsets login. The MCP’s Client ID and Client Secret don’t work with the CLI.
No. The CLI runs on your MoltSets plan, with the same data and limits as the API and MCP. Account, billing and usage commands are free, and a lookup that finds nothing isn’t charged.
moltsets enrich saves its progress after every batch. Run the same command again and it carries on where it stopped; --restart starts from the beginning. If your tokens run out mid-run, results already returned are kept and the remaining rows are marked dropped.
Before each batch it checks your fair use headroom. If the 5-hour window can’t cover the next batch, it says so and waits for the window to reset, or saves and stops if you pass --no-wait. On a 429 it waits the time the API gives and retries, up to four times. Searches never run more pages at once than your plan allows.
Yes, Node.js 18 or later. npx moltsets --help runs it without installing, or npm install -g moltsets installs it globally.
Not working in a terminal?
For AI Agents
A copy-paste setup prompt and connection steps for Claude, ChatGPT, Cursor and other agents. Connected in a couple of minutes.
how it works →MCP Server
Give Claude, ChatGPT, Cursor or any MCP client live access to verified contact data. Ask in plain English; the agent makes the calls.
how it works →REST API
One POST endpoint per tool, one response shape across all of them. Wire verified emails and mobiles into Clay, n8n, your scripts or your product.
how it works →Chrome Extension
Enrich any LinkedIn profile from a side panel in one click, build lead lists as you prospect, and send them to HubSpot, Attio, Salesforce or Clay.
how it works →Get your API key
1,000 API calls, no card. Sign up and start calling the API today.