feature.review
Record an explicit named approval or rejection for one technical feature.
This record as markdown: /tools/visionmcp/feature.review.md
What feature.review does on Visionmcp
AI agents use feature.review to create or update resources in Visionmcp, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Visionmcp environment.
Why feature.review is rated Medium
This tool writes/records a review decision (approval or rejection) for a feature. It creates or modifies review state data, which is reversible (a rejection can be changed to an approval or vice versa). No code execution, deletion, or financial transaction is involved.
From the tool's definition Record an explicit named approval or rejection for one technical feature
Attacks that exploit this kind of access
The rule that runs feature.review 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 feature.review, this is the rule to start with:
feature.review stays usable, but capped: an agent stuck in a loop can't make hundreds of changes 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 feature.review call is checked against it from then on.
Questions about feature.review
Record an explicit named approval or rejection for one technical feature. It is categorised as a Write tool in the Visionmcp MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Vision MCP server in PolicyLayer and add a rule for feature.review: 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.
feature.review is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the feature.review 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 feature.review. 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.
feature.review 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.
This server
Across the catalogue