@trigv/mcp
Enables AI clients in Cursor, Claude Code, and VS Code to send notification events to your Trigv workspace.
README
@trigv/mcp
MCP (Model Context Protocol) server for Trigv. Lets AI clients in Cursor, Claude Code, and VS Code send notification events to your Trigv workspace.
What Trigv is
Trigv delivers developer notifications to your team's devices. Your backend (or AI agent) sends lightweight JSON events; Trigv queues push delivery. Notification title and body are not stored on Trigv servers — metadata only.
Installation
npm install @trigv/mcp
Or run directly with npx:
npx @trigv/mcp
Quick start
- Create a workspace API key at app.trigv.com.
- Set
TRIGV_API_KEYin your MCP client config (see below). - Ask your AI assistant to send an event using the
send_eventtool.
Example tool call:
{
"channel": "deploys",
"title": "Production deploy complete",
"description": "Build #42 succeeded in 38s (commit abc1234)",
"level": "success",
"event_type": "deploy.completed",
"idempotency_key": "deploy-prod-42"
}
Authentication
| Variable | Required | Default | Description |
|---|---|---|---|
TRIGV_API_KEY |
Yes | — | Workspace ingest API key (trgv_…) |
TRIGV_BASE_URL |
No | https://api.trigv.com/api |
Override for local dev (http://trigv-platform.test/api) |
The API key is sent as Authorization: Bearer and is never included in tool responses or error messages.
Tool: send_event
Sends a notification event via POST /v1/events.
| Field | Required | Description |
|---|---|---|
channel |
Yes | Channel slug (e.g. general, deploys) |
title |
Yes | Notification title |
description |
No | Body text |
image_url |
No | HTTPS image URL (not stored server-side) |
url |
No | Destination URL for the notification (max 2048 characters; not stored server-side) |
level |
No | info, success, warning, error (default: info) |
delivery_urgency |
No | standard or time_sensitive (default: standard) |
event_type |
No | Free-form label (e.g. deploy.completed) |
idempotency_key |
No | Dedup key per workspace |
Success response includes event.public_id, duplicate (true when HTTP 200), and other event metadata.
Error response includes error.type, error.message, and optional error.errors for validation failures.
Levels
info— general information (default)success— completed successfullywarning— attention needederror— failure or alert
Delivery urgency
standard— normal notifications (default)time_sensitive— iOS Time Sensitive delivery
Idempotency
When you set idempotency_key, retries with the same key return the existing event (duplicate: true) without billing again.
Error handling
| Error type | When |
|---|---|
ConfigurationError |
Missing TRIGV_API_KEY |
ValidationError |
Invalid input (client or server 422) |
AuthenticationError |
HTTP 401 |
AuthorizationError |
HTTP 403 |
NotFoundError |
Channel not found (HTTP 404) |
RateLimitError |
HTTP 429 |
NetworkError / TimeoutError |
Connection issues |
MCP client configuration
Cursor
Add to .cursor/mcp.json in your project (or global Cursor MCP settings):
{
"mcpServers": {
"trigv": {
"command": "npx",
"args": ["-y", "@trigv/mcp"],
"env": {
"TRIGV_API_KEY": "trgv_your_api_key_here"
}
}
}
}
For a local checkout during development:
{
"mcpServers": {
"trigv": {
"command": "node",
"args": ["/path/to/trigv-mcp/dist/index.js"],
"env": {
"TRIGV_API_KEY": "trgv_your_api_key_here",
"TRIGV_BASE_URL": "http://trigv-platform.test/api"
}
}
}
}
Claude Code
Add to ~/.claude/settings.json or project .claude/settings.json:
{
"mcpServers": {
"trigv": {
"command": "npx",
"args": ["-y", "@trigv/mcp"],
"env": {
"TRIGV_API_KEY": "trgv_your_api_key_here"
}
}
}
}
VS Code
Add to .vscode/mcp.json in your workspace:
{
"servers": {
"trigv": {
"type": "stdio",
"command": "npx",
"args": ["-y", "@trigv/mcp"],
"env": {
"TRIGV_API_KEY": "trgv_your_api_key_here"
}
}
}
}
Examples
Basic event
{ "channel": "general", "title": "Hello from MCP" }
Deploy completed (canonical)
{
"channel": "deploys",
"title": "Production deploy complete",
"description": "Build #42 succeeded in 38s (commit abc1234)",
"level": "success",
"delivery_urgency": "standard",
"event_type": "deploy.completed",
"idempotency_key": "deploy-prod-42"
}
Cron job failed
{
"channel": "alerts",
"title": "Nightly backup failed",
"description": "Exit code 1 after 12 minutes",
"level": "error",
"event_type": "cron.failed"
}
Development
git clone https://github.com/Trigv/trigv-mcp.git
cd trigv-mcp
npm install
npm run build
npm test
Run locally:
TRIGV_API_KEY=trgv_… npm run dev
Testing
npm test
Tests use mocked HTTP — no live API key required in CI.
Contributing
See the Trigv SDK programme for API contract and conformance requirements.
Licence
MIT — see LICENSE.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.