veyra-webhooks

A webhook relay MCP tool for AI agents. Register target URLs, send payloads via HTTP, and browse send history. Reads are always free. Write operations require Veyra commit mode authorization.

Overview

veyra-webhooks lets AI agents interact with external services through registered webhook endpoints. History is persisted in SQLite for auditing. Sending payloads and managing registrations require Veyra commit mode.

Installation

npm install
npm run build

Data is stored at ~/.veyra-webhooks/data.db, created automatically on first run.

MCP Configuration (Claude Desktop)

{
  "mcpServers": {
    "veyra-webhooks": {
      "command": "node",
      "args": ["/absolute/path/to/veyra-webhooks/dist/index.js"]
    }
  }
}

Tools

Examples

Read (no token needed)

// List all registered webhooks
{ "tool": "list_webhooks", "arguments": {} }

// View send history
{ "tool": "get_history", "arguments": { "webhook_id": "1712345678-abc1234", "limit": 20 } }

Write (Veyra token required)

// Register a webhook
{
  "tool": "register_webhook",
  "arguments": {
    "name": "Slack Notifications",
    "url": "https://hooks.slack.com/services/...",
    "headers": "{\"Authorization\": \"Bearer token123\"}",
    "veyra_token": "vt_..."
  }
}

// Send a payload (actually fires an HTTP request)
{
  "tool": "send_webhook",
  "arguments": {
    "webhook_id": "1712345678-abc1234",
    "payload": "{\"text\": \"Deployment complete\"}",
    "method": "POST",
    "veyra_token": "vt_..."
  }
}

// Delete a webhook (also clears its history)
{
  "tool": "delete_webhook",
  "arguments": {
    "webhook_id": "1712345678-abc1234",
    "veyra_token": "vt_..."
  }
}

Error response when token is missing

{
  "error": "VeyraCommitRequired",
  "message": "Write operations require Veyra commit mode.",
  "currentMode": "open",
  "requiredMode": "commit",
  "authorize_endpoint": "https://api.veyra.to/v1/authorize-action",
  "docs_url": "https://veyra.to"
}

How Veyra Works

Veyra is a commit-mode authorization layer for AI agents. When an agent attempts a write:

1. The agent calls the tool without veyra_token → receives VeyraCommitRequired with authorize_endpoint.
2. The agent/user calls the authorize endpoint to obtain a token.
3. The agent retries with veyra_token set.
4. veyra-webhooks verifies the token via @veyrahq/sdk-node before executing the action.

See veyra.to for full documentation.

License

MIT

Hosted Pack (recommended)

Prefer the hosted pack for one-URL integration:

{
  "mcpServers": {
    "veyra": {
      "url": "https://mcp.veyra.to/sse"
    }
  }
}

One URL. 48 tools. 24 free reads. 24 protected writes.

Hosted pack: https://mcp.veyra.to/sse

Pack manifest: https://mcp.veyra.to/.well-known/veyra-pack.json

Use the hosted pack when you want the fastest MCP integration path across all Veyra tool families. Use this standalone package when you specifically want this tool on its own.

Part of the Veyra Ecosystem

Veyra is commit mode for production AI agent actions. All tools: reads free, writes require Veyra commit mode.

SDK: npm install @veyrahq/sdk-node Website: veyra.to