MCP Path
Screenshot Task-Isolation
Screenshot Task-Isolation is a public reference for visual evidence, screenshots, and reviewable differences. It names the signal, policy, or flow an agent should understand before choosing a concrete tool.
Reference page for a documented MCP capability path.
- Type
- MCP path
- Family
- Streaming & Screenshots (Advanced)
- Effect
- bounded run
- Status
- Reference
- Path
- 31.5
Purpose
What this entry explains
What it does
This reference explains Screenshot Task-Isolation for visual evidence, screenshots, and reviewable differences. It is kept as a named reference so agents can cite the flow without inventing a tool name.
Use when
- Use this entry when an agent needs to start or monitor the bounded flow "Screenshot Task-Isolation" for visual evidence, screenshots, and reviewable differences.
- Use it as a reference path when the catalog describes a capability but no single public tool name is explicit.
- Use it before chaining follow-up tools so the next step is based on current evidence.
Reference Use
How agents should cite and apply this area
Examples are maintained at family level and use only public tool names or reference paths already present in the catalog.
Screenshot Task-Isolation describes a behavior for visual evidence, screenshots, and reviewable differences. The path shows which signal, gate, behavior, or boundary must be checked before choosing a concrete tool.
An agent cites this path when it needs Screenshot Task-Isolation as context for a decision, block, target check, or follow-up tool choice.
The public source does not name one callable tool for this path. The documentation therefore keeps it as a reference path and does not invent a callable name.
Relevant response signals: screenshotFilePath, contextId, claimTaskId, mcpSessionId. Safety axes: Recording / media, Automation. The reference path alone is not permission to execute. Before acting, check current MCP discovery, visible target, scope, and the actual response.
Family example
A user needs visual or media evidence in visual evidence, screenshots, and reviewable differences without capturing private content unnecessarily.
The agent starts with nova.stream_url, reads the current response or reference, and only then chooses the concrete next tool.
Capture only needed evidence, keep recording state visible, and respect private content.Contract
Inputs and important response fields
This page is a public reference. Agents and integrators should still read current MCP tool discovery before execution, because schemas can be gated by settings or version.
Inputs
No stable public input field is derived from the catalog source for this path. Read current MCP discovery before execution.
| Response field | Explanation |
|---|---|
screenshotFilePath | Artifact or evidence reference. Do not publish local values; use it for lookup, lifetime, or review context. |
contextId | Identifier or reference value. Do not guess it from memory; read it from the current response. |
claimTaskId | Identifier or reference value. Do not guess it from memory; read it from the current response. |
mcpSessionId | Identifier or reference value. Do not guess it from memory; read it from the current response. |
Safety
Boundary before execution
Starts or observes a bounded run. Scope, limits, progress, and terminal status need to stay visible.
Set scope and limits before starting the run, poll explicit progress or status fields, and stop instead of assuming completion.
For humans, this entry shows which bounded flow in visual evidence, screenshots, and reviewable differences starts or continues, and where scope, progress, and stopping conditions belong.
High-Impact Review
Execution boundary and recheck hints
Review category: Recording/screenshots/media
Capture only the needed visual or media evidence and respect private content, recording state, and export boundary.
False assumption: screenshots or recordings contain only technical evidence.
Recording, screenshot, media access, or export must be visible to the user and purpose-bound.
Before capture, check target, scope, and privacy; use artifacts as evidence only and do not forward them unrequested.
Abort if private content is visible, media permission is unclear, or the export contains more than needed.
Safety Axes
How this path can affect work
Axes are stable catalog signals for humans, agents, and LLM discovery. One path can carry several axes.
recording_or_media
Creates or reads screenshots, recordings, media, visual evidence, or audio/video signals.
Capture only needed evidence, respect private content, and keep media or recording state visible.automation_run
Starts or monitors crawls, sequences, schedulers, tasks, batches, or longer runs.
Keep scope, budget, progress, stop condition, and terminal status visible before and during the run.