copilot_suggest_shell · GitHub Copilot CLI MCP Server MCP

WHAT IT DOES

What copilot_suggest_shell does on GitHub Copilot CLI MCP Server

AI agents invoke copilot_suggest_shell to trigger actions in GitHub Copilot CLI MCP Server. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.

WHY IT NEEDS A POLICY

Why copilot_suggest_shell needs a policy

The tool name implies shell command suggestion, which based on the server context wraps GitHub Copilot CLI to generate shell commands. Shell command suggestions can lead to execution of arbitrary shell commands, making this potentially high severity.

From the tool's definition Tool name 'copilot_suggest_shell' combined with server description: 'natural language command suggestions...for shell...commands'. Sibling tools include 'copilot_suggest' and 'copilot_explain', suggesting shell command generation/execution.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

copilot_suggest_shell Rate-limited

copilot_suggest_shell stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "copilot_suggest_shell": {
      "limits": [
        {
          "counter": "copilot_suggest_shell_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

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

FAQ

Questions about copilot_suggest_shell

What does the copilot_suggest_shell tool do? +

copilot_suggest_shell. It is categorised as a Execute tool in the GitHub Copilot CLI MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on copilot_suggest_shell? +

Register the GitHub Copilot CLI MCP Server MCP server in PolicyLayer and add a rule for copilot_suggest_shell: 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 Copilot CLI MCP Server. Nothing to install.

What risk level is copilot_suggest_shell? +

copilot_suggest_shell is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit copilot_suggest_shell? +

Yes. Add a rate_limit block to the copilot_suggest_shell 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 copilot_suggest_shell completely? +

Set action: deny in the PolicyLayer policy for copilot_suggest_shell. 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 copilot_suggest_shell? +

copilot_suggest_shell is provided by the GitHub Copilot CLI MCP Server MCP server (wminson/copilot-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.