start_session · OpenClaude MCP Server MCP: Risk & Policy

WHAT IT DOES

What start_session does on OpenClaude MCP Server

AI agents invoke start_session to trigger actions in OpenClaude 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 start_session needs a policy

Starting a session on an LLM control plane initiates execution of external processes (Ollama instances, model inference) whose effects depend on arguments (model selection, session parameters). This falls under Execute rather than Write because it triggers live operations rather than merely storing data.

From the tool's definition Tool name 'start_session' combined with server context describing 'Ollama-based local LLM sessions' indicates the tool initiates or spawns a session object that executes language model operations.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

start_session Rate-limited

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": {
    "start_session": {
      "limits": [
        {
          "counter": "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 OpenClaude MCP Server, so you can run agents against it safely.

FAQ

Questions about start_session

What does the start_session tool do? +

start_session. It is categorised as a Execute tool in the OpenClaude 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 start_session? +

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

What risk level is start_session? +

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

Can I rate-limit start_session? +

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

Set action: deny in the PolicyLayer policy for 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 start_session? +

start_session is provided by the OpenClaude MCP Server MCP server (sandraschi/openclaude-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

// THE FULL RECORD

start_session is one line of OpenClaude MCP Server's registry record.

The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.

Teams ship this data inside their own products. See what a licence covers →