Skip to main content
Glama
beekamai
by beekamai

stream_start

Start a periodic screen capture session, saving frames to disk and returning a session ID to retrieve or stop the stream.

Instructions

Start a periodic capture session. Saves frames to disk every intervalSeconds for at most durationSeconds, keeping the last ringCapacity frames in memory. Returns a session id used by stream_status / stream_latest / stream_stop. Streams default to disk-only to keep LLM context lean - call stream_latest with includeBase64=true when you actually want to look at a frame.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
intervalSecondsYesSeconds between frames. Minimum 0.25.
durationSecondsYesTotal duration of the stream in seconds.
cursorRadiusNo
formatNojpeg
qualityNo
maxEdgeNoLongest edge in px. Default 1920 for full-screen frames; cursor crops keep native resolution unless overridden.
ringCapacityNoMaximum number of recent frames kept in memory. Older frames are evicted (still on disk).

Implementation Reference

  • Core handler function `startStream()` — creates a stream session, starts periodic capture on an interval, returns session id and expected frame count.
    export function startStream(args: StartStreamArgs): { id: string; expectedFrames: number } {
      const intervalMs = Math.max(250, Math.floor(args.intervalSeconds * 1000));
      const durationMs = Math.max(intervalMs, Math.floor(args.durationSeconds * 1000));
      const id = `s-${Date.now().toString(36)}-${Math.random().toString(36).slice(2, 6)}`;
      const sess: StreamSession = {
        id,
        startedAt: Date.now(),
        intervalMs,
        durationMs,
        frames: [],
        capacity: Math.max(1, args.ringCapacity ?? 60),
        options: {
          cursorRadius: args.cursorRadius,
          format: args.format,
          quality: args.quality,
          maxEdge: args.maxEdge,
          includeBase64: false /* streams default to disk-only; pull frames on demand */,
        },
        outDir: args.outDir,
        stopAt: Date.now() + durationMs,
        done: false,
      };
    
      const tick = async () => {
        if (sess.done) return;
        if (Date.now() >= sess.stopAt) {
          stopStream(id);
          return;
        }
        try {
          const frame = await capture({ ...sess.options, outDir: sess.outDir });
          sess.frames.push(frame);
          while (sess.frames.length > sess.capacity) sess.frames.shift();
        } catch (e) {
          sess.error = (e as Error).message;
        }
      };
    
      /* Fire one immediately so the first frame is available right away, then keep
       * ticking on interval. */
      void tick();
      sess.ticker = setInterval(tick, sess.intervalMs);
      sessions.set(id, sess);
    
