Describe the proposed permission change for a finding. Appwrite
AI agents call preview_fix to retrieve information from Appwrite Security without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool appears to generate or display a description of a potential security fix (permission change proposal) for audit findings. The word 'preview' and 'describe' indicate it shows information about what could be changed rather than actually applying changes. This is a retrieval/information-display operation with no side effects—the actual permission changes would need to be applied through a separate tool.
From the tool's definition Tool name 'preview_fix' and description 'Describe the proposed permission change' indicate this is a descriptive/informational tool that displays or previews proposed changes without executing them.
Attacks that exploit this kind of access
Describe the proposed permission change for a finding. Appwrite. It is categorised as a Read tool in the Appwrite Security MCP Server, which means it retrieves data without modifying state.
Register the Appwrite Security MCP server in PolicyLayer and add a rule for preview_fix: 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 Appwrite Security. Nothing to install.
preview_fix 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 preview_fix 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 preview_fix. 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.
preview_fix is provided by the Appwrite Security MCP server (perufitlife/appwrite-security-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →