execute_stream · Rxjs MCP: Risk & Policy

WHAT IT DOES

What execute_stream does on Rxjs

AI agents invoke execute_stream to trigger actions in Rxjs. 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 execute_stream needs a policy

This tool executes arbitrary RxJS/JavaScript code provided as arguments in an isolated worker thread. While the isolation provides some sandboxing, code execution capabilities are inherently high-risk for AI agent misuse—an agent could execute malicious code, access sensitive data within the execution environment, or perform unintended operations.

From the tool's definition Tool description explicitly states 'Execute RxJS code in an isolated environment' and 'capture the stream emissions, timeline, and performance metrics.' The name 'execute_stream' combined with capability to run code indicates arbitrary code execution…

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

execute_stream Rate-limited

execute_stream 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": {
    "execute_stream": {
      "limits": [
        {
          "counter": "execute_stream_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 Rxjs, so you can run agents against it safely.

FAQ

Questions about execute_stream

What does the execute_stream tool do? +

Execute RxJS code in an isolated environment and capture the stream emissions, timeline, and performance metrics. Code runs in a separate worker thread for security. It is categorised as a Execute tool in the Rxjs MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on execute_stream? +

Register the Rxjs MCP server in PolicyLayer and add a rule for execute_stream: 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 Rxjs. Nothing to install.

What risk level is execute_stream? +

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

Can I rate-limit execute_stream? +

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

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

execute_stream is provided by the Rxjs MCP server (shuji-bonji/rxjs-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.