Privy MCP Server
Segments, campaigns, popups and tags for your Privy account.
Servidor MCP hospedado
npx add-mcp 'https://cotlet.dev/mcp/v1/privy'Instala no Claude Code, Codex, Cursor e outros
Documentação
Cotlet · Integrations · How it works · Security · For developers · For automation agencies · Blog · API docs · Help center · Changelog · Contact · Pricing · Sign up
Privy API and MCP server: Let your AI agent run the Privy campaigns, not just read them.
Privy runs its own MCP server at mcp.privy.com on paid plans, and "all tools are read-only" (checked 27 Oct 2026). Its public API has read campaigns, flows, displays and segments since 22 Oct 2026, and writes only contacts, orders and events. Cotlet runs 13 Privy tools hosted, over MCP for agents and REST for scripts, 8 of them writes: segments, campaign drafts, sends, popups and tags.
Segments, campaigns, popups and tags for your Privy account. Use it in ChatGPT, Claude or any AI agent over MCP, or in n8n, Make and scripts over REST.
- Free 7-day trial, no card
- Unofficial, not affiliated with Privy
- Page: https://cotlet.dev/integrations/privy-api-mcp-server
Cotlet is an independent service. It is not affiliated with, endorsed by or sponsored by Privy. Privy is a trademark of its owner. If Privy's own integrations cover what you need, use them first.
What can you automate in Privy?
- Resend a sale email to non-openers
- Schedule the weekly newsletter
- Build a segment from one prompt
- Pause popups that do not convert
- Tag contacts for a sunset flow
- Report campaigns, flows and popups
Does Privy have an MCP server or an API?
- For questions such as "how did my welcome flow do last month", Privy's own MCP is free on a paid plan and reads more than ours: coupons, orders, products and reports.
- Nothing official creates a segment, copies or schedules a campaign, or pauses and relaunches a display.
- The Zapier app is "private and available by invitation only" and has 4 contact actions. Tags change one contact per API call, 60 calls a minute.
| What you need | Privy MCP | Privy API | Cotlet |
|---|---|---|---|
| Read campaigns, flows, popups, segments | Yes, with reports | Yes, since 22 Oct 2026 | Yes |
| Create a segment | No | No | Yes |
| Draft, copy or schedule an email | No | No | Yes, sends after your OK |
| Pause or relaunch a popup | No | No | Yes |
| Tag contacts | No | One contact per call | In bulk, after your OK |
| What you need first | A paid plan | A paid plan and a token | Your Privy login |
Checked 27 Oct 2026. Sources: Privy Help: Privy MCP, Privy Help: API Overview, Privy API Changelog, Privy Help: Connect Privy to Zapier, Privy pricing
How does Cotlet connect to Privy?
- Sign in to Privy. Use your own account in its Cotlet Cloud Browser.
- Choose MCP or REST. Connect your agent or create a Cotlet API key.
- Run your workflow. Ask your agent or send an HTTP request.
We never keep your Privy password, and no email send, popup relaunch or tag that starts a flow happens until you approve it.
Connect Privy to your agent or workflow
Use MCP with your AI agent, or HTTP requests in n8n, Make, Zapier and scripts. Follow the MCP setup below or jump to the REST guide.
- Sign in to Privy in a Cloud Browser. Create a Cotlet account, open Privy in its Cloud Browser, log in to the Privy dashboard, pick your business and press Enable for agents.
- Add the Cotlet address. Paste https://cotlet.dev/mcp/v1 into the MCP server or connector field of your agent.
- Approve the connection. Chat apps show a Cotlet sign-in page. Editors, n8n and scripts send an API key from the console.
Privy shares the address https://cotlet.dev/mcp/v1 with every other app you enable. You can keep Privy's own read-only server (mcp.privy.com) connected next to it; your agent then has two sets of Privy tools. Enabled Privy after connecting? Refresh the connector so the 13 tools appear.
Claude:
Settings > Connectors > Add custom connector
URL: https://cotlet.dev/mcp/v1/connect
Claude Code:
claude mcp add --transport http cotlet-privy \
https://cotlet.dev/mcp/v1 \
--header "Authorization: Bearer $COTLET_API_KEY"
ChatGPT:
Settings > Apps & Connectors > Create
MCP server URL: https://cotlet.dev/mcp/v1/connect
Authentication: OAuth
Cursor:
// ~/.cursor/mcp.json
{
"mcpServers": {
"cotlet-privy": {
"url": "https://cotlet.dev/mcp/v1",
"headers": { "Authorization": "Bearer ${env:COTLET_API_KEY}" }
}
}
}
Codex:
# ~/.codex/config.toml
[mcp_servers.cotlet-privy]
url = "https://cotlet.dev/mcp/v1"
bearer_token_env_var = "COTLET_API_KEY"
n8n:
MCP Client Tool (inside an AI Agent)
Transport: HTTP Streamable
URL: https://cotlet.dev/mcp/v1
Auth: Bearer, <your key>
Tool: privy_read
Make, Zapier:
Make: MCP Client > Call a tool
Zapier: MCP Client by Zapier > Run Tool
Server URL: https://cotlet.dev/mcp/v1
Token: <your key>
Tool: privy_write
How to use the Privy REST API
Create your Cotlet API key
Create a Cotlet API key with access to Privy and its read operations. Store it as COTLET_API_KEY in your environment or automation platform's credential store.
