Create a new issue in a GitHub repository
AI agents use create_issue 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 |
|---|---|---|---|
body | string | — | |
repo | string | Yes | |
owner | string | Yes | |
title | string | Yes | |
labels | array | — | |
assignees | array | — | |
milestone | number | — |
Parameters from the server's own tool schema.
This tool creates new issues in a repository, which modifies repository state by adding issue records. This is a Write operation—it creates data reversibly without deleting or executing arbitrary code. Severity is medium because a compromised agent could spam issues or create noise, but the impact is limited to a single repository and issues can be deleted.
From the tool's definition Tool name: 'create_issue'; description: 'Create a new issue in a GitHub repository'. The verb 'create' indicates data creation; issues are reversibly created and can be deleted or modified.
Risk signalsAccepts raw HTML/template content (body)
Attacks that exploit this kind of access
Create a new issue in a GitHub repository. 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.
create_issue accepts 7 parameters: body, repo, owner, title, labels, assignees, milestone. Required: repo, owner, title. 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 create_issue: 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.
create_issue 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_issue 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_issue. 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_issue 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.
create_issue is one line of Server Github's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →