happy_start_session · Happy Server MCP: Risk & Policy

WHAT IT DOES

What happy_start_session does on Happy Server MCP

AI agents invoke happy_start_session to trigger actions in Happy Server MCP. 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 happy_start_session needs a policy

This tool initiates processes on remote machines and creates development environments, making it an Execute action. It has a high severity due to its ability to spawn sessions and configure development contexts across multiple machines, with potential side effects including resource allocation, environment setup, and Git repository state changes.

From the tool's definition The tool 'starts a new Happy AI session on a machine' and can 'create a Git worktree for isolated development', triggering external operations on remote machines whose effects depend on arguments (machine selection, environment preset, Git configuration).

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

happy_start_session Rate-limited

happy_start_session 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": {
    "happy_start_session": {
      "limits": [
        {
          "counter": "happy_start_session_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 Happy Server MCP, so you can run agents against it safely.

FAQ

Questions about happy_start_session

What does the happy_start_session tool do? +

Start a new Happy AI session on a machine. Use happy_list_machines to find available machines first. Use happy_list_environment_sets to see available environment presets. Optionally create a Git worktree for isolated development. It is categorised as a Execute tool in the Happy Server MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on happy_start_session? +

Register the Happy Server MCP server in PolicyLayer and add a rule for happy_start_session: 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 Happy Server MCP. Nothing to install.

What risk level is happy_start_session? +

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

Can I rate-limit happy_start_session? +

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

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

happy_start_session is provided by the Happy Server MCP server (zhigang1992/happy-server-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.