Upload file to Supabase Storage
AI agents use supabase.storage_put to create or update resources in MCP Fullstack — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your MCP Fullstack environment.
File upload is a write operation that creates or modifies data in cloud storage. Severity is high rather than critical because the blast radius depends on file content and destination permissions - an AI agent could upload malicious files, overwrite existing files, or fill storage quotas, but this is less severe than financial transactions or irreversible system destruction.
From the tool's definition Tool uploads file to Supabase Storage - a cloud storage service. The verb 'put' and 'Upload' confirm this is a write operation that creates/modifies data.
Attacks that exploit this kind of access
Upload file to Supabase Storage. It is categorised as a Write tool in the MCP Fullstack MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the MCP Fullstack MCP server in PolicyLayer and add a rule for supabase.storage_put: 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 MCP Fullstack. Nothing to install.
supabase.storage_put 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 supabase.storage_put 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 supabase.storage_put. 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.
supabase.storage_put is provided by the MCP Fullstack MCP server (jacobfv/mcp-fullstack). 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 →