Create a new release
AI agents use gh_release_create to create or update resources in GitHub CLI MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your GitHub CLI MCP Server environment.
This tool creates a new release, which is a reversible write operation. While releases can be deleted, the primary action is creation/modification of repository metadata and artifacts. This is more severe than a simple Read operation but less severe than Destructive (which would be permanent deletion) or Execute (which would run arbitrary code).
From the tool's definition Tool name 'gh_release_create' and description 'Create a new release' indicate creation of a new release artifact in a GitHub repository.
Attacks that exploit this kind of access
Create a new release. It is categorised as a Write tool in the GitHub CLI MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the GitHub CLI MCP Server MCP server in PolicyLayer and add a rule for gh_release_create: 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 GitHub CLI MCP Server. Nothing to install.
gh_release_create 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 gh_release_create 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 gh_release_create. 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.
gh_release_create is provided by the GitHub CLI MCP Server MCP server (munch-group/gh-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 →