Create a new release in a GitHub repository.
AI agents use create_release to create or update resources in Downscoping — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Downscoping environment.
This tool creates a new release, which is a reversible write operation on GitHub (releases can be deleted or updated). While significant, it does not irreversibly destroy data (Destructive), execute arbitrary code (Execute), or move money (Financial). The severity is high because creating releases affects software distribution and users, and misuse could publish unintended versions or disrupt release pipelines.
From the tool's definition Tool name 'create_release' and description 'Create a new release in a GitHub repository' indicate creation of a new versioned release artifact.
Attacks that exploit this kind of access
Create a new release in a GitHub repository. It is categorised as a Write tool in the Downscoping MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Downscoping MCP server in PolicyLayer and add a rule for create_release: 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 Downscoping. Nothing to install.
create_release 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_release 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_release. 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_release is provided by the Downscoping MCP server (kbroughton/downscoping-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 →