vibe_preview_summaries
Read recent text summaries for a project (Phase 4). Each entry is a one-sentence description of what visibly changed between two frames, with before/after hashes. Default returns last 50; use limit to widen.
This record as markdown: /tools/io-github-kivanccakmak-yaver/vibe-preview-summaries.md
What vibe_preview_summaries does on Yaver
AI agents call vibe_preview_summaries 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 |
|---|---|---|---|
limit | integer | — | Max entries (default 50, cap 500) |
project | string | Yes | Project name |
Parameters from the server's own tool schema.
Why vibe_preview_summaries is rated Low
This tool retrieves and lists previously generated summaries of visual changes in a project. It is purely informational—fetching data about frame diffs with hashes. No data is created, modified, deleted, or executed. The blast radius of misuse is minimal: an agent could only read summaries it has access to, not alter them or trigger external operations.
From the tool's definition "Read recent text summaries" and "returns last 50" indicate retrieval of pre-computed summary data with no mutation or execution. The tool queries stored project history without side effects.
Attacks that exploit this kind of access
The rule that runs vibe_preview_summaries 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_summaries, this is the rule to start with:
vibe_preview_summaries 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_summaries call is checked against it from then on.
Questions about vibe_preview_summaries
Read recent text summaries for a project (Phase 4). Each entry is a one-sentence description of what visibly changed between two frames, with before/after hashes. Default returns last 50; use limit to widen. It is categorised as a Read tool in the Yaver MCP Server, which means it retrieves data without modifying state.
vibe_preview_summaries accepts 2 parameters: limit, 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_summaries: 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_summaries 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_summaries 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_summaries. 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_summaries 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