Apply a baseline branch-protection policy. WRITE OPERATION.
AI agents use set_branch_protection to create or update resources in Ghe Mcp Gateway — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Ghe Mcp Gateway environment.
This tool modifies repository settings reversibly by applying or updating branch protection policies. It is categorized as Write because it creates or modifies data (branch protection configuration) without permanently destroying information.
From the tool's definition Tool name 'set_branch_protection' and explicit description 'Apply a baseline branch-protection policy. WRITE OPERATION.' indicate modification of repository configuration.
Attacks that exploit this kind of access
Apply a baseline branch-protection policy. WRITE OPERATION. It is categorised as a Write tool in the Ghe Mcp Gateway MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Ghe Mcp Gateway MCP server in PolicyLayer and add a rule for set_branch_protection: 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 Ghe Mcp Gateway. Nothing to install.
set_branch_protection 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 set_branch_protection 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 set_branch_protection. 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.
set_branch_protection is provided by the Ghe Mcp Gateway MCP server (mholzinger/ghe-mcp-gateway). 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 →