Tools / Email finder / Tool
Bulk email verification software usually means uploading a CSV to one more dashboard. Here your agent reads the list from a file, a sheet or a workspace table, runs contact.verify on each address in one batch with a total spend cap, and writes valid, invalid or unknown back next to every row.
Ask your agent
Verify every email in leads.csv, keep a max total cost of $5, and give me back a CSV with a status column.
Connect RouterGrowth once, then ask in plain words. New workspaces start with $1 of credit. Get a key or read the setup guide.
A real run
One call to contact.verify (email deliverability check), run through RouterGrowth on October 16, 2026. These are the first rows it returned; fields that name a person are masked.
| status | certainty | mx_provider | |
|---|---|---|---|
| t***@***.co.uk | valid | ultra_sure |
One row of a list check, shown on its own: a UK domain address came back valid and ultra_sure on Google Workspace.
Step by step
Add the MCP server to Claude, ChatGPT, Claude Code, Codex or Cursor, or call the REST API with your RouterGrowth key.
Point the agent at a CSV, a Google Sheet export or a RouterGrowth workspace table with an email column.
The agent sends the addresses through batch_run with a maximum total cost, so the job stops before going over budget.
Each row gets its status, certainty and catch-all flag. Ask for a CSV of the valid ones, or a count by verdict.
For invalid rows where name and company are known, the agent can find a fresh address with contact.find.
Price
List prices on this call, read from the catalog when this page was built. The exact figure is quoted before every run, and a monthly plan lowers it.
In practice
You describe the job; the agent picks the calls, shows the price and runs them.
Verify every email in leads.csv, keep a max total cost of $5, and give me back a CSV with a status column.
Check the emails in my webinar sign-up table and replace the invalid ones with found work emails.
How many addresses in this list are catch-all? List them separately.
Connect
One MCP server for Claude, ChatGPT, Claude Code, Codex and Cursor, or the same call over the CLI and REST with the input above.
claude mcp add --transport http routergrowth https://api.routergrowth.com/mcp
npm install -g routergrowth && routergrowth setup
routergrowth run -c contact.verify -i '{"email": "alex.rivera@example.com"}'curl -X POST https://api.routergrowth.com/v1/run \
-H "Authorization: Bearer $ROUTERGROWTH_API_KEY" \
-d '{"capability": "contact.verify", "input": {"email": "alex.rivera@example.com"}}'Worth knowing
batch_run takes a maximum total cost. The batch stops before it would pass it.
Ask the agent to dedupe the list before the run, so the same address is not checked twice.
Rows are read and written by your agent. There is no upload to a separate verification site.
FAQ
The batch runs row by row, so size is limited by your budget and time, not by a file limit.
Whatever you ask for: a CSV, rows added to a sheet, or a workspace table with the verdict per address.
Each verdict returned is charged, valid or invalid. A row where no provider returns a result is not.
Yes, if your agent runs on a schedule. Each run verifies the rows you point it at.
More on Email finder
Reading this as an agent? This page as markdown: /tools/email-finder/bulk-verification-software.md
Connect your agent once. The first calls run on the $1 that comes with signup.