      const expectedFrames = Math.max(1, Math.floor(durationMs / intervalMs));
      return { id, expectedFrames };
    }
  • Call handler dispatch for tool "stream_start" — extracts arguments from the request and delegates to `startStream()`.
    case "stream_start": {
      const cursorRadius = numArg(args, "cursorRadius", 0);
      const r = startStream({
        intervalSeconds: numArg(args, "intervalSeconds", 1),
        durationSeconds: numArg(args, "durationSeconds", 10),
        cursorRadius,
        format: strEnum(args, "format", ["png", "jpeg", "webp"] as const, "jpeg"),
        quality: numArg(args, "quality", 72),
        maxEdge: optionalNumArg(args, "maxEdge", cursorRadius > 0 ? 0 : 1920),
        ringCapacity: numArg(args, "ringCapacity", 60),
        outDir: DEFAULT_OUT_DIR,
      });
      return text(r);
    }
  • Tool registration including name, description, and inputSchema for stream_start (intervalSeconds, durationSeconds, cursorRadius, format, quality, maxEdge, ringCapacity).
      name: "stream_start",
      description:
        "Start a periodic capture session. Saves frames to disk every intervalSeconds " +
        "for at most durationSeconds, keeping the last ringCapacity frames in memory. " +
        "Returns a session id used by stream_status / stream_latest / stream_stop. " +
        "Streams default to disk-only to keep LLM context lean - call stream_latest " +
        "with includeBase64=true when you actually want to look at a frame.",
      inputSchema: {
        type: "object",
        required: ["intervalSeconds", "durationSeconds"],
        properties: {
          intervalSeconds: {
            type: "number",
            minimum: 0.25,
            description: "Seconds between frames. Minimum 0.25.",
          },
          durationSeconds: {
            type: "number",
            minimum: 0.25,
            description: "Total duration of the stream in seconds.",
          },
          cursorRadius: { type: "integer", default: 0 },
          format: { type: "string", enum: ["png", "jpeg", "webp"], default: "jpeg" },
          quality: { type: "integer", minimum: 1, maximum: 100, default: 72 },
          maxEdge: {
            type: "integer",
            description: "Longest edge in px. Default 1920 for full-screen frames; cursor crops keep native resolution unless overridden.",
          },
          ringCapacity: {
            type: "integer",
            description: "Maximum number of recent frames kept in memory. Older frames are evicted (still on disk).",
            default: 60,
          },
        },
      },
    },
  • src/index.ts:37-165 (registration)
    All tools are registered in a single ListToolsRequestSchema handler; stream_start is one of the tools listed at lines 80-116.
    server.setRequestHandler(ListToolsRequestSchema, async () => ({
      tools: [
        {
          name: "screenshot",
          description:
            "Capture a single screenshot of the desktop. Persists the file to disk and " +
            "optionally returns a base64 payload. Set cursorRadius>0 to crop a square " +
            "region around the mouse cursor instead of the full screen.",
          inputSchema: {
            type: "object",
            properties: {
              cursorRadius: {
                type: "integer",
                description: "If >0, crop a square of (2*radius)x(2*radius) px centered on the cursor. 0 = full screen.",
                default: 0,
              },
              format: { type: "string", enum: ["png", "jpeg", "webp"], default: "jpeg" },
              quality: { type: "integer", minimum: 1, maximum: 100, default: 82 },
              maxEdge: {
                type: "integer",
                description: "Resize the longest edge to this many pixels. 0 disables resizing. " +
                  "Default 2400 for full screen; with cursorRadius>0 the cursor crop is kept at native resolution unless overridden.",
              },
              display: {
                type: "integer",
                description: "Optional display index for multi-monitor setups (omit for primary).",
              },
              includeBase64: {
                type: "boolean",
                description: "If true, include the image bytes inline in the response. Default true.",
                default: true,
              },
            },
          },
        },
        {
          name: "cursor_info",
          description:
            "Return the current mouse cursor position, the foreground window title, and the " +
            "title of the window directly under the cursor (Windows only; other platforms " +
            "report position only when available).",
          inputSchema: { type: "object", properties: {} },
        },
        {
          name: "stream_start",
          description:
            "Start a periodic capture session. Saves frames to disk every intervalSeconds " +
            "for at most durationSeconds, keeping the last ringCapacity frames in memory. " +
            "Returns a session id used by stream_status / stream_latest / stream_stop. " +
            "Streams default to disk-only to keep LLM context lean - call stream_latest " +
            "with includeBase64=true when you actually want to look at a frame.",
          inputSchema: {
            type: "object",
            required: ["intervalSeconds", "durationSeconds"],
            properties: {
              intervalSeconds: {
                type: "number",
                minimum: 0.25,
                description: "Seconds between frames. Minimum 0.25.",
              },
              durationSeconds: {
                type: "number",
                minimum: 0.25,
                description: "Total duration of the stream in seconds.",
              },
              cursorRadius: { type: "integer", default: 0 },
              format: { type: "string", enum: ["png", "jpeg", "webp"], default: "jpeg" },
              quality: { type: "integer", minimum: 1, maximum: 100, default: 72 },
              maxEdge: {
                type: "integer",
                description: "Longest edge in px. Default 1920 for full-screen frames; cursor crops keep native resolution unless overridden.",
              },
              ringCapacity: {
                type: "integer",
                description: "Maximum number of recent frames kept in memory. Older frames are evicted (still on disk).",
                default: 60,
              },
            },
          },
        },
        {
          name: "stream_status",
          description: "Snapshot of a running or finished stream session - frame count, time remaining, last frames metadata.",
          inputSchema: {
            type: "object",
            required: ["id"],
            properties: {
              id: { type: "string" },
              lastN: { type: "integer", default: 8 },
            },
          },
        },
        {
          name: "stream_latest",
          description:
            "Read the most recent frame of a stream from disk and return it as base64. Use sparingly - this is the path that actually puts pixels into the LLM context.",
          inputSchema: {
            type: "object",
            required: ["id"],
            properties: {
              id: { type: "string" },
            },
          },
        },
        {
          name: "stream_stop",
          description: "Stop a running stream early. Frames already on disk remain.",
          inputSchema: {
            type: "object",
            required: ["id"],
            properties: { id: { type: "string" } },
          },
        },
        {
          name: "stream_list",
          description: "List active and completed stream sessions known to this process.",
          inputSchema: { type: "object", properties: {} },
        },
        {
          name: "stream_drop",
          description: "Forget a finished stream session (frees its in-memory ring; on-disk files are preserved).",
          inputSchema: {
            type: "object",
            required: ["id"],
            properties: { id: { type: "string" } },
          },
        },
      ],
    }));
  • Import of `capture` and `CaptureResult` (used by startStream) and TypeScript definitions for StreamSession and StartStreamArgs.
    import { capture, CaptureOptions, CaptureResult } from "./capture.js";
    
