reference.propose_masks
Generate replayable automatic mask proposals with no review authority.
This record as markdown: /tools/visionmcp/reference.propose-masks.md
What reference.propose_masks does on Visionmcp
AI agents invoke reference.propose_masks 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 reference.propose_masks is rated High
The tool generates automatic mask proposals, which involves executing an automated process to produce outputs. It explicitly states 'no review authority', meaning it runs autonomously. While the results may be proposals (not directly applied), the act of generating them involves executing computation/inference.
From the tool's definition "Generate replayable automatic mask proposals" — triggers an automated generation/execution process
Attacks that exploit this kind of access
The rule that runs reference.propose_masks 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 reference.propose_masks, this is the rule to start with:
reference.propose_masks 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 reference.propose_masks call is checked against it from then on.
Questions about reference.propose_masks
Generate replayable automatic mask proposals with no review authority. 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 reference.propose_masks: 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.
reference.propose_masks 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 reference.propose_masks 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 reference.propose_masks. 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.
reference.propose_masks 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