vibe_preview_snapshot
Force one capture against an active session. Returns the new frame's seq + content hash. Pair with vibe_preview_summarize to ask Claude what changed.
This record as markdown: /tools/io-github-kivanccakmak-yaver/vibe-preview-snapshot.md
What vibe_preview_snapshot does on Yaver
AI agents call vibe_preview_snapshot to retrieve information from Yaver without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
project | string | Yes | Project name |
Parameters from the server's own tool schema.
Why vibe_preview_snapshot is rated Low
The tool captures a snapshot of an active session state and returns metadata (sequence number and content hash). While 'force' might suggest some control, the operation is read-only—it retrieves frame data without side effects. No data is modified, deleted, or executed. The low severity reflects minimal blast radius if misused; an AI agent misusing this would merely retrieve redundant session frames.
From the tool's definition Tool description states it 'Force one capture against an active session. Returns the new frame's seq + content hash.' This retrieves and returns frame data without modifying, deleting, or executing operations.
Attacks that exploit this kind of access
The rule that runs vibe_preview_snapshot safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Yaver, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For vibe_preview_snapshot, this is the rule to start with:
vibe_preview_snapshot is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Yaver, apply this rule, and every vibe_preview_snapshot call is checked against it from then on.
Questions about vibe_preview_snapshot
Force one capture against an active session. Returns the new frame's seq + content hash. Pair with vibe_preview_summarize to ask Claude what changed. It is categorised as a Read tool in the Yaver MCP Server, which means it retrieves data without modifying state.
vibe_preview_snapshot accepts 1 parameter: project. Required: project. The full parameter table on this page comes from the server's own tool schema.
Register the Yaver MCP server in PolicyLayer and add a rule for vibe_preview_snapshot: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Yaver. Nothing to install.
vibe_preview_snapshot is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the vibe_preview_snapshot rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for vibe_preview_snapshot. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
vibe_preview_snapshot is provided by the Yaver MCP server (yaver-cli). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Yaver, and thousands of servers like it.
This server
Across the catalogue