Works in Claude · ChatGPT · Cursor · Windsurf

Your GTM pipeline,
in plain language.

Connect RichAPI to Claude or ChatGPT once. Then just ask: "Find 20 VPs of Marketing at Series-B SaaS companies who posted about pipeline this week, with verified emails." RichAPI does the data work behind the scenes — searching, enriching, verifying across 50+ sources — and your assistant hands back the list with a cost receipt. No code. No CSV shuffling. No platform subscription.

Start free — 25 credits, no card See starter prompts

Claude@richapi · 35+ tools

Find 20 Series-B SaaS CTOs who posted about hiring this week, get verified emails

richapi_post_keyword_search20 authors · 6 cr

richapi_enrich_profile×20 · 20 cr

richapi_email_finder×20 · 100 cr

✓ 20 profiles · 14 verified emails · 126 credits ($2.52)6 search + 20 enrich + 100 email finding = 126

RichAPI MCP is a Model Context Protocol server for GTM data. It gives Claude, Cursor, Windsurf, and ChatGPT 35+ tools — LinkedIn profile/company enrichment, people search, post and hiring signals, and five multi-provider waterfalls (email finding, phone finding, email verification, person and company enrichment) — from the same key and credit pool as the REST API at api.richapi.ai. Billing follows published per-call or per-result endpoint rates.

What you can ask for

If you can describe your buyer, you can build the list.

"Who's actively in-market this week?" → people who posted, commented, or started hiring around your topic — fresher than any static database.
"Get me their verified emails." → multiple data providers tried automatically; endpoint rates and receipts make each step auditable.
"Research these 30 accounts." → company data, tech stacks, headcount, recent posts — summarized by your assistant, sourced by RichAPI.
"Check this list before I send." → email verification that flags risky and invalid addresses, at a penny each.
"What did that cost?" → every answer includes its own receipt. Ask anytime; the usage report is free.

The same actions are available as a REST API for whoever on your team writes code — same account, same credits.

You stay in control

Built so you can let an assistant loose on it.

Read-only by design. RichAPI tools look things up. They never send emails, never write to your CRM, never trigger outreach. The worst a confused prompt can do is spend a few credits — never embarrass you in front of a customer.
Spend limits you set. Cap what a workspace can spend; the assistant sees its own running cost ("126 credits so far") and so do you.
Receipts on everything. Which source answered, what was billed, what was refunded — in every result.
Free practice mode. The 25-credit sandbox needs no card. Let Claude try it before a single euro is at stake.

Connect

Connected in about a minute.

Three plain steps

Create your account → app.richapi.ai/signup (25 free credits, no card)
Connect your assistant → In Claude: Settings → Connectors → RichAPI → Connect. (This path goes live with the Anthropic directory listing; until then, the config route below works today.)
Run your first starter prompt → pick one from the library below; your first verified list arrives with a receipt.

For implementation owners — manual config (Claude Desktop, Cursor, Windsurf, ChatGPT)

Claude Desktop / Cursor — via mcp-remote shim

{ "mcpServers": { "richapi": {
    "command": "npx",
    "args": ["mcp-remote", "https://mcp.richapi.ai/mcp",
             "--header", "x-api-key: ${RICHAPI_KEY}"] } } }

Windsurf — native remote

{ "mcpServers": { "richapi": {
    "serverUrl": "https://mcp.richapi.ai/mcp",
    "headers": { "x-api-key": "${RICHAPI_KEY}" } } }

Per-client guides (Continue, Zed, VS Code, ChatGPT connectors): docs.richapi.ai/mcp — client config formats change faster than marketing pages; the docs page is canonical.

Starter prompt library

Copy, paste, edit the brackets, run.

Weekly pipeline fill

@richapi find 20 [VPs of Marketing] at [50–200 person SaaS companies] who posted about [pipeline / hiring SDRs] in the last week. Enrich them and get verified emails. Table the results, flag the misses, and tell me the total cost.

Account research before a call

@richapi research [acme.com]: company size, tech stack, recent LinkedIn posts, and who runs [marketing]. Two-paragraph summary.

Mine a competitor's engagement

@richapi who liked and commented on this post [URL]? Enrich the top 20 by seniority and find their emails.

List hygiene before a send

@richapi verify these emails [paste] and split into valid / risky / invalid. Cost me as little as possible.

Signal watch (save and re-run weekly)

@richapi which of these accounts [paste domains] posted jobs or content about [topic] in the last 7 days? Rank by activity.

Each prompt shows its receipt when it finishes. Typical cost of the weekly pipeline fill: ~120-160 credits ≈ $2.40-$3.20.

Why one connector beats five

Every data vendor ships an MCP server for their own database now. Connect five and your assistant juggles five logins, five bills, and five tool lists. RichAPI is one connector whose tools run across providers automatically — one schema, one invoice, billed by outcome. Fewer tools is also how assistants stay accurate: less catalog, better choices.

Pricing

Same bundles as the REST API

Sandbox

25 credits · no card

All endpoints unlocked
REST + MCP
Rate-limited for evaluation

For: your first 200 OK and an MCP test-drive.

Start free

Starter

$100

5,000 credits · never expire

All endpoints
REST + MCP
Email support

For: prototypes and small pipelines.

Buy Starter

GrowthMost popular

$450

25,000 credits (11% bonus) · never expire

Priority support

For: production pipelines and agent builders.

Buy Growth

Scale

$800

50,000 credits (25% bonus) · never expire

Priority support + shared Slack channel

For: production at volume, agencies, platform prototypes.

Buy Scale

Enterprise

Custom

Committed volume

Custom rate card on committed volume
99.9% uptime SLA
SOC 2 documentation under NDA
DPA/MSA · white-label webhooks
Custom rate limits · dedicated engineer contact

Talk to sales

Same credit pool whether your assistant calls it or your code does. Endpoint rates are explicit and auditable. See full pricing →

FAQ

Frequently asked questions

Do I need to code?

No. Connect once, then everything happens in plain language. Code is optional, for automating what you've already proven in chat.

Can I break something?

No — every RichAPI tool is read-only data lookup. Nothing gets sent, posted, or written to your systems. The blast radius of a bad prompt is a few credits.

How do I control spend?

Set a workspace spend cap; watch the receipt in every result; the usage report is free to check. Sandbox mode costs nothing to try.

Which assistants work?

Claude (web/desktop/Code), ChatGPT (connector support varies by plan), Cursor, Windsurf, Continue, Zed — anything MCP-compatible.

Is this a Claude wrapper?

No — it's a thin protocol surface over a data engine that's run since 2018. Better models make it more useful.

What does a typical session cost?

A 20-prospect research-and-verify run is often around 120–160 credits ($2.40–$3.20), depending on endpoint mix.

What if Claude is down?

The REST API keeps working — same key, same credits.

Can I white-label this for my product?

Yes — partner program: /partners.

Your next list is one prompt away.

Start free — 25 credits Copy a starter prompt

Your GTM pipeline,in plain language.