remote_connect · Jupyter MCP: Risk & Policy

WHAT IT DOES

What remote_connect does on JupyterMCP

AI agents invoke remote_connect to trigger actions in JupyterMCP. 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 remote_connect needs a policy

Given the server's stated capability to 'connect to remote Jupyter servers' and the tool name 'remote_connect', this tool likely establishes a connection to a remote Jupyter server. This is an external operation that could expose the agent to remote execution environments, kernel access, and notebook data. It spans Write/Execute territory at minimum. Confidence is lowered due to the empty description.

From the tool's definition Tool name 'remote_connect' on a server that 'connect[s] to remote Jupyter servers'; description is empty and uninformative.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

remote_connect Rate-limited

remote_connect 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": {
    "remote_connect": {
      "limits": [
        {
          "counter": "remote_connect_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 JupyterMCP, so you can run agents against it safely.

FAQ

Questions about remote_connect

What does the remote_connect tool do? +

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

How do I enforce a policy on remote_connect? +

Register the Jupyter MCP server in PolicyLayer and add a rule for remote_connect: 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 JupyterMCP. Nothing to install.

What risk level is remote_connect? +

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

Can I rate-limit remote_connect? +

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

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

remote_connect is provided by the Jupyter MCP server (try3d/jupytermcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.