About Alphorn
Alphorn MCP Server connects AI agents to Alphorn, an open-source notification router. It is for workflows that need to report task completion, failure, or a request for input through configured channels, and works with hosted or self-hosted Alphorn.
Key features
- 01Send notices with send_notification
- 02Set titles, priorities, and tags
- 03Route notices using Alphorn filters
- 04Connect to hosted or self-hosted Alphorn
Use cases
- 01Notify when a coding task finishes
- 02Alert people when a task fails or is blocked
- 03Request a decision from a person
- 04Route alerts to channels by priority
MCP support
The MCP server exposes the send_notification tool, which sends messages to an Alphorn webhook. Alphorn can route them to configured channels such as Slack, Telegram, Discord, email, SMS, and push.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
npx -y @alphorn/mcpALPHORN_WEBHOOK_URLSecretWebhook Endpoint URL, e.g. https://app.alphorn.dev/n/V1StGXR8_Z5jdHi6B-myTALPHORN_API_KEYSecretWebhook API key (alp_...), if the webhook requires oneLocal servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.
Tools
1Saved tool list · updated 2w ago
| Parameter | Type | Required | Description |
|---|---|---|---|
| tags | array | No | Tags the user can filter and route on, e.g. ["ai-agent", "completed"]. |
| title | string | No | Short title. Start with the project name, e.g. "my-app - tests passing". |
| message | string | Yes | What happened and what you need from the user, in one or two sentences. |
| priority | integer | No | 1 (lowest) to 5 (urgent). Use 2 when finished, 3 when you need input, 4 when blocked or failed. |
Details
From the project READMEAlphorn MCP Server
MCP server for Alphorn, the open-source notification router. It gives AI agents (Claude Code, Claude Desktop, Cursor, Codex, and any other MCP client) a send_notification tool, so an agent can tell you when a task finishes, fails, or needs your decision, on whatever channel you configured in Alphorn: Slack, Telegram, Discord, email, SMS, push, and more.
Works with the hosted service at app.alphorn.dev and with self-hosted Alphorn.
Setup
- Create a webhook in Alphorn and copy its Endpoint URL, plus its API key if you switched on Require API key (docs).
- Add the server to your MCP client with two environment variables:
| Variable | Value |
|---|---|
ALPHORN_WEBHOOK_URL | Endpoint URL, e.g. https://app.alphorn.dev/n/V1StGXR8_Z5jdHi6B-myT |
ALPHORN_API_KEY | Webhook API key (alp_...). Leave unset if the webhook does not require one. |
Claude Code
claude mcp add alphorn -s user \
-e ALPHORN_WEBHOOK_URL=https://app.alphorn.dev/n/V1StGXR8_Z5jdHi6B-myT \
-e ALPHORN_API_KEY=alp_... \
-- npx -y @alphorn/mcp
Claude Desktop (one-click bundle)
Download alphorn.mcpb from the latest release and open it. Claude Desktop asks for the Endpoint URL and API key.
Claude Desktop, Cursor, and other JSON-configured clients
Add to claude_desktop_config.json, ~/.cursor/mcp.json, or your client's MCP config:
{
"mcpServers": {
"alphorn": {
"command": "npx",
"args": ["-y", "@alphorn/mcp"],
"env": {
"ALPHORN_WEBHOOK_URL": "https://app.alphorn.dev/n/V1StGXR8_Z5jdHi6B-myT",
"ALPHORN_API_KEY": "alp_..."
}
}
}
}
OpenAI Codex CLI
# ~/.codex/config.toml
[mcp_servers.alphorn]
command = "npx"
args = ["-y", "@alphorn/mcp"]
env = { ALPHORN_WEBHOOK_URL = "https://app.alphorn.dev/n/V1StGXR8_Z5jdHi6B-myT", ALPHORN_API_KEY = "alp_..." }
Tool
send_notification
| Argument | Type | Required | Description |
|---|---|---|---|
message | string | yes | What happened and what the agent needs from you (max 4,000 characters) |
title | string | no | Short title, e.g. my-app - tests passing (max 200 characters) |
priority | integer 1-5 | no | 2 = finished, 3 = needs input, 4 = blocked or failed, 5 = urgent |
tags | string[] | no | Tags to filter and route on in Alphorn, e.g. ["ai-agent", "completed"] |
The tool wraps Alphorn's send endpoint. For direct HTTP use, see the API reference and the OpenAPI 3.1 specification.
Use Alphorn's filters to decide where each notification goes, for example SMS only for priority 4 and above.
Development
pnpm install
pnpm test # builds, then runs the tests against a local fake endpoint
Releasing
- Bump
versioninpackage.json,server.json(both fields),manifest.json, andVERSIONinsrc/server.ts. npm publish --access public- Push a
v<version>tag (or run the Publish to MCP Registry workflow): it publishesserver.jsonto the MCP Registry via GitHub OIDC pnpm bundle, then attachalphorn.mcpbto a GitHub release
License
AGPL-3.0-or-later
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.