Connect Privy in Cotlet and enable it for agents. Account access: Your own Privy account, signed in to the business you want the agent to work in.
Make your first Privy API request
REST:
curl https://cotlet.dev/api/v1/privy/campaigns \
-H "Authorization: Bearer $COTLET_API_KEY"
Read campaigns and apply the operation limits
A successful REST call puts the tool output in result. This illustrative response excerpt omits call IDs, messages and credit details.
Illustrative response excerpt:
{
"status": "success",
"app": "privy",
"tool": "list_campaigns",
"result": {
"data": [
{
"id": "cmp_41c8",
"title": "October sale announcement",
"channel": "email",
"status": "sent",
"subject": "Our October sale starts now",
"send_date": "2026-10-20T10:00:00-04:00",
"delivered": 4820,
"opened": 1930,
"clicked_percent": 2.4,
"unsubscribed_percent": 0.3
},
{
"id": "cmp_3a07",
"title": "Fall lookbook",
"channel": "email",
"status": "sent",
"subject": "The fall lookbook is here",
"send_date": "2026-10-06T10:00:00-04:00",
"delivered": 4710,
"opened": 2105,
"clicked_percent": 3.1,
"unsubscribed_percent": 0.2
},
{
"id": "cmp_5b92",
"title": "October sale resend",
"channel": "email",
"status": "draft",
"subject": "In case you missed it: our October sale",
"send_date": null,
"delivered": 0,
"opened": 0,
"clicked_percent": 0,
"unsubscribed_percent": 0
}
],
"pagination": {
"page": 1,
"per_page": 25,
"total_count": 3,
"total_pages": 1
}
}
}
Returns the rows of the Campaigns table: title, channel, status, subject and send date, plus Delivered, Opened, Clicked and Unsubscribed. Opened is a count and the other two rates are percentages of delivered contacts.
Privy tracks an open with an invisible image, so a contact whose client blocks images is not counted as opened.
page: Page number, starting at 1
per_page: Items per page
Keep the same selection when continuing a list. Compare changed record values as well as identifiers when refreshing your destination.
Privy workflows for agents and automations
| Tool | Connect through | Example workflow |
|---|---|---|
| n8n | HTTP Request | List popups, flyouts, bars and other displays with status, views and signups. Use list_displays in your configured marketing report. |
| Make | HTTP > Make a request | List automated flows with status, trigger and the steps they contain. Use list_flows in your configured marketing report. |
| Python or Node.js | REST API | Search contacts, or list the members of a segment, with consent and tags. Use list_contacts in your configured marketing report. |
Send Authorization: Bearer <your Cotlet API key> in request headers. You configure the schedule, destination and record comparisons.
Cotlet reads Privy; your workflow steps write to your chosen destination. These HTTP workflows do not require a native Cotlet connector or a prebuilt template.
Python and Node.js can use the same HTTP requests without an AI agent. Keep access keys in credentials, outside shared workflow exports.
The API and MCP reference lists operations and inputs. The REST API guide explains authentication, errors and approvals.
Privy API endpoints and MCP tools
Reads
Opened is a count; Clicked and Unsubscribed are percentages of delivered. Privy counts no open when an email client blocks images, so Did not open holds some readers. Archived displays come back only when you ask for them.
- List campaigns (
list_campaigns, read): List email and SMS campaigns with status, subject, send date and results. - List flows (
list_flows, read): List automated flows with status, trigger and the steps they contain. - List displays (
list_displays, read): List popups, flyouts, bars and other displays with status, views and signups. - List segments (
list_segments, read): List custom and smart segments with the number of mailable and textable contacts. - List contacts (
list_contacts, read): Search contacts, or list the members of a segment, with consent and tags.
Segments and campaigns
Privy cannot edit a segment's conditions after it is made, so a wrong campaign name means a new segment. A draft uses the template as saved; the tools do not edit designs. Unschedule works only before Privy starts preparing the send.
- Create a segment (
create_segment, write): Create a custom segment from conditions such as Did not open a campaign. - Duplicate a campaign (
duplicate_campaign, write): Copy a campaign into a new draft with its own name, subject and recipients. - Create an email campaign draft (
create_email_campaign, write): Create an email campaign draft from a template, with subject and recipients. - Send or schedule an email campaign (
send_email_campaign, write, asks first): Send a draft email campaign now or schedule it for a day and time. - Unschedule a campaign (
unschedule_campaign, write): Move a scheduled campaign back to draft.
