WaveXisMCP

wavexis_screencast

Read-onlyIdempotent

Capture frame-by-frame screenshots over a set duration to record page animations or time-series UI changes.

Instructions

Capture a frame-by-frame screenshot sequence over a duration.

Use wavexis_screenshot for a single still image, or wavexis_screencast when animation or time-series capture is needed.

Side effects: launches/acquires a browser backend, navigates to url if provided, captures frames for duration; writes frame files to output_dir when given. Returns: JSON string with keys: 'status' ('ok'/'error'), 'frames' (list[str]) or 'dir' (str), 'count' (int).

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "input": "<input>"
    },
    "name": "wavexis_screencast"
  }
}

Input Schema

Name	Required	Description	Default
`input`	Yes

Output Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed13 schema fields changedv1.6.24Jul 29, 2026
- addedInput schema / $defs / ScreencastInput / properties / backend / description
```
Added value: +"Backend: 'cdp', 'bidi', or 'auto'"
```
- addedInput schema / $defs / ScreencastInput / properties / backend / enum
```
Added value: +[
+  "cdp",
+  "bidi",
+  "auto"
+]
```
- addedInput schema / $defs / ScreencastInput / properties / format / description
```
Added value: +"Image format: 'png' or 'jpeg'"
```
- addedInput schema / $defs / ScreencastInput / properties / format / enum
```
Added value: +[
+  "png",
+  "jpeg"
+]
```
- addedInput schema / $defs / ScreencastInput / properties / headless / description
```
Added value: +"Run browser in headless mode"
```
- addedInput schema / $defs / ScreencastInput / properties / max_height / description
```
Added value: +"Maximum screenshot height in pixels"
```
- addedInput schema / $defs / ScreencastInput / properties / max_width / description
```
Added value: +"Maximum screenshot width in pixels"
```
- addedInput schema / $defs / ScreencastInput / properties / quality / description
```
Added value: +"JPEG quality 1-100 (ignored for PNG)"
```
- addedInput schema / $defs / ScreencastInput / properties / session_id / description
```
Added value: +"Active session ID. If omitted, a stateless session is created for this call."
```
- addedInput schema / $defs / ScreencastInput / properties / url / description
```
Added value: +"URL to navigate to (required without session_id)"
```
- addedInput schema / $defs / ScreencastInput / properties / wait_timeout / description
```
Added value: +"Timeout in ms for wait conditions"
```
- addedInput schema / $defs / ScreencastInput / properties / wait_timeout / maximum
```
Added value: +300000
```
- addedInput schema / $defs / ScreencastInput / properties / wait_timeout / minimum
```
Added value: +1000
```
First observedv1.0.1Jul 7, 2026

TDQS

A3.8/5.0

Behavior1/5

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

The description lists side effects (launching browser backend, navigating to URL, writing frames) which contradict the readOnlyHint annotation (true). The annotation implies no side effects, but the description explicitly states them. This is an annotation contradiction, warranting a score of 1 per guidelines.

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 remarkably concise: one sentence for purpose, one for usage guidance, and one for side effects/return value. It is front-loaded and every sentence adds value.

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 the main action, side effects, and return format. With an output schema available, it does not need to detail the return structure beyond the key names. It is complete for a tool with many parameters and a nested input.

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 already contains detailed descriptions for each parameter, so schema coverage is effectively high. The description adds minimal extra meaning (e.g., that frames are written to output_dir when given), which is also in the schema. 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 defines the tool as capturing a frame-by-frame screenshot sequence over a duration. It uses a specific verb ('capture') and contrasts with the sibling tool wavexis_screenshot, leaving no ambiguity about its purpose.

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

Usage Guidelines5/5

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

The description explicitly advises when to use this tool versus wavexis_screenshot ('use wavexis_screenshot for a single still image, or wavexis_screencast when animation or time-series capture is needed'), providing clear alternative guidance.

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

Deploy Server