Update a pull request branch with the latest changes from the base branch
AI agents use update_pull_request_branch to create or update resources in Server Github — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Server Github environment.
| Parameter | Type | Required | Description |
|---|---|---|---|
repo | string | Yes | Repository name |
owner | string | Yes | Repository owner (username or organization) |
pull_number | number | Yes | Pull request number |
expected_head_sha | string | — | The expected SHA of the pull request's HEAD ref |
Parameters from the server's own tool schema.
This tool merges/rebases the base branch into the PR branch, modifying the PR branch's commit history. This is a reversible write operation (the branch can be reset), not destructive. Misuse could introduce unwanted changes into a PR branch, but the blast radius is moderate since it's scoped to a specific PR branch.
From the tool's definition Update a pull request branch with the latest changes from the base branch
Attacks that exploit this kind of access
Update a pull request branch with the latest changes from the base branch. It is categorised as a Write tool in the Server Github MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
update_pull_request_branch accepts 4 parameters: repo, owner, pull_number, expected_head_sha. Required: repo, owner, pull_number. The full parameter table on this page comes from the server's own tool schema.
Register the Server Github MCP server in PolicyLayer and add a rule for update_pull_request_branch: 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 Server Github. Nothing to install.
update_pull_request_branch 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 update_pull_request_branch 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 update_pull_request_branch. 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.
update_pull_request_branch is provided by the Server Github MCP server (@iflow-mcp/server-github). 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 →