AI agents use update_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 |
|---|---|---|---|
body | string | — | The body of the pull request |
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) |
state | string | — | The state of the pull request |
title | string | — | The title of the pull request |
labels | string | — | The labels of the pull request. example: bug,performance |
number | number | Yes | The number of the pull request |
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.
Updating a pull request modifies metadata, description, state, or other properties of an existing PR. This is a Write operation because it creates or modifies data reversibly — changes can be undone or reverted. The severity is high because an AI agent could modify pull requests in unintended ways (change descriptions, merge settings, reviewer assignments) affecting code review workflows and repository management.
From the tool's definition Tool name 'update_pull' and description 'Update a pull request' indicate modification of existing pull request data. This is a reversible change operation typical of Write category tools.
Risk signalsAccepts raw HTML/template content (body) · High parameter count (14 properties)
Attacks that exploit this kind of access
Update 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.
update_pull accepts 12 parameters: body, repo, draft, issue, owner, state, title, labels, number, testers, assignees, testers_number. Required: repo, owner, number. 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 update_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.
update_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 update_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 update_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.
update_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 →