runTypeTests · TypeScript LSP MCP: Risk & Policy

WHAT IT DOES

What runTypeTests does on TypeScript LSP MCP

AI agents invoke runTypeTests to trigger actions in TypeScript LSP 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 runTypeTests needs a policy

This tool executes type test assertions from files, which is an Execute action rather than a passive Read (like getDefinition or getDiagnostics). While the blast radius is limited compared to arbitrary shell execution, running untrusted test assertions could trigger side effects, infinite loops, or resource exhaustion.

From the tool's definition Tool performs 'Run type test assertions' — executes code-based assertions from files. Even though the execution is scoped to type testing, it still constitutes code execution whose outcome depends on file content and test logic.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

runTypeTests Rate-limited

runTypeTests 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": {
    "runTypeTests": {
      "limits": [
        {
          "counter": "runtypetests_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 TypeScript LSP MCP, so you can run agents against it safely.

FAQ

Questions about runTypeTests

What does the runTypeTests tool do? +

Run type test assertions from files with @ts-lsp-mcp expect-type/expect-error comments. It is categorised as a Execute tool in the TypeScript LSP 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 runTypeTests? +

Register the TypeScript LSP MCP server in PolicyLayer and add a rule for runTypeTests: 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 TypeScript LSP MCP. Nothing to install.

What risk level is runTypeTests? +

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

Can I rate-limit runTypeTests? +

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

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

runTypeTests is provided by the TypeScript LSP MCP server (jaenster/ts-lsp-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.