blackwall-mcp

bluetieroperations-create/blackwall-mcp

★ 0 stars JavaScript 🤖 AI/LLM Updated 4d ago

Pre-action risk gate for AI agents — MCP server. Risk-checks an agent's action before it runs and gates the irreversible ones. blackwalltier.com

View on GitHub → Try with Claude — $10 free →

Quick Install

Copy the config for your editor. Some servers may need additional setup — check the README.

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "blackwall-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "bluetieroperations-create/blackwall-mcp"
      ]
    }
  }
}

README Excerpt

**A guardrail for AI agents, as an MCP server.** Your agent calls one tool — `forecast` — before any irreversible action (send email, move money, run SQL, delete data, post content). It gets back a risk score (0–100), a `GO` / `CAUTION` / `STOP` recommendation, and named red flags in ~sub-second. Works in any MCP host: **Claude Desktop, Claude Code, Cursor, Windsurf, ChatGPT (Apps SDK)**, and any agent framework with MCP support.

Tools (9)

BLACKWALL_API_KEYBLACKWALL_BASE_URLBLACKWALL_MODEactioncontextdeepdepthenforceinputs

blackwall-mcp

Quick Install

README Excerpt

Tools (9)

Related AI/LLM Servers