WebhookSAFE
mcp webhook
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
A powerful MCP server that enables webhook messaging capabilities for your AI agents
[](https://www.npmjs.com/package/@kevinwatt/mcp-webhook) [](https://smithery.ai/server/@kevinwatt/mcp-webhook) [](https://opensource.org/licenses/MIT) [](https://nodejs.org/) [](https://mseep.ai/app/kevinwatt-mcp-webhook)
Send messages to any webhook endpoint through Claude, Dive, and other MCP-compatible AI systems. Perfect for notifications, alerts, and automated messaging.
Features • Installation • Tools • Usage • Configuration
✨ Features
🌐 Generic Webhook Support
- Works with any webhook endpoint
- Compatible with Discord, Slack, Mattermost
- Custom HTTP POST requests
- JSON payload formatting
🎨 Customization
- Custom display name (username)
- Avatar URL support
- Flexible message content
- Easy integration with any platform
🔌 MCP Integration
- Works with Dive Desktop
- Claude Desktop compatible
- Cursor, VS Code support
- Any MCP-compatible LLM
🛡️ Simple & Secure
- Minimal configuration
- Environment variable support
- No tracking or analytics
- MIT licensed
🚀 Installation
Getting Started
Add the following config to your MCP client:
2a13b64baa9aOBSERVED · 2026-10-08Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control.
claude mcp add mcp-webhook -- npx -y @kevinwatt/[email protected]
{
"mcpServers": {
"mcp-webhook": {
"command": "npx",
"args": [
"-y",
"@kevinwatt/[email protected]"
]
}
}
}Exposed tools (2)
0 read · 2 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
send_json | write | Send arbitrary JSON object to webhook endpoint |
send_message | write | Send message to webhook endpoint |
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- declared (3 observation(s))
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (1)
@modelcontextprotocol/sdk, axios, @babel/preset-env, @babel/preset-typescript, @types/jest, @types/node, jest, ts-jest
Gates applied: no_behavioural_pass.
2a13b64baa9afull audit observations/trust-audit/mcp-server/kevinwatt__webhook.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-08 | 2a13b64baa9a | SAFE | B | 89 | first audit |
Questions
What is the Webhook MCP server?
mcp webhook
What tools does Webhook expose?
2 in total: 0 read-only, 2 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is Webhook safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.
What credentials does Webhook need?
No credential environment variables were found in its source, so it appears to need none.
How does Webhook run?
It speaks stdio, so it runs as a local process your client starts. It is published on npm as @kevinwatt/mcp-webhook at 0.2.3.
How current is this page?
The grade is for one exact copy of the source (2a13b64baa9a), read on 2026-10-08. The repository is watched and re-audited when it changes.