gh_issues · RedisNexus MCP: Risk & Policy

WHAT IT DOES

What gh_issues does on RedisNexus

AI agents use gh_issues to create or update resources in RedisNexus — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your RedisNexus environment.

WHY IT NEEDS A POLICY

Why gh_issues needs a policy

This tool performs reversible modifications to GitHub issues (creating, closing, reopening, commenting, editing). These are all write operations that change data state but can be undone or reversed. The severity is medium because misuse could spam issues, close legitimate tickets, or vandalize project documentation, but the blast radius is limited to GitHub issues rather than production systems.

From the tool's definition Tool description states it can 'create, close, reopen, comment, edit' GitHub issues—all write operations that modify state. While 'list' and 'view' are read operations, the tool's primary capability is modifying issue state and content.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

gh_issues Rate-limited

gh_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.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "gh_issues": {
      "limits": [
        {
          "counter": "gh_issues_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches RedisNexus, so you can run agents against it safely.

FAQ

Questions about gh_issues

What does the gh_issues tool do? +

Manage GitHub issues: list, view, create, close, reopen, comment, edit. It is categorised as a Write tool in the RedisNexus MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on gh_issues? +

Register the RedisNexus MCP server in PolicyLayer and add a rule for gh_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 RedisNexus. Nothing to install.

What risk level is gh_issues? +

gh_issues is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit gh_issues? +

Yes. Add a rate_limit block to the gh_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.

How do I block gh_issues completely? +

Set action: deny in the PolicyLayer policy for gh_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.

What MCP server provides gh_issues? +

gh_issues is provided by the RedisNexus MCP server (rajkumar-madhu/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.