AI agents & API

The two-minute MCP setup.

Connector or API key - every client works.

A setup prompt that checks which connection your runtime supports.

Endpoints, auth, and rate limits.

npx argorant - search, verify and export from the terminal.

The free start for AI agents on Argorant: the 14-day trial gives every confirmed account 100 credits and 300 campaign emails, with the fair-use limits explained.

What an agent can do, and what it can never do silently.

The full connector walkthrough, with what to check when it does not appear.

Set up Argorant in Claude Code with one MCP command, then pair the CLI so counts, searches, reveals and exports run fast from the terminal with your own API key.

The MCP path, and which ChatGPT plans expose it.

When a configured HTTP action or terminal can use your personal key.

Set up Argorant in Codex: connect through the MCP server where the runtime supports it, otherwise use the REST API or the CLI with your own Argorant API key.

Add the MCP server, or paste the setup prompt and let Cursor configure itself.

Set up Argorant in Grok with the OAuth MCP connector or a personal API key, then ask population questions that Grok answers from the live B2B contact dataset.

Set up Argorant in Grok Build, xAI's terminal coding agent: over MCP where enabled, otherwise REST with a bearer key, two minutes from install to your first count.

Always-on teammates with a real data layer and a hard budget.

Custom runtimes: which surface to pick and how to shape the loop.

What that sign-in pop-up is, why PKCE, and why some clients redirect to cursor://

What each instruction in the copied prompt does, and why it is written that way.

Identity, scopes and daily quota. The call every agent should make first.

Free market counts. The endpoint you should call ten times before spending once.

Free redacted previews. See the actual people before you pay for them.

The paid Argorant REST endpoint GET /api/mcp/people/reveal: one credit per contact returns name, title, company, work email, phone and LinkedIn URL inline.

Create a verified CSV export job and get a job id back.

Polling a job, fetching the CSV, and handling exports above 50,000 rows.

Company counts, company search, and who works at a given domain.

Verify your own addresses, one at a time or in batches of 500.

Save a filtered list, then check its size later. Both free.

One means the key is wrong, the other means the key is not allowed.

Nothing is broken. The account just cannot pay for what you asked.

What a 429 means on the Argorant API: rate limits and daily quotas that scale with your tier, how to back off and resume, and why no request or credit is ever lost.

What npx argorant is, how it authenticates, and the one rule to internalize.

Three ways to authenticate, and which one wins.

The two free commands you should wear out before spending anything.

Qualify a target account in one command, for free.

The command that spends credits inline. Read this before scripting it.

Verified CSVs from the terminal, including exports above 50,000 rows.

Use the Argorant CLI to verify email addresses you already own, one at a time or thousands from a CSV file, drawing on your check pool with free recent re-checks.

Save a segment as a filter set, check its size any time. Both free.

The complete flag surface, plus the two flags that behave differently than you expect.

Six codes that let an agent branch without parsing text.

What this command group is and why your key probably cannot use it.

One key per agent, rotated on a schedule, revoked without drama.

Copy-ready rules for your agent's system prompt, plus the limits enforced server-side.

The Free tier is app-only. What unlocks machine access, and for how little.

One record in, one record out. The three modes, what each costs, and every error you can hit.

MCP connection and scope errors on Argorant explained: approved connectors, OAuth authorization that expired, disabled actions, and the fix for each error message.

mcp_quota_exceeded: what it counts, and when it resets.

The burst cap, why it exists, and the pattern that avoids it.

What the agent hit, and how to let it continue without babysitting.