MCPLow riskUnclaimed

figuard-mcp

Pre-flight spend authorization for AI agents. Set a budget, enforce limits, audit every decision.

figuardfiguard/figuard-mcp★ 2Updated Jun 17, 2026

server.json

{
  "$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
  "name": "io.github.figuard/figuard-mcp",
  "description": "Pre-flight spend authorization for AI agents. Set a budget, enforce limits, audit every decision.",
  "repository": {
    "url": "https://github.com/figuard/figuard-core",
    "source": "github",
    "subfolder": "packages/mcp"
  },
  "version": "1.2.0",
  "websiteUrl": "https://figuard.io",
  "packages": [
    {
      "registryType": "npm",
      "identifier": "figuard-mcp",
      "version": "1.2.0",
      "transport": {
        "type": "stdio"
      },
      "environmentVariables": [
        {
          "description": "FiGuard API key — set this (with FIGUARD_BASE_URL) to use a self-hosted FiGuard server. Leave unset to run embedded: in-process enforcement against a local SQLite file, no account or server needed.",
          "format": "string",
          "isSecret": true,
          "name": "FIGUARD_API_KEY"
        },
        {
          "description": "Self-hosted FiGuard server URL. Leave unset to run embedded against a local SQLite file.",
          "format": "string",
          "name": "FIGUARD_BASE_URL"
        },
        {
          "description": "Path to the embedded SQLite file (default ~/.figuard/figuard.db). Embedded is the default backend — no server required.",
          "format": "string",
          "name": "FIGUARD_DATABASE"
        },
        {
          "description": "Backend mode: embedded | server | sandbox. Defaults to embedded when nothing else is configured.",
          "format": "string",
          "name": "FIGUARD_MODE"
        }
      ]
    }
  ]
}

Permissions

DeclaredDetected
Runs code—node
Installs—npm:figuard-mcp@1.2.0
Runs install scripts—None
NetworkNoneNone
Needs credentialsFIGUARD_API_KEYFIGUARD_API_KEY
Outside the workspace—None
Agent tools—None

Checks

Low risk · Nothing worth a warning was found.

Not reviewed by a person · Checked by rules; the model review is not switched on yet.

Versions

  1. #11.2.0latestOct 7, 2026