Create or update repository files on GitHub
AI agents use create_or_update_file to create or update resources in Mcp Asana Minimal — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Mcp Asana Minimal environment.
This tool creates or modifies files in a repository, which are reversible operations (files can be edited or deleted afterward). It does not permanently delete data (not Destructive), execute arbitrary commands (not Execute), nor involve financial transactions (not Financial).
From the tool's definition Tool description states 'Create or update repository files on GitHub' — explicitly modifies data (creates or updates files).
Attacks that exploit this kind of access
Create or update repository files on GitHub. It is categorised as a Write tool in the Mcp Asana Minimal MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Mcp Asana Minimal MCP server in PolicyLayer and add a rule for create_or_update_file: 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 Asana Minimal. Nothing to install.
create_or_update_file 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 create_or_update_file 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 create_or_update_file. 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.
create_or_update_file is provided by the Mcp Asana Minimal MCP server (mcp-asana-minimal). 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 →