About mcp-zenvia
mcp-zenvia is an MCP server for Zenvia's multichannel messaging platform. It lets MCP clients send SMS, WhatsApp, RCS, email, voice and Facebook Messenger messages. It also covers templates, reports, webhook subscriptions and contacts.
Key features
- 01Covers SMS, WhatsApp, RCS, email and voice channels
- 02Sends pre-approved WhatsApp template messages
- 03Checks message delivery status by ID
- 04Creates and manages webhook subscriptions
- 05Manages contacts and the opt-out list
Use cases
- 01Sending WhatsApp or SMS notifications through an AI assistant
- 02Checking delivery status and reviewing report entries
- 03Managing contacts and recording opt-out requests
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
npx -y @codespar/mcp-zenviaZENVIA_API_TOKENSecretAPI key for zenviaLocal servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.
Tools
18Saved tool list · updated 2w ago
| Parameter | Type | Required | Description |
|---|---|---|---|
| to | string | Yes | Recipient phone number with country code (e.g. 5511999999999) |
| from | string | Yes | Sender ID |
| text | string | Yes | Message text |
Details
From the project README@codespar/mcp-zenvia
MCP server for Zenvia — multichannel messaging (SMS, WhatsApp, RCS)
Quick Start
Claude Desktop
Add to ~/.config/claude/claude_desktop_config.json:
{
"mcpServers": {
"zenvia": {
"command": "npx",
"args": ["-y", "@codespar/mcp-zenvia"],
"env": {
"ZENVIA_API_TOKEN": "your-token"
}
}
}
}
Claude Code
claude mcp add zenvia -- npx @codespar/mcp-zenvia
Cursor / VS Code
Add to .cursor/mcp.json or .vscode/mcp.json:
{
"servers": {
"zenvia": {
"command": "npx",
"args": ["-y", "@codespar/mcp-zenvia"],
"env": {
"ZENVIA_API_TOKEN": "your-token"
}
}
}
}
Tools (18)
| Tool | Purpose |
|---|---|
send_sms | Send an SMS message |
send_whatsapp | Send a WhatsApp message |
send_rcs | Send an RCS (Rich Communication Services) message |
send_email | Send a transactional email |
send_voice | Send a voice message via TTS or pre-recorded audio URL |
send_facebook_message | Send a Facebook Messenger message |
get_message_status | Get message delivery status by ID |
list_channels | List available messaging channels |
create_subscription | Create a webhook subscription for message events |
list_subscriptions | List all webhook subscriptions |
delete_subscription | Delete a webhook subscription by ID |
list_contacts | List contacts from the contact base |
create_contact | Create a contact in the contact base |
delete_contact | Delete a contact by ID |
send_template | Send a WhatsApp template message (pre-approved) |
list_templates | List approved message templates (WhatsApp/SMS/RCS) |
get_report_entries | Get message report entries within a date range |
add_opt_out | Add a phone number to the opt-out list (suppresses future messages) |
Authentication
Zenvia uses an API token passed via the X-API-TOKEN header.
Sandbox / Testing
Zenvia provides a sandbox via the dashboard for testing messages.
Get your credentials
- Go to Zenvia
- Create an account
- Get your API token from the dashboard
- Set the
ZENVIA_API_TOKENenvironment variable
Environment Variables
| Variable | Required | Description |
|---|---|---|
ZENVIA_API_TOKEN | Yes | API token from Zenvia dashboard |
Roadmap
v0.2 (planned)
create_contact_list— Create a contact list for campaignssend_batch— Send batch messages to a contact listget_report— Get message delivery reportscreate_flow— Create a conversational flowlist_templates— List approved message templates
v0.3 (planned)
chatbot_integration— Integrate with Zenvia chatbot builderanalytics_dashboard— Get channel analytics and metrics
Want to contribute? Open a PR or request a tool.
Links
Enterprise
Need governance, budget limits, and audit trails for agent payments? CodeSpar Enterprise adds policy engine, payment routing, and compliance templates on top of these MCP servers.
License
MIT
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.