BLACK_WALL

BLACKWALL gives your agent a brake.

Community: Submitted by a user or imported; check the owner before granting accessOnlineAPI key requiredGlobalFreeCan modify data

What it can do

  • Forecast: Call this BEFORE taking ANY irreversible or high-stakes action — sending an email, making a payment, running SQL, deleting files or data, posting public content, or calling an external API t

What data it sees

Do you need an account

An API key from the service settings is required

BLACK_WALL gives your agent a brake. It exposes a single tool, forecast, that the agent calls before any irreversible action — sending an email, making a payment, running SQL, deleting data, posting content.

It returns:

  • a risk score (0–100)
  • a reversibility class + rollback cost (reversible / recoverable / irreversible)
  • a gate: proceed / confirm / human-required
  • named red flags from 28 documented failure modes (SQL_NO_WHERE, INTENT_MISMATCH, CROSS_ENVIRONMENT, MASS_RECIPIENT, PROMPT_INJECTION_LIKELY, …)

A normal email clears in one call; a DROP TABLE on prod comes back STOP / human-required — before it runs. The agent can't talk itself into the bad action, because the verdict is a hard gate.

Setup: paste your BLACK_WALL API key as the apiKey parameter. Get one free at https://blackwalltier.com (~100 forecasts/month, no card). A verdict takes ~4–8s.

A BLUETIER product.

Server tool list (1)

Raw names from tools/list. Only developers need these.

forecastCall this BEFORE taking ANY irreversible or high-stakes action — sending an email, making a payment, running SQL, deleting files or data, posting public content, or calling an external API that changes state. Returns a risk score (0–100), a recommendation (GO / CAUTION / STOP), and named red flags. If STOP, do not act — surface the flags to the user. If CAUTION, confirm with the user first.