vision.saccade
Plan and commit a saccade to a new region (IOR-aware).
This record as markdown: /tools/visionmcp/vision.saccade.md
What vision.saccade does on Visionmcp
AI agents invoke vision.saccade to trigger actions in Visionmcp. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call: builds kicked off, notifications sent, workflows started.
Why vision.saccade is rated High
The tool both plans and commits an action (a saccade, i.e., a directed visual focus shift), making it an Execute-category tool. It triggers an external operation within the vision/UI system rather than merely reading data or writing static content. The IOR (Inhibition of Return) awareness implies stateful side effects on the attention model.
From the tool's definition 'Plan and commit a saccade to a new region' — actively commits a navigation/focus action in the visual system
Attacks that exploit this kind of access
The rule that runs vision.saccade safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Visionmcp, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For vision.saccade, this is the rule to start with:
vision.saccade stays usable, but rate-capped: a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Visionmcp, apply this rule, and every vision.saccade call is checked against it from then on.
Questions about vision.saccade
Plan and commit a saccade to a new region (IOR-aware). It is categorised as a Execute tool in the Visionmcp MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Vision MCP server in PolicyLayer and add a rule for vision.saccade: 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 Visionmcp. Nothing to install.
vision.saccade is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the vision.saccade 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.saccade. 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.saccade is provided by the Vision MCP server (joshuahickscorp/visionmcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Vision, and thousands of servers like it.
Across the catalogue