mcpField
S
Suprsend Mcp Server

Suprsend Mcp Server

Local
suprsend.comDeveloper Tools12Updated 5d ago

About Suprsend Mcp Server

Suprsend CLI is a command-line tool for working with the SuprSend API, aimed at managing notification workspace assets and environment profiles. Its README recommends the hosted MCP server, rather than the deprecated built-in server, for connecting AI tools.

Key features

  1. 01Manage templates, workflows, and events
  2. 02Sync assets between workspaces
  3. 03Generate typed code in several languages
  4. 04Configure multiple accounts and environments

Use cases

  1. 01Review or push notification workspace assets
  2. 02Move assets between workspaces
  3. 03Generate typed code from schemas

MCP support

The README marks the CLI's MCP server as deprecated and recommends that AI clients connect to the hosted service at https://mcp.suprsend.com/mcp. The old server remains available for service-token authentication or self-hosted BYOC instances.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
"mcpServers": {
"cli-suprsend": {
"command": "npx",
"args": [
"-y",
"suprsend"
],
"env": {
"SUPRSEND_SERVICE_TOKEN": "<SUPRSEND_SERVICE_TOKEN>",
"SUPRSEND_BASE_URL": "<SUPRSEND_BASE_URL>",
"SUPRSEND_MGMNT_URL": "<SUPRSEND_MGMNT_URL>"
}
}
}
}
Run commandnpx -y suprsend
Environment variables to set
SUPRSEND_SERVICE_TOKENSecretSuprSend service token. Create one in the SuprSend dashboard under Developers → API Keys.
SUPRSEND_BASE_URLBase API URL. Only set for BYOC / self-hosted SuprSend instances.
SUPRSEND_MGMNT_URLManagement API URL. Only set for BYOC / self-hosted SuprSend instances.

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npmsuprsend1.0.1

Tools

22

Saved tool list · updated 2w ago

ParameterTypeRequiredDescription
object_idstringYesThe object_id of the object's subscriptions to get.
workspacestringNoSuprsend workspace to get the object from.
propertiesobjectNoProperties of an user/object
recipientsarrayYesUsers & Objects who are subscribing to an object
object_typestringYesThe type of object you want to get.

Details

From the project README

SuprSend CLI

SuprSend CLI is a command-line interface tool for interacting with the SuprSend API, written in Go. To connect AI agents (Claude, Cursor, VS Code, Gemini, etc.) to SuprSend, use the hosted SuprSend MCP server instead of the CLI.

What you can do with it

  • Manage workspace resources — template, workflow, schema, event, category, translation, workspace. Most support list, get, pull, push and commit against your local working directory (event has no commit, category has no get, and workspace only has list).
  • Sync between workspaces — suprsend sync pulls assets from one workspace and pushes and commits them in another (changes go live in the destination), using a local directory (default ./suprsend) as intermediate storage.
  • Generate typed payload code — suprsend generate-types emits typed code in Go, TypeScript, Python, Java, Kotlin, Swift, or Dart from your event / workflow JSON Schemas.
  • MCP server (deprecated) — suprsend start-mcp-server still works but is deprecated. Use the hosted MCP server at https://mcp.suprsend.com/mcp (for Claude Code: claude mcp add --transport http suprsend https://mcp.suprsend.com/mcp), or the suprsend/claude-plugin and suprsend/agent-plugin plugins. Gemini CLI: add "suprsend": {"httpUrl": "https://mcp.suprsend.com/mcp"} under mcpServers in ~/.gemini/settings.json, then run /mcp auth suprsend (the Gemini CLI extension is retired). Keep using start-mcp-server only if you need service-token auth or a self-hosted (BYOC) instance.
  • Multi-account / multi-environment profiles — suprsend profile add|modify|list|use|remove stores per-account credentials and base URLs, so the same CLI works against public cloud, BYOC, staging, pre-prod, etc.

Full command reference: docs.suprsend.com/reference/cli-intro. Or run suprsend --help for the command tree.

Installation

npm / npx

Run without installing:

npx suprsend --help

Or install globally:

npm i -g suprsend
suprsend --help

Works on macOS, Linux, and Windows (x64 and arm64). Requires Node.js ≥ 18 (for npx).

Homebrew

You can install SuprSend CLI using Homebrew:

brew tap suprsend/tap
brew install --cask suprsend
Binary Releases

Pre-compiled binaries for various platforms are available on the Releases page.

Building from Source

To build SuprSend CLI from source, follow these steps:

  1. Ensure you have Go installed on your system (version 1.27.3 or later — see go.mod).

  2. Clone the repository:

    git clone https://github.com/suprsend/cli.git
    cd cli/cmd/suprsend
    
  3. Build the binary:

    go build -o suprsend
    
  4. The binary will be created in the current directory. You can move it to a location in your PATH for easy access:

    sudo mv suprsend /usr/local/bin/
    

Now you can use the suprsend command from anywhere in your terminal.

Usage

After installation, you can use the CLI by running the suprsend command. For example:

suprsend --help

Documentation

Please refer to documentation here OR if you want to access the cobra generated docs those are here

Contributing

Contributions are welcome! Please feel free to submit a Pull Request.

Generating build artifacts locally

make build compiles the embedded type-morph Deno binary (requires Deno), then generates CLI documentation in docs/ and AI skills in skills/.

make build

A CI check on PRs to main verifies that docs/ and skills/ are up to date. Run make build and commit the output before opening a PR. Both are generated from the command definitions, so edit the command help text rather than the generated files.

Run the unit tests (after make build, which creates the embedded binary the packages compile against) with:

go test ./...
Removing local build artifacts
make clean

License

This project is licensed under the MIT License - see the LICENSE file for details.

Comments

Markdown supported

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.