vision_query
Look at the screen currently being shared in a meeting and answer a question about it. Returns a natural-language answer based on the visual content. Use ONLY when the user explicitly asks about the screen/slide/document being shown.
This record as markdown: /tools/io-github-saloprj-dialogbrain/vision-query.md
What vision_query does on Dialogbrain
AI agents call vision_query to retrieve information from Dialogbrain 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 |
|---|---|---|---|
question | string | Yes | Question about the shared screen. |
image_b64 | string | — | Base64-encoded JPEG image of the screen-share frame. |
Parameters from the server's own tool schema.
Why vision_query is rated Low
vision_query retrieves and analyzes visual information from a shared screen to provide answers. It does not modify data, execute code, delete content, or commit financial transactions. The operation is purely observational and read-only, consistent with Read category tools.
From the tool's definition Tool description states it 'Look at the screen currently being shared in a meeting and answer a question about it.
Attacks that exploit this kind of access
The rule that runs vision_query safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Dialogbrain, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For vision_query, this is the rule to start with:
vision_query 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 Dialogbrain, apply this rule, and every vision_query call is checked against it from then on.
Questions about vision_query
Look at the screen currently being shared in a meeting and answer a question about it. Returns a natural-language answer based on the visual content. Use ONLY when the user explicitly asks about the screen/slide/document being shown. It is categorised as a Read tool in the Dialogbrain MCP Server, which means it retrieves data without modifying state.
vision_query accepts 2 parameters: question, image_b64. Required: question. The full parameter table on this page comes from the server's own tool schema.
Register the Dialogbrain MCP server in PolicyLayer and add a rule for vision_query: 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 Dialogbrain. Nothing to install.
vision_query 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 vision_query 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 vision_query. 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.
vision_query is provided by the Dialogbrain MCP server (https://api.dialogbrain.com/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Dialogbrain, and thousands of servers like it.
This server
Across the catalogue