stop_github_copilot_agent
AI agents invoke stop_github_copilot_agent to trigger actions in SousChef. 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.
Stopping a GitHub Copilot agent constitutes triggering an external operation whose effects depend on the agent's current state and integration points. While not destructive (the agent can be restarted) or write-like (not modifying data directly), it is an active control action that affects infrastructure state. Classification as Execute reflects that this tool initiates an external process termination.
From the tool's definition Tool name 'stop_github_copilot_agent' indicates termination of an external service agent; no description provided to clarify scope.
Documented attack patterns abuse exactly the kind of access stop_github_copilot_agent gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and SousChef, and nothing reaches the server without passing your rules. This is the rule we recommend for stop_github_copilot_agent:
{
"version": "1",
"default": "deny",
"tools": {
"stop_github_copilot_agent": {
"limits": [
{
"counter": "stop_github_copilot_agent_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}stop_github_copilot_agent 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.
Free to start. No card required.
stop_github_copilot_agent. It is categorised as a Execute tool in the SousChef MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the SousChef MCP server in PolicyLayer and add a rule for stop_github_copilot_agent: 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 SousChef. Nothing to install.
stop_github_copilot_agent is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the stop_github_copilot_agent 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 stop_github_copilot_agent. 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.
stop_github_copilot_agent is provided by the SousChef MCP server (kpeacocke/souschef). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from SousChef, 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.
96 SousChef tools catalogued and risk-classified — across an index of 43,000+ MCP servers.