triage_issue
Triage an issue by capturing a focused triage rationale and optionally applying metadata (labels, issue type, and issue fields) in a single operation. Use this tool when: - You are triaging a newly opened or untriaged issue for maintainers - You need to categorize the issue (type) and suggest/app...
This record as markdown: /tools/github/triage-issue.md
What triage_issue does on GitHub
AI agents use triage_issue 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.
| Parameter | Type | Required | Description |
|---|---|---|---|
repo | string | — | Repository name |
type | string | — | The issue type to set (optional, e.g., 'bug', 'feature_request') |
owner | string | — | Repository owner (username or organization) |
fields | array | — | Custom fields to set on the issue (optional) |
labels | array | — | Labels to apply to the issue (optional) |
issue_number | number | — | The issue number to triage |
triage_rationale | string | — | The triage comment body containing analysis and rationale. This will be posted as a comment on the issue. |
Parameters from the server's own tool schema.
Why triage_issue is rated Medium
This tool modifies issue state by applying labels, issue type, and custom fields—reversible write operations. While it doesn't delete data (ruling out Destructive) or execute arbitrary code (ruling out Execute), it does alter issue metadata that maintainers depend on.
From the tool's definition The tool description states it applies metadata (labels, issue type, and issue fields) and records a triage report in a single operation.
Attacks that exploit this kind of access
The rule that runs triage_issue safely
PolicyLayer is an MCP gateway: it sits between your AI agents and GitHub, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For triage_issue, this is the rule to start with:
triage_issue stays usable, but capped: an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect GitHub, apply this rule, and every triage_issue call is checked against it from then on.
Questions about triage_issue
Triage an issue by capturing a focused triage rationale and optionally applying metadata (labels, issue type, and issue fields) in a single operation. Use this tool when: - You are triaging a newly opened or untriaged issue for maintainers - You need to categorize the issue (type) and suggest/apply relevant labels - You want to record a brief, structured triage report Do not use this tool when: - The user is asking a general product question unrelated to triaging a specific issue triage_rationale should be concise markdown aimed at maintainers (not the issue author); it should contain: - Summary of the issue - Analysis of the problem or request - Suggested next steps or actions. 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.
triage_issue accepts 7 parameters: repo, type, owner, fields, labels, issue_number, triage_rationale. The full parameter table on this page comes from the server's own tool schema.
Register the GitHub MCP server in PolicyLayer and add a rule for triage_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 GitHub. Nothing to install.
triage_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 triage_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 triage_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.
triage_issue is provided by the GitHub MCP server (oci:ghcr.io/github/github-mcp-server:1.3.0). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on GitHub, and thousands of servers like it.
This server
Across the catalogue