This server has a remotely hosted endpoint. Open its connector listing for connection details, authentication requirements, and setup instructions:
The Send4 MCP server is hosted by Send4 at https://mcp.send4.ai/mcp. There's nothing to
install or run: add the address to your assistant, sign in to Send4 in your browser, and choose
what the assistant may do. This repository holds the setup guides, the tool list and the place to
report a problem. It does not contain the server's code.
Pick your assistant. Cursor and VS Code install from the button; the others open a short guide.
Prefer to set it up by hand? Any assistant that supports remote MCP servers takes the address:
https://mcp.send4.ai/mcpRelated MCP server: Mirlo MCP Server
Understand your flows: "What does my website form flow do?"
Find out what went wrong: "Why did yesterday's conversation from the quote form stop?"
See where people drop off: "Which flow lost the most people this week?"
Check your numbers: "How did last week compare with the week before?" or "How close are we to our SMS limit this month?"
Build and fix flows: "Build a draft flow that thanks a new lead, asks for their address and books a site visit."
Run campaigns: "Create a draft campaign for leads tagged spring, and check it before launch."
Work the inbox and calendar: "Which conversations are waiting for a person?" or "Find a free 30-minute slot on Thursday."
More in examples/prompts.md.
Assistant | Where you add Send4 | Guide |
Claude (claude.ai, Claude Desktop) | Customize → Connectors (Pro, Max), or an owner under Organization settings → Connectors (Team, Enterprise) | |
Claude Code |
| |
ChatGPT |
| |
Grok |
| |
VS Code (GitHub Copilot) | The button above, or MCP: Add Server → HTTP | |
Cursor | The button above, or | |
Le Chat | Intelligence → Connectors → Add Connector | |
Perplexity | Account settings → Connectors → + Custom connector | |
Gemini CLI, Codex CLI, opencode | One or two commands |
Another assistant should work too if it connects to a remote MCP server over Streamable HTTP and signs in through your browser (OAuth with dynamic client registration).
A plan that includes it. Every paid plan does, and so does the 14-day trial once a card is on file. Starter has no campaigns, so campaign tools aren't offered there.
A Client Admin switches it on. In Send4, open Settings → Integrations → AI assistants and turn on Allow AI assistants under Workspace access.
You sign in as yourself. Each person connects with their own Send4 login.
flowchart LR
A["Your assistant<br/>Claude, ChatGPT, Cursor…"] -- "MCP over HTTPS" --> B["mcp.send4.ai/mcp"]
A -. "first time: sign in<br/>and choose what it may do" .-> C["app.send4.ai"]
B --> D["Your Send4 workspace<br/>as you, with your role"]You add the address to your assistant.
You sign in to Send4 in your browser. Send4 shows the account you're signed in to and the choices your role and your workspace allow. You tick what this assistant may do and select Connect.
The assistant asks Send4 for its tools. It only hears about the tools this connection can use.
You ask in your own words. The assistant picks the tools, and Send4 runs each one as you: your workspace, your role, your choices.
The workspace always comes from your sign-in. An assistant can't point a tool at another workspace.
Every connection can read. Each kind of change is a separate permission, off until a Client Admin allows it for the workspace and you tick it when you connect.
Permission | What it allows |
Read flows, runs, campaigns and usage | Every connection has this. Reads your flows, runs, campaigns, analytics and plan usage, and changes nothing. Phone numbers and email addresses are masked. |
Read conversation messages | What customers and the AI said to each other, and the details a flow collected. |
Build and change flows | Create flows, change their cards, rehearse them and switch them on. |
Create and launch campaigns | Create campaigns, add and tag leads, and launch, pause or cancel a campaign. |
Reply to customers and manage conversations | Reply, text someone first, assign, take over from the AI, and book, move or cancel meetings. |
Invite and manage team members | Invite managers and agents, change their role, and deactivate them. |
Create email addresses | Create new email addresses for the workspace on Send4. |
Open a group to see its tools. Each name links to that tool's full definition in tools/:
its description, its inputs and its safety hints, exactly as your assistant receives them.
