Skip to main content
Glama
wave-av

WAVE MCP Server

Official
by wave-av

wave_start_stream

Activate a live stream by its UUID, transitioning it to the active state.

Instructions

Start a stream by its ID, transitioning it to the active state

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
stream_idYesThe UUID of the stream to start

Implementation Reference

  • The handler function for 'wave_start_stream' tool. Starts a stream by its ID by POSTing to /api/v1/streams/{stream_id}/start.
    server.tool(
      "wave_start_stream",
      "Start a stream by its ID, transitioning it to the active state",
      {
        stream_id: z.string().uuid().describe("The UUID of the stream to start"),
      },
      async ({ stream_id }) => {
        const res = await waveFetch(`/api/v1/streams/${stream_id}/start`, {
          method: "POST",
        });
        if (!res.ok) return errorContent(res.status, res.body);
    
        return textContent(res.body);
      },
    );
  • Input schema for 'wave_start_stream' - requires a single 'stream_id' parameter which is a UUID string.
    {
      stream_id: z.string().uuid().describe("The UUID of the stream to start"),
    },
  • The registerStreamTools function that registers all stream tools including 'wave_start_stream' on the MCP server.
    export function registerStreamTools(server: McpServer): void {
      server.tool(
        "wave_list_streams",
        "List all streams in your WAVE account with pagination support",
        {
          limit: z
            .number()
            .int()
            .min(1)
            .max(100)
            .optional()
            .describe("Maximum number of streams to return (1-100, default 25)"),
          offset: z
            .number()
            .int()
            .min(0)
            .optional()
            .describe("Number of streams to skip for pagination (default 0)"),
          status: z
            .enum(["active", "idle", "error", "all"])
            .optional()
            .describe("Filter by stream status"),
        },
        async ({ limit, offset, status }) => {
          const params = new URLSearchParams();
          params.set("limit", String(limit ?? 25));
          params.set("offset", String(offset ?? 0));
          if (status && status !== "all") {
            params.set("status", status);
          }
    
          const res = await waveFetch(`/api/v1/streams?${params.toString()}`);
          if (!res.ok) return errorContent(res.status, res.body);
    
          return textContent(res.body);
        },
      );
    
      server.tool(
        "wave_create_stream",
        "Create a new stream in your WAVE account",
        {
          title: z.string().min(1).max(255).describe("Stream title"),
          description: z.string().max(2000).optional().describe("Stream description"),
          protocol: z
            .enum(["webrtc", "srt", "rtmp", "hls"])
            .optional()
            .describe("Streaming protocol (default: webrtc)"),
          record: z.boolean().optional().describe("Enable recording for this stream (default: false)"),
          region: z
            .string()
            .optional()
            .describe("Preferred ingest region (e.g., us-east-1, eu-west-1)"),
        },
        async ({ title, description, protocol, record, region }) => {
          const payload: Record<string, unknown> = { title };
          if (description !== undefined) payload["description"] = description;
          if (protocol !== undefined) payload["protocol"] = protocol;
          if (record !== undefined) payload["record"] = record;
          if (region !== undefined) payload["region"] = region;
    
          const res = await waveFetch("/api/v1/streams", {
            method: "POST",
            body: JSON.stringify(payload),
          });
          if (!res.ok) return errorContent(res.status, res.body);
    
          return textContent(res.body);
        },
      );
    
      server.tool(
        "wave_start_stream",
        "Start a stream by its ID, transitioning it to the active state",
        {
          stream_id: z.string().uuid().describe("The UUID of the stream to start"),
        },
        async ({ stream_id }) => {
          const res = await waveFetch(`/api/v1/streams/${stream_id}/start`, {
            method: "POST",
          });
          if (!res.ok) return errorContent(res.status, res.body);
    
          return textContent(res.body);
        },
      );
    
      server.tool(
        "wave_stop_stream",
        "Stop an active stream by its ID",
        {
          stream_id: z.string().uuid().describe("The UUID of the stream to stop"),
        },
        async ({ stream_id }) => {
          const res = await waveFetch(`/api/v1/streams/${stream_id}/stop`, {
            method: "POST",
          });
          if (!res.ok) return errorContent(res.status, res.body);
    
          return textContent(res.body);
        },
      );
    
      server.tool(
        "wave_get_stream_health",
        "Get real-time health metrics for a stream including bitrate, frame rate, and latency",
        {
          stream_id: z.string().uuid().describe("The UUID of the stream to check"),
        },
        async ({ stream_id }) => {
          const res = await waveFetch(`/api/v1/streams/${stream_id}/health`);
          if (!res.ok) return errorContent(res.status, res.body);
    
          return textContent(res.body);
        },
      );
    }
  • The waveFetch helper used by the handler to make authenticated API calls.
    async function waveFetch(
      path: string,
      init?: RequestInit,
    ): Promise<{ ok: boolean; status: number; body: string }> {
      const url = `${getBaseUrl()}${path}`;
      const res = await fetch(url, {
        ...init,
        headers: {
          ...getAuthHeaders(),
          ...init?.headers,
        },
      });
      const body = await res.text();
      return { ok: res.ok, status: res.status, body };
    }
  • Helper functions textContent and errorContent used to format responses.
    function textContent(text: string): { content: Array<{ type: "text"; text: string }> } {
      return { content: [{ type: "text" as const, text }] };
    }
    
    function errorContent(
      status: number,
      body: string,
    ): { content: Array<{ type: "text"; text: string }> } {
      return textContent(`Error ${status}: ${body}`);
    }
Behavior2/5

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

With no annotations, the description carries the full burden. It only discloses the transition to active state but omits side effects, error conditions, or required permissions.

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?

A single 12-word sentence with no redundancy, efficiently conveying the core action.

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

Completeness3/5

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

For a simple one-parameter tool, the description is adequate but could benefit from notes on success/error outcomes, especially since no output schema is present.

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 has 100% coverage for the single parameter, providing a clear description. The tool description adds no extra meaning beyond what the schema already provides.

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 tool starts a stream by its ID and transitions it to active state. It distinguishes from siblings like wave_stop_stream (stop) and wave_create_stream (create).

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

Usage Guidelines3/5

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

The description implies the tool is used after stream creation but does not provide explicit when-to-use, prerequisites like stream existence or state, nor when to avoid using it.

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/wave-av/mcp-server'

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