AI agents use github_prepare_feature_workflow to create or update resources in Github — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Github environment.
This tool performs reversible data modification (branch creation and main updates) but does not push changes to remote, delete data, or trigger external deployments. The most severe action is branch creation, which is a Write operation.
From the tool's definition Tool creates a new feature branch and updates main, which are reversible write operations. Description explicitly states it 'check[s] status, update[s] main, and create[s] a new feature branch.' Creating branches modifies repository state.
Attacks that exploit this kind of access
Check status, update main, and create a new feature branch. Does not push or create a PR. It is categorised as a Write tool in the Github MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Github MCP server in PolicyLayer and add a rule for github_prepare_feature_workflow: 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. Nothing to install.
github_prepare_feature_workflow 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 github_prepare_feature_workflow 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 github_prepare_feature_workflow. 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.
github_prepare_feature_workflow is provided by the Github MCP server (matiasnjacob/github-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 →