inspector_disconnect · Mcp Inspector MCP: Risk & Policy

WHAT IT DOES

What inspector_disconnect does on Mcp Inspector

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

PARAMETERS

Parameter	Type	Required	Description
`session_id`	string	Yes	Session ID returned by inspector_connect

Parameters from the server's own tool schema.

WHY IT NEEDS A POLICY

Why inspector_disconnect needs a policy

An AI agent can call inspector_disconnect faster than any human can review — one bad instruction and it creates or modifies resources in Mcp Inspector by the hundred, each call as confident as the last.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

inspector_disconnect Rate-limited

inspector_disconnect 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": {
    "inspector_disconnect": {
      "limits": [
        {
          "counter": "inspector_disconnect_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 Mcp Inspector, so you can run agents against it safely.

FAQ

Questions about inspector_disconnect

What does the inspector_disconnect tool do? +

Close an active MCP server session by session_id. It is categorised as a Write tool in the Mcp Inspector MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

What parameters does inspector_disconnect accept? +

inspector_disconnect accepts 1 parameter: session_id. Required: session_id. The full parameter table on this page comes from the server's own tool schema.

How do I enforce a policy on inspector_disconnect? +

Register the Mcp Inspector MCP server in PolicyLayer and add a rule for inspector_disconnect: 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 Mcp Inspector. Nothing to install.

What risk level is inspector_disconnect? +

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

Can I rate-limit inspector_disconnect? +

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

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

inspector_disconnect is provided by the Mcp Inspector MCP server (@fre4x/mcp-inspector). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

// THE FULL RECORD

inspector_disconnect is one line of Mcp Inspector'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 →