For every role
Tool | What it does |
Which workspace and person this connection belongs to, what it was granted, and what it wasn't. | |
Your inbox, filtered as on the Conversations page, without the messages. | |
Your leads and tags, filtered as on the Leads page. | |
The meetings on your Send4 calendar. | |
The free times for a customer, or the times a meeting could move to. Nothing is booked. | |
The people in your workspace. A Client Admin sees their details, and anyone else sees names. | |
Your sending numbers and mailboxes, and whether a campaign can send from each. | |
Conversations started, replies, details collected, bookings and cost over time. | |
Messages and SMS parts sent and received, their cost, and your monthly SMS limit. |
For Client Admin and Client Agent
Tool | What it does |
Your flows, with their status and what starts them. | |
One flow in full, with its cards, settings and wiring. | |
Everything the flow builder would flag on a flow. | |
Every type of card a flow can use. | |
What one type of card does and which settings it takes. | |
Send4's rules and common traps for building a flow. | |
The ready-made flows a new flow can start from. | |
The identities a flow's AI can speak as. | |
The runs of one flow and how each ended. | |
How many runs of a flow started lately and how they ended. | |
Where conversations stop, across your flows or card by card in one. | |
What happened in one conversation or flow run, which cards it went through, and what's still missing. | |
How new wording differs from a card's current text. Nothing is saved. |
For Client Admin only
Tool | What it does |
What you've used against your plan in a month. | |
Your campaigns, with their status and results. | |
One campaign's status, progress and results. | |
A launched campaign's report, by card, day and meeting. |
Tool | What it does |
What was said in one conversation. Every role. |
Tool | What it does |
Start a draft flow, blank or from a template. | |
Copy a flow into a new draft. The copy gets its own webhook address, so anything that sends to the old one has to move. | |
Change a draft or switched-off flow: its cards, where each one leads, what starts it, its name and its settings. All the changes are saved together or not at all, and the answer reports anything they broke. A live flow can only be renamed. | |
Create or change a persona. A persona used by a live flow can't be changed. | |
Leave new wording on one card for a person to accept in the builder. It changes nothing live, so it works on a live flow too. | |
Play a flow as the customer on Send4's simulator. Nobody is texted, but webhook, email and Hanna cards still send for real, marked as tests. | |
Read what was said in a rehearsal. | |
See what switching a flow on, or a live flow off, would do, without doing it. Send4 gives the assistant a summary to show you and ask for your yes. | |
Switch a flow on or off. Switching one on, or a live one off, needs the code from that preview. |
Tool | What it does |
Count who a campaign would reach, before creating it. | |
Create a draft campaign. Nothing is sent. | |
Run every launch check and work out the cost, without sending anything. Send4 gives the assistant a summary to show you and ask for your yes. | |
Send a draft campaign to its recipients, using the code from that preview. | |
Count who would be added to a campaign, without adding anyone. Send4 gives the assistant a summary to show you and ask for your yes. | |
Add those people to the campaign, using the code from that preview. On a running campaign, they'll be messaged. | |
Change the pace, sending hours or goal of a campaign that's scheduled, running or paused. | |
Stop starting new people. Conversations already going carry on. | |
Start new people again. | |
Stop a campaign for good. A draft is deleted. | |
Add one lead. This sends nothing. | |
Add tags to leads or take them off. |
Tool | What it does |
Reply to a customer. Once sent, it can't be taken back, and the AI stops answering that conversation. | |
Check how a typed phone number reads and the exact text, without sending anything. Send4 gives the assistant a code for it. | |
Text someone first. A typed number needs the code from that preview; a lead doesn't. Once sent, it can't be taken back, and no flow answers until the AI is resumed. | |
Give a conversation to a team member, or to nobody. The AI keeps answering. | |
Pause the AI so a person answers. | |
Hand a paused conversation back to the AI. | |
Stop texting a number, for a customer who asked in words other than STOP. Only a person can opt it back in, on the lead's page. | |
Book or move a meeting. This doesn't tell the customer. | |
Cancel a meeting, or mark it completed or a no-show. A cancellation tells the customer only if the assistant is asked to. |
Tool | What it does |
See who would be invited, in which role, and the seats in use, without sending anything. Send4 gives the assistant a summary to show you and ask for your yes. | |
Invite someone as a manager or agent, using the code from that preview. Nobody can be made an admin this way. | |
Change someone's role between manager and agent, or deactivate or reactivate them. | |
Send a fresh link to someone whose invitation is still pending. |
Tool | What it does |
Whether this workspace can have an email address on Send4 and on which domains, whether it can connect its own mailbox, and the Send4 page that does it. | |
Create an email address on Send4. It sends nothing until a flow or a campaign uses it. |
Tool | What it does |
Draw one flow card by card, for the flow map view. |
docs/tools.md has the same list, with which roles can use each tool.
docs/permissions.md has the workspace switches and who can use what.
"Give me last week's report: conversations started, reply rate, meetings booked, how each running campaign did, and where people dropped off."