Popups and tags
Pausing hides a display and keeps it; Launch shows it again under its old targeting. A tag can start a flow set to Contact Tagged, which may email or text those contacts.
- Pause a display (
pause_display, write): Pause a live popup or other display so visitors stop seeing it. - Launch a paused display (
launch_display, write, asks first): Turn a paused display back on so visitors see it again. - Tag contacts (
tag_contacts, write, asks first): Add a Privy tag to contacts, or remove it from them.
Inputs, REST path and example response of every tool: https://cotlet.dev/integrations/privy-api-mcp-server#tools
Who can see my Privy session, and how do I revoke it?
- What we store. Your signed-in Privy profile, AES-256-GCM encrypted, in Finland. No password.
- What your agent gets. The 13 Privy tools, never the cookie or the login.
- What the session sees. The business you picked: contacts, consent, campaigns, popups, flows.
- What no tool touches. Billing, plan, SMS numbers, store connection, designs, deletes.
- If Privy signs you out. You log in again yourself, in the same Cloud Browser.
- How to cut access. Disable for agents, reset the browser, or change your Privy password.
Contacts carry email and SMS consent, and no tool changes consent. Our site scores A+ on Qualys SSL Labs, securityheaders.com and Mozilla Observatory (live results).
Approvals, undo and mistakes
- Checks the original. Sent 2 to 3 days ago, as Privy advises, or the agent stops.
- Builds the segment. Did not open, with the exact campaign name, and its mailable count.
- Copies the email. New subject, new audience, still a draft that reaches no one.
- Waits for your OK. The send time and audience show up in your Cotlet console first.
| Action | Undo |
|---|---|
| Create a segment or draft | Nobody sees it; delete it in Privy |
| Schedule a send | unschedule_campaign, before preparation starts |
| Send now | No, sent emails cannot be recalled |
| Pause a popup | launch_display shows it again |
| Add a tag | Remove it; a flow it started may have sent |
3 of 13 tools ask first: send_email_campaign, launch_display and tag_contacts. A segment, a draft, an unscheduled send or a paused popup reaches no shopper, so they run at once. You can turn the wait off per tool for a weekly send you already checked.
The audience is fixed when you approve the send, and Privy may send a scheduled email a couple of minutes early. Approve with a margin.
MCP call:
{
"name": "send_email_campaign",
"arguments": {
"campaign_id": "cmp_5b92",
"send_at": "2026-10-22T10:00:00-04:00"
}
}
REST:
curl -X POST https://cotlet.dev/api/v1/privy/campaigns/cmp_5b92/email-campaigns \
-H "Authorization: Bearer $COTLET_API_KEY" \
-H "Content-Type: application/json" \
-d '{"send_at":"2026-10-22T10:00:00-04:00"}'
Response:
{
"campaign_id": "cmp_5b92",
"status": "scheduled",
"send_at": "2026-10-22T10:00:00-04:00",
"send_in_recipient_timezone": false
}
A cron job or n8n flow calls the same tools over REST at /api/v1/privy, with the same key and price, for example a Monday script that drafts the newsletter and leaves the send for you. A send on a campaign that is not a draft fails, and failed calls are free. Each tool row above shows its REST path.
How much does the Privy MCP server cost?
About $13 a month for a store with about 4,000 mailable contacts, 2,270 credits. Your Privy plan stays as it is.
| Job | Calls | Credits |
|---|---|---|
| Weekly campaign from a Saved Template | 4 × 4 | 160 |
| Resend to non-openers 2 days later | 5 × 4 | 200 |
| Monday report: campaigns, flows, popups | 3 × 4 | 120 |
| Pause popups under your signup rate | 4 × 4 | 160 |
| Tag Unengaged Contacts for the sunset flow | 10 × 1 | 100 |
| Pull back a send with a wrong subject | 3 × 1 | 30 |
| Cloud Browser, 30 days | 1,500 | |
| Total | 2,270 |
- Free 7-day trial, no card
- 10 credits per successful call, MCP or REST
- 50 credits a day for the Cloud Browser
- No API token or Zapier invitation needed
The month is our example: one weekly newsletter, one resend a week, a Monday report, a popup check and one sunset tagging run. Privy prices Email by mailable contacts, from $30 a month for 1,500 to about $90 at 5,000 (reviews, Oct 2026), with unlimited sends. Dollars at the $29 pack rate.
