AI agents use create_pull to create or update resources in Mcp Gitee — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Mcp Gitee environment.
| Parameter | Type | Required | Description |
|---|---|---|---|
base | string | Yes | The target branch of the pull request |
body | string | — | The body of the pull request |
head | string | Yes | The source branch of the pull request, Format: branch (master) or: path_with_namespace:branch (oschina/gitee:master) |
repo | string | Yes | The path of the repository |
draft | boolean | — | Whether to set the pull request as draft |
issue | string | — | The issue of the pull request |
owner | string | Yes | The space address to which the repository belongs (the address path of the enterprise, organization or individual) |
title | string | Yes | The title of the pull request |
labels | string | — | The labels of the pull request. example: bug,performance |
testers | string | — | The testers of the pull request, example: (username1,username2) |
assignees | string | — | The assignees of the pull request, example: (username1,username2) |
testers_number | number | — | The min number of testers need accept of the pull request |
Parameters from the server's own tool schema.
Creating a pull request modifies repository state by adding a new PR, but this action is reversible (the PR can be closed or deleted). It does not execute arbitrary code, delete data irreversibly, or move financial resources. It fits the Write category as it creates a new data entity.
From the tool's definition Tool name is 'create_pull' and description states 'Create a pull request'. This creates a new pull request object in the repository, which is a reversible write operation.
Risk signalsAccepts raw HTML/template content (body) · High parameter count (14 properties)
Attacks that exploit this kind of access
Create a pull request. It is categorised as a Write tool in the Mcp Gitee MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
create_pull accepts 12 parameters: base, body, head, repo, draft, issue, owner, title, labels, testers, assignees, testers_number. Required: base, head, repo, owner, title. The full parameter table on this page comes from the server's own tool schema.
Register the Mcp Gitee MCP server in PolicyLayer and add a rule for create_pull: 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 Mcp Gitee. Nothing to install.
create_pull 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_pull 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_pull. 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_pull is provided by the Mcp Gitee MCP server (@gitee/mcp-gitee). 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 →