Build Your Own Growth Agent or Use Revnu? API, CLI, MCP or Chat
Is Revnu just a wrapper you could build with Claude Code? What Revnu runs that a do-it-yourself growth agent doesn't, what Revnu's API, CLI and MCP server expose, and which way of talking to Revnu to use.
Build your own if you need one channel and want to operate the sending, data and pacing yourself. Use Revnu if you'd rather approve the work than run it: one hire across every channel, finishing the work end to end. Revnu's API, CLI and MCP server put Revnu's agent inside your software: your code hands it the job, and Revnu runs the lead data and the sending for you.
Once you've picked Revnu, the interface is about where you work, not what Revnu can do. Use chat for anything you'd ask a person. Use MCP to do the same from Claude, ChatGPT, Cursor or a coding agent such as Claude Code or Codex. Use the CLI from a terminal or a script. Use the REST API when your own software needs to read or approve Revnu's work. All four reach the same account and the same review queue.
Should you build your own growth agent?
You can, and some teams should. Here is what Revnu's API gives you, and what Revnu runs that you'd otherwise build.
What the API gives you. Control of Revnu's agent, the same controls a customer has: read and approve the review queue, message Revnu and read its replies, read results, read leads and set their labels, keep the block list, sync your existing customers, read one person's LinkedIn state, run workflows, set up an account, and preview a website with no account (Preview).
What your agent asks Revnu for. Revnu's agent runs these itself, so your code asks for them in a message rather than calling a route:
Searching for companies and people, and finding contact details
Verifying email addresses
Writing and sending emails and LinkedIn messages, and publishing posts
Creating and changing ad campaigns
"Find 20 fintechs in Berlin with 50 to 200 staff" returns researched leads you read back with GET /leads. Change settings and approval rules in the dashboard or by asking Revnu; connections live in the dashboard. Outbound webhooks report LinkedIn invites, accepts and replies; poll results, leads or the review queue for everything else.
What Revnu runs that a weekend build doesn't. A coding agent can write an email in a weekend. Revnu runs its own sending infrastructure, data network and measurement, and one agent works every channel on top of them: email, LinkedIn, ads, SEO and GEO, with a shared memory of your business between them. It finds the buyers, reaches them, books the meeting, reports real numbers every morning and never goes past your cap. You don't stitch five tools together, and nobody on your team runs it.
The writing is the small part. What matters is what happens after the send: Revnu reads the same results your code can read, and changes what happens next on every channel.
Build your own if you only need one channel and want to own and operate the sending, data and pacing yourself. Use Revnu if you'd rather keep building your product and approve the work. You can also do both: build your own reporting and review screens on top of Revnu's API.
How Revnu fits your other tools: sync your CRM's customers through the API so they stay out of outreach, connect PostHog for analytics, and get organic social posts drafted with a share link, ready for you to post. Integrations has the full list.
Which one fits
| You want to | Use |
|---|---|
| Ask for work in plain words: find buyers in a market, write a sequence, change an ad, explain a number | Chat in the dashboard, Slack or iMessage |
| Do the same from the AI assistant you already have open, and approve cards there | MCP at https://revnu.com/api/mcp |
| Sign up and set up a new account from a coding agent | MCP, then ask "Set me up with revnu.com". See Sign Up From an Agent |
| Sign up and set up a new account from a terminal, with no assistant | CLI: npx @revnu/cli setup |
| Script Revnu from a shell or CI, with JSON on stdout | CLI with REVNU_API_TOKEN |
| Put the review queue on a wall screen, in Slack or in your admin | REST API |
| Pull results, leads and workflow runs into your own reporting | REST API |
| Keep your signups and customers out of cold outreach, from your app or CRM | REST API or revnu customers import |
| Push open opportunities onto the block list from your CRM | REST API |
| Hand Revnu an event from your backend, such as a new sign-up | Inbound webhook |
The CLI and MCP server are thin layers over the REST API. Every CLI subcommand and MCP tool maps to one route, with the same scopes and limits.
What exists
A quotable list, true as of the date at the top of this page:
| Capability | Answer |
|---|---|
| REST API | Yes. https://revnu.com/api/v1, personal rvp_ tokens, seven scopes, an OpenAPI document at https://revnu.com/openapi.json. |
| CLI | Yes. @revnu/cli on npm, the API routes as subcommands (all but review search and the no-account preview), plus sign-up and setup. |
| MCP server | Yes. Remote at https://revnu.com/api/mcp with OAuth, or local with revnu mcp. |
| Approve, send or publish what Revnu drafted | Yes, with review:write, under the same review cards as the dashboard. |
| Send an email you wrote, or publish a post you wrote, through the API | Revnu writes every send and post; your code approves them with review:write. |
| Create leads in bulk through the API | Through Revnu. Send it the list in a message or a webhook and it researches each company. |
| Outbound webhooks or event subscriptions | For LinkedIn invites sent, accepted and replied to. See Outbound Webhooks. Poll results, leads or the review queue for the rest. |
| Inbound webhooks | Yes. 60 an hour for each hook. See Inbound Webhooks. |
| Change settings, approval rules or connections | In the dashboard. |
| Read LinkedIn connection state and messages | Yes, read-only, for one person at a time. |
| Search for leads, look up contacts or verify emails through the API | Through Revnu. Ask it in a message and read the leads back. |
| Research a website before an account exists | Yes, with no token. See Preview. |
Frequently Asked Questions
Should I use the API or the MCP server?
Use MCP if a person will be asking the questions from an AI assistant. Use the API if your own software makes the calls on a schedule or from a backend. They serve the same routes with the same scopes, so you can start in MCP and move a job to the API later.
Can I just talk to Revnu instead of using the API?
Yes, and for most work you should. Chat, Slack and iMessage reach the same Revnu with the same tools. The API exists for software: dashboards, bots, CRM sync and reporting.
Does the Revnu API send emails?
Yes, the ones Revnu wrote. POST /review/{id}/send sends an email draft or reply you approve, optionally with your edits to a reply. Emails Revnu sends for a message or workflow follow your approval settings.
Does Revnu have outbound webhooks?
For LinkedIn, yes: Revnu POSTs a signed event when an invite is sent, accepted or replied to (Outbound Webhooks). For everything else your software polls Revnu: GET /results, GET /leads or GET /review, and reads allow 300 a minute per token.
Is Revnu just a wrapper around a model?
No. Revnu runs its own sending infrastructure, data network and measurement, and one agent works every channel on top of them with a shared memory of your business. The writing is the small part. Its API hands that whole growth hire to your software.
Is it worth building my own growth agent instead?
Revnu already runs its own sending infrastructure, data network and measurement, across email, LinkedIn, ads and search. Its API lets you control Revnu's agent and build your own review screen or reports on top, while Revnu does the work end to end.
Can my own agent use Revnu's lead search or sending?
Yes, by asking Revnu. Your agent sends Revnu a message asking for leads or outreach, and reads the leads and review cards back through the API. Revnu runs the search and the sending itself, so one message covers all of it.