Create a new issue in a GitHub repository
AI agents use create_issue to create or update resources in GitHub MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your GitHub MCP Server environment.
This tool creates new issues, which is a reversible Write operation. Issues can be edited, closed, or deleted, so the action is not permanently irreversible. The blast radius is medium because malicious issue creation could spam repositories, disrupt workflows, or socially engineer developers, but the damage is limited and easily remediated.
From the tool's definition Tool name: 'create_issue'; description: 'Create a new issue in a GitHub repository'. The verb 'create' indicates data creation.
Attacks that exploit this kind of access
Create a new issue in a GitHub repository. It is categorised as a Write tool in the GitHub MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the GitHub MCP Server 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 GitHub MCP Server. 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 GitHub MCP Server MCP server (tuanle96/mcp-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 →