The assistant reads your performance, campaigns and drop-off, and writes the report. Nothing changes. Some assistants offer this as the ready-made weekly_report request.
"Which card in my quote flow loses the most people? Suggest clearer wording for it."
The assistant finds the card and leaves the new wording on it as a suggestion. You read it in the flow builder and accept it or not. Needs Build and change flows.
"Make the opening message of my booking flow friendlier."
A live flow is never edited in place. The assistant duplicates it, changes the copy, rehearses it as a customer and checks it. Switching the copy on and the original off each wait for your yes. Needs Build and change flows.
"Count the leads tagged spring, create a draft campaign for them with the reactivation flow, sending on weekdays 9:00–17:00, and check it before launch."
The assistant counts the audience and creates the draft. Before launch, Send4 runs every check and works out the cost, and the assistant shows you that summary. Nothing is sent until you say yes. Needs Create and launch campaigns.
"Which conversations are waiting for a person? Take over the one from this morning's form."
The assistant pauses the AI on that conversation so you can answer yourself. To hand it back, ask it to resume the AI. Needs Reply to customers and manage conversations.
You sign in with your Send4 account, through your browser. No API key or password goes into the assistant.
It acts as you. Every tool runs in your workspace, with your role. It can't do more than you can in Send4.
Your admin sets the limits, and you choose within them. The workspace switches decide what any assistant may do. When you connect, you tick what this one may do.
Contact details are masked. Read answers mask phone numbers and email addresses. Customer messages are shared only when the workspace allows conversation content and you tick Read conversation messages.
The big steps wait for your yes. These are launching a campaign, adding people to one, switching a flow on or a live flow off, inviting someone, and texting a number you typed. Before any of them, Send4 gives the assistant a summary to show you. After your yes, only what that summary described runs.
A live flow is never edited in place. The assistant changes a copy, and you switch it over.
No passwords in the chat. No tool takes a mailbox password. You connect your own mailbox yourself, in Send4.
Every change is recorded. Changes appear in your Audit log, marked as made through an AI assistant.
Requests are rate-limited per connection. A refused request says when to try again.
Where your data goes: what an assistant reads goes to the company behind it, under your own account with them. Check their terms before you allow conversation content.
Messages are data, not instructions: customers write the messages an assistant reads, and a message could try to give the assistant instructions. Don't let an assistant that reads conversations also manage your team.
In Settings → Integrations → AI assistants, under Workspace access:
Allow AI assistants lets people connect an assistant to their own account. On its own, an assistant can then read, and change nothing.
Allow conversation content lets connections read messages and the details flows collected.
Under What assistants may change, each kind of change has its own switch: Build and change flows, Reply to customers and manage conversations, Create and launch campaigns, Invite and manage team members and Create email addresses.
All of these are off to begin with. See docs/permissions.md.
Every change an assistant makes appears in Settings → Audit log, marked as made through an AI assistant, with the person who connected it.
One person, one assistant: they open Settings → Integrations → AI assistants and select Disconnect beside it. Its access ends immediately.
Everyone at once: a Client Admin turns off Allow AI assistants and selects Switch off. Every assistant in the workspace is disconnected, and nobody can connect one until an admin switches it on again.
You see | What to do |
"Connecting AI assistants needs a plan, or a trial with a card on file" | A Client Admin sets up a plan under Settings → Plan & billing. |
The assistant can't connect at all | A Client Admin turns on Allow AI assistants. |
A tool you expected is missing | The workspace switch is off, you didn't tick it, or your role can't use it. Ask "What can you do in Send4?". |
The sign-in page says you'll return to "an app on this computer" | Normal for Claude Code, VS Code, Cursor and terminal tools. Continue only if you started it from that app. |
More in docs/troubleshooting.md.
Please report a security problem privately, never in a public issue. Use Report a vulnerability on this repository's Security tab, or see SECURITY.md.
A setup step is wrong or something doesn't work: open an issue. Issues are public: never paste access tokens, passwords, or your customers' messages, names, numbers or addresses.
Something you'd like an assistant to do: open an issue with the Idea form.
Account, plan or workspace questions: support@send4.ai
Help centre: send4.ai/support/ai-assistant-tools
The guides and configuration in this repository are MIT licensed. Send4 itself is a commercial service, used under its terms.
This server cannot be deployed
Connect your AI assistant to Revensi OS agents, workflows, and business data.
Connect AI assistants to Preset to explore data, charts, and dashboards in authorized workspaces.
Connect AI assistants to Stellary projects, boards, documents, and governed agent workflows.