Privy MCP server on GitHub, Zapier or hosted: which to use
| Option | What it does | Where it stops |
|---|---|---|
| Privy MCP | Privy's hosted server: search, describe and execute over campaigns, flows, displays, segments, contacts, coupons, orders, products and reports. In Claude's connector directory. | Read-only; paid Privy plans only. |
| Privy/privy-cursor-plugin | Privy's Cursor plugin around the same server, MIT, 0 stars, last commit 4 Sep 2026. | Read-only, same limits. |
| Privy Zapier app | Create, find, find or create, and update a contact. | Invitation only; contacts only, no campaigns, segments or popups. |
| incentivai-io/privy-mcp-server | An MCP server for privy.io wallet accounts, 1 star. | A different company with the same name; it does not reach privy.com. |
We found no privy.com MCP server or CLI on GitHub that writes. For questions about your numbers, connect Privy's own MCP. For a store that pushes contacts or orders from its own code, the API covers it. For an agent that builds segments, schedules sends and pauses popups, Cotlet does it hosted, next to the official server.
Who runs Cotlet
Cotlet is run by Take Group sp. z o.o., a software company registered in Poland, EU (VAT PL6342984273) and in business since 2019. Its founders are Bart Krawczyk (Co-founder, CTO) and Jake Slugocki (Co-founder, SEO, sales and marketing). Send questions about the Privy tools to contact@cotlet.dev.
Privy API and MCP: questions
How do I get access?
Sign up free at https://cotlet.dev, open Privy under Integrations in the console and log in to Privy in its Cloud Browser. The trial starts when you sign up and asks for no card.
How do I connect Privy to ChatGPT or Claude?
Sign up at cotlet.dev, log in to Privy once in its Cloud Browser and add Cotlet to ChatGPT or Claude, following the steps in your console. No API key is needed. ChatGPT and Claude then work in your Privy account through Cotlet, in their phone apps too.
What can ChatGPT do in Privy?
With Cotlet, ChatGPT, Claude and other AI agents handle jobs like these in Privy: resend a campaign to people who did not open it; schedule a weekly email campaign; pause popups that do not convert. You ask in plain words, and anything that reaches other people waits for your OK first.
Do I need a paid Privy plan?
Privy's own API and MCP server need one, and only paid businesses show up in the MCP business picker. Cotlet works in your dashboard instead, so you need whatever your plan allows there. SMS campaigns, for example, need a plan that includes SMS and an approved toll-free number.
Why are some people who opened my email in the Did not open segment?
Privy tracks an open with an invisible image. If the recipient's client blocks images, Privy counts no open, so the segment holds some people who read the email. A resend to them is harmless but redundant.
What can it not do in Privy?
The tools do not edit an email or popup design, build or publish flows, send SMS campaigns, import contacts from CSV or delete contacts. You change a design in the Privy editor, and the agent sends the result. Reads cover campaigns, flows, displays, segments and contacts.
Should I use Privy's own MCP server instead?
For reading, yes: it is free on a paid plan, Privy maintains it, and it reads coupons, orders, products and reports that our tools do not. It cannot change anything. Use both if your agent should also build segments, schedule sends and pause popups.
Can it react when someone signs up?
Cotlet has no Privy trigger. Privy's own webhooks send Signups and Orders to Slack or a URL you choose, so an n8n flow can start your agent from there. Or run the agent on a schedule.
Is this the Privy wallet company?
No. These tools work with privy.com, the popup, email and SMS app for online stores, not privy.io.
Is the MCP server different from the REST API?
Only in how it is called. Both carry the same 13 tools, inputs, answers, API key and price. Agents use MCP; scripts and HTTP steps use REST.
Is Cotlet affiliated with Privy?
No. Cotlet is independent and not affiliated with Privy Operations, LLC.
Can I use the Privy API without an AI agent?
Yes. Call Cotlet's REST API from a script or an HTTP step in n8n, Make or Zapier with your Cotlet key. MCP is the alternative for AI agents; you do not need to connect an agent to use REST.
Give your AI agents your signed-in browser.
Product: Integrations · How it works · Pricing · Security
Resources: Blog · API docs · Help center · Changelog · GitHub
Solutions: For developers · For automation agencies
Company: About · AI info: company facts · Contact
Legal: Terms of service · Privacy policy · Refund policy · Acceptable use · Cookie policy · DPA · Subprocessors
Elsewhere: Status page · Cotlet on GitHub · Cotlet on X · Cotlet on LinkedIn · Cotlet on Product Hunt · Cotlet on Crunchbase · Cotlet on SaaSHub
Cotlet.dev is built by Bart Krawczyk and Jake Slugocki, the founders of Take Group sp. z o.o., ul. Wincentego Janasa 4, 40-855 Katowice, Poland. KRS 0000871398, NIP 6342984273, VAT EU: PL6342984273. About us
Cotlet is an independent service. It is not affiliated with, endorsed by or sponsored by any of the products listed on this site. Product names are trademarks of their respective owners.