Decision Assistant: a guardrail MCP server for AI coding

Hi Cursor community,

I built a small MCP server called Decision Assistant.

It adds deterministic guardrails to AI coding workflows.

Instead of reviewing AI-generated code after the fact,
it interrupts risky actions before execution.

Example signals:

  • files_touched
  • diff_lines_total
  • ship_gap_days

If a change looks risky the server returns:

ALLOW
REQUIRE_CONFIRM
BLOCK

In REQUIRE_CONFIRM mode the server issues a receipt
bound to a plan_hash. The user must explicitly re-run
the action with that receipt.

Repeated EXECUTE calls are idempotent.

The goal is not to replace AI coding tools,
but to add a safety layer around execution.

GitHub:

npm:
npx [email protected]

Would love feedback from people experimenting with MCP tooling.

1 Like

An MCP that interrupts risky AI coding actions before execution.

Would you prefer this as a local solo-dev safety layer, or as a team policy layer with shared rules?