vision.run
Queue normalized geometry evidence generation without promoting unresolved scale.
This record as markdown: /tools/visionmcp/vision.run.md
What vision.run does on Visionmcp
AI agents invoke vision.run 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.run is rated High
This tool executes a geometry processing operation (evidence generation) rather than simply reading or writing static data. While the description is somewhat opaque and lacks detail about side effects or rollback capability, the verb 'run' combined with 'Queue' and 'generation' suggests triggering an external computation.
From the tool's definition 'Queue normalized geometry evidence generation' indicates the tool triggers an external operation (evidence generation) whose effects depend on the geometry arguments provided. The word 'Queue' suggests asynchronous execution of a computational process.
Attacks that exploit this kind of access
The rule that runs vision.run 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.run, this is the rule to start with:
vision.run 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.run call is checked against it from then on.
Questions about vision.run
Queue normalized geometry evidence generation without promoting unresolved scale. 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.run: 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.run 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.run 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.run. 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.run 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