Upload app to PGYER
AI agents use upload-app to create or update resources in PGYER MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your PGYER MCP Server environment.
The tool creates or stores new app artifacts on the PGYER platform, which is a Write category action. Severity is medium because uploading an app could have downstream consequences if malicious code is deployed, but the tool itself is reversible and doesn't directly move money or destroy data. Confidence is high because the functionality is explicit in the name and description.
From the tool's definition Tool name 'upload-app' and description 'Upload app to PGYER' indicate creation and storage of app binaries on the platform. This is a reversible write operation (apps can be deleted/replaced).
Attacks that exploit this kind of access
Upload app to PGYER. It is categorised as a Write tool in the PGYER MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the PGYER MCP Server MCP server in PolicyLayer and add a rule for upload-app: 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 PGYER MCP Server. Nothing to install.
upload-app 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 upload-app 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 upload-app. 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.
upload-app is provided by the PGYER MCP Server MCP server (pgyer/pgyer-mcp-server). 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 →