    interface StreamSession {
      id: string;
      startedAt: number;
      intervalMs: number;
      durationMs: number;
      /* Frames are kept in a bounded ring so a long stream doesn't bloat memory. */
      frames: CaptureResult[];
      capacity: number;
      options: Omit<CaptureOptions, "outDir">;
      outDir: string;
      ticker?: NodeJS.Timeout;
      stopAt: number;
      done: boolean;
      error?: string;
    }
    
    const sessions = new Map<string, StreamSession>();
    
    export interface StartStreamArgs {
      intervalSeconds: number;
      durationSeconds: number;
      cursorRadius?: number;
      format?: "png" | "jpeg" | "webp";
      quality?: number;
      maxEdge?: number;
      ringCapacity?: number;
      outDir: string;
    }
Behavior3/5

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

No annotations are provided, so the description bears full responsibility. It discloses that frames are saved to disk, memory retains only ringCapacity frames, and streams default to disk-only. This adds moderate behavioral context, but lacks details on disk usage, permission requirements, or automatic stop conditions.

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?

The description is three sentences long, each serving a distinct purpose: stating the main action, detailing memory/disk behavior, and providing usage guidance. No extraneous words or redundancy.

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?

Given the complexity of 7 parameters and no output schema, the description covers the core lifecycle, disk/memory behavior, and ties to sibling tools. It lacks explicit return value schema or error conditions, but is sufficiently complete for a start tool.

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?

With schema description coverage at 57%, the description adds some contextual meaning (e.g., explaining ringCapacity as memory retention) and clarifies the roles of intervalSeconds and durationSeconds. However, it does not elaborate on cursorRadius, format, quality, or maxEdge beyond what the schema already states. The baseline of 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 specifies a clear verb ('Start'), resource ('periodic capture session'), and critical details: saves frames to disk, keeps recent frames in memory, returns a session ID. It distinguishes from sibling tools by naming the related tools (stream_status, stream_latest, stream_stop) and how they interact.

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?

Provides clear context for use: stream_start initiates capture, and it mentions that stream_latest with includeBase64=true should be called when actually viewing a frame. This helps agents decide when to use stream_latest vs relying on disk-only behavior. However, it does not explicitly state when not to use stream_start or list alternatives.

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/beekamai/mcp-screenshot'

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