mcp-restart

Tool annotations

No tools have read-only/destructive annotations

Add readOnlyHint or destructiveHint annotations to every tool so hosts can warn users before invoking.

All four hints declared on every tool

5/5 tools missing one or more hints — list_agents (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); server_status (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); start_agent (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +2 more. OpenAI's directory rejects tools where any of the four hints are missing or non-boolean.

For every tool, set all four hints (readOnlyHint, destructiveHint, idempotentHint, openWorldHint) to explicit true/false values that match the handler’s actual behaviour.

Tool inputs are validated

Only 0/5 tool handlers declare input schemas (0%)

Declare an inputSchema with zod/joi/yup on every tool definition.

Tests pass

npm test failed — tests do not pass

Make sure npm test runs cleanly. Common cause: missing build step or missing env vars.

Shell command execution

4 child_process/subprocess calls in production code — runs shell commands (src/cli.ts:136, src/supervisor.ts:117, src/supervisor.ts:150)

Prefer library functions over shell-outs. If you must shell out, ensure all inputs are properly escaped.

Secrets never reach shell commands

1 secret value passed to shell commands — possible command injection

Never pass secrets through shell commands. Use library APIs that accept credentials as arguments.

Secrets not logged

2 secret values sent to console.log

Redact or omit secret values from log output.