Skip to main content
Glama
zeph-to

@zeph-to/mcp-server

by zeph-to

zeph_broadcast

Send a push notification to all subscribers of a channel. Provide channel ID and title, with optional body, URL, and priority.

Instructions

Send a push notification to all subscribers of a channel. Use zeph://channels resource to find available channels.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
channelIdYesChannel ID to broadcast to (e.g., "ch_...")
titleYesNotification title
bodyNoNotification body text
urlNoOptional URL to open on the device.
priorityNoNotification prioritynormal

Implementation Reference

  • The main handler function 'registerBroadcastTool' that registers the 'zeph_broadcast' tool on the MCP server. The handler calls client.sendPush with channelId, title, body, url, and priority parameters, returning the pushId and channelId on success.
    export const registerBroadcastTool = (server: McpServer, client: ZephApiClient) => {
      server.registerTool(
        'zeph_broadcast',
        {
          description:
            'Send a push notification to all subscribers of a channel. Use zeph://channels resource to find available channels.',
          annotations: {
            readOnlyHint: false,
            destructiveHint: false,
            openWorldHint: true,
          },
          inputSchema: {
            channelId: z.string().describe('Channel ID to broadcast to (e.g., "ch_...")'),
            title: z.string().describe('Notification title'),
            body: z.string().optional().describe('Notification body text'),
            url: z.string().url().optional().describe('Optional URL to open on the device.'),
            priority: z
              .enum(['low', 'normal', 'high', 'urgent'])
              .default('normal')
              .describe('Notification priority'),
          },
        },
        async ({ channelId, title, body, url, priority }) => {
          try {
            const result = await client.sendPush({
              title,
              body,
              url,
              type: 'hook',
              priority,
              channelId,
            });
            return textResult({ pushId: result.data.pushId, channelId });
          } catch (err) {
            return formatToolError(err);
          }
        },
      );
    };
  • Input schema for zeph_broadcast: channelId (string), title (string), body (optional string), url (optional URL string), priority (enum low/normal/high/urgent, default 'normal').
    inputSchema: {
      channelId: z.string().describe('Channel ID to broadcast to (e.g., "ch_...")'),
      title: z.string().describe('Notification title'),
      body: z.string().optional().describe('Notification body text'),
      url: z.string().url().optional().describe('Optional URL to open on the device.'),
      priority: z
        .enum(['low', 'normal', 'high', 'urgent'])
        .default('normal')
        .describe('Notification priority'),
    },
  • src/index.ts:15-15 (registration)
    Import of registerBroadcastTool from './tools/broadcast.js'.
    import { registerBroadcastTool } from './tools/broadcast.js';
  • src/index.ts:65-65 (registration)
    Registration call: registerBroadcastTool(server, client) invoked in the server setup.
    registerBroadcastTool(server, client);
  • The sendPush method on ZephApiClient that makes the actual POST /pushes/send API request, used by the broadcast handler.
    async sendPush(params: {
      title: string;
      body?: string;
      url?: string;
      type?: string;
      priority?: string;
      targetDeviceId?: string;
      channelId?: string;
      files?: { fileKey: string; fileName: string; fileSize: number; fileType: string }[];
    }): Promise<PushResponse> {
      return this.request<PushResponse>('POST', '/pushes/send', params);
    }
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already indicate readOnlyHint=false and destructiveHint=false, and the description confirms it's a write (send notification). However, it doesn't add additional context like rate limits or whether the operation returns a response, which would increase transparency beyond annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, each valuable: first states purpose, second provides prerequisite resource. No wasted words, appropriately front-loaded.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description covers purpose and prerequisite but omits return value expectations (no output schema). Given the tool's complexity (5 params, no output schema), a brief mention of outcome would improve completeness.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema provides full descriptions for all 5 parameters (100% coverage), so the description adds no additional parameter-specific meaning. Baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action ('send a push notification') and the resource ('all subscribers of a channel'), and distinguishes it from siblings like zeph_notify by specifying broadcast to all subscribers. The mention of using zeph://channels resource adds specificity.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies a prerequisite (find channels via zeph://channels) and that it's for broadcasting to all subscribers, but does not explicitly state when to avoid using it or contrast with alternatives like zeph_notify.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/zeph-to/mcp-server'

If you have feedback or need assistance with the MCP directory API, please join our Discord server