Manages GitHub Issues for tracking bugs, features, and tasks. Supports listing issues with filters, getting issue details, creating new issues, updating existing issues, closing issues, and adding issues to GitHub Projects.
AI agents use github_issues to create or update resources in SushiMCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your SushiMCP environment.
The tool can create, modify, and close GitHub issues. Closing an issue is reversible (can be reopened), and creation/updates are standard write operations. No irreversible deletion is mentioned. The blast radius is medium — an AI agent could spam issues or close valid ones, but this is recoverable.
From the tool's definition creating new issues, updating existing issues, closing issues, and adding issues to GitHub Projects
Documented attack patterns abuse exactly the kind of access github_issues gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and SushiMCP, and nothing reaches the server without passing your rules. This is the rule we recommend for github_issues:
{
"version": "1",
"default": "deny",
"tools": {
"github_issues": {
"limits": [
{
"counter": "github_issues_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}github_issues 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.
Free to start. No card required.
Manages GitHub Issues for tracking bugs, features, and tasks. Supports listing issues with filters, getting issue details, creating new issues, updating existing issues, closing issues, and adding issues to GitHub Projects. It is categorised as a Write tool in the SushiMCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Sushi MCP server in PolicyLayer and add a rule for github_issues: 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 SushiMCP. Nothing to install.
github_issues 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 github_issues 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 github_issues. 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.
github_issues is provided by the Sushi MCP server (maverickg59/sushimcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from SushiMCP, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
7 SushiMCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.