{
  "markdown": "# @securecode/mcp-server\n\nMCP Server for [SecureCodeHQ](https://securecodehq.com). Lets Claude Code access your secrets securely without ever seeing them.\n\n[![SecureCode MCP server](https://glama.ai/mcp/servers/juanisidoro/securecode-mcp/badges/card.svg)](https://glama.ai/mcp/servers/juanisidoro/securecode-mcp)\n\n## Quick Start\n\n```bash\nclaude mcp add securecode -- npx -y @securecode/mcp-server\n```\n\nThen tell Claude Code:\n\n```\nSet up SecureCode in this project\n```\n\nThe onboard tool walks you through account creation, secret import, and configuration. Takes about 2 minutes.\n\n## What It Does\n\nYour secrets (API keys, tokens, passwords) are encrypted with AES-256 and stored in SecureCode. Claude Code accesses them via MCP, but the actual values never appear in the chat.\n\nWhen Claude reads a secret, the value is written to a local file on your machine. The AI gets the file path but never sees the raw value. This is inject mode, the default.\n\n## Tools\n\n| Tool | What it does |\n|------|-------------|\n| `onboard` | Guided setup: signup, import, API key, config, SDK |\n| `get-secret` | Get a secret (injected to file by default, `reveal: true` to show to AI) |\n| `list-secrets` | List all secrets with tags and expiry status |\n| `create-secret` | Create a new secret |\n| `update-secret` | Update value, description, or tags |\n| `delete-secret` | Delete a secret |\n| `renew-secret` | Renew expired secrets or change TTL |\n| `import-env` | Import .env via secure web window (values never pass through AI) |\n| `export-env` | Export secrets as .env or CSV |\n| `get-status` | Check plan, usage, and MCP server version |\n| `wake-session` | Unlock session with optional scope and auto-sleep timer |\n| `sleep-session` | Lock session and clean injected files |\n| `session-status` | Check session state and time remaining |\n| `byebye` | Lock session + clean all secrets from disk |\n| `get-active-rules` | List active MCP access rules (read-only) |\n| `security-check` | Post-setup security hardening checks |\n| `help` | Docs: tools, SDK, sessions, rules, troubleshooting |\n\n## MCP Access Rules\n\nControl how AI agents access your secrets with tag-based policies. Created from the [dashboard](https://securecodehq.com), enforced server-side.\n\n| Action | Effect |\n|--------|--------|\n| Block Always | Secret only accessible from the dashboard |\n| Require Confirmation | Agent must acknowledge before accessing |\n| Require Session | Requires active session (wake-session) |\n| Block Models | Only allows specific AI models |\n| Notify | Sends email on access (non-blocking) |\n\n## Session Lock\n\n```\nYou: \"Wake my session for acme staging\"\nClaude: Session unlocked. Only acme/staging secrets accessible.\n\nYou: \"byebye\"\nClaude: Session locked & secrets cleaned from disk.\n```\n\nSessions auto-sleep after configurable inactivity (default: 2 hours).\n\n## How It Works\n\n- Secret values are written to a local file, the AI never sees them (inject mode)\n- Explicit `reveal: true` returns value to AI (audited)\n- Injected files are removed on sleep, byebye, or process exit\n- Multiple Claude Code instances don't collide (hash based on API key + PID)\n- Encrypted with AES-256-GCM using envelope encryption (Cloud KMS)\n- Every access is logged with AI model, IP, machine identity, and timestamp\n- Runs locally via stdio transport, secrets never pass through third parties\n- Device approval required on first use from each machine\n\n## SDK\n\nThe companion SDK lets your app load secrets at runtime:\n\n```bash\nnpm install @securecode/sdk\n```\n\n```typescript\nimport { loadEnv } from '@securecode/sdk';\nawait loadEnv(); // all secrets loaded into process.env\n```\n\n[SDK on npm](https://www.npmjs.com/package/@securecode/sdk)\n\n## Links\n\n- Website: https://securecodehq.com\n- npm: https://www.npmjs.com/package/@securecode/mcp-server\n- SDK: https://www.npmjs.com/package/@securecode/sdk\n\n## Requirements\n\n- Node.js >= 18\n- A SecureCodeHQ account (free tier: 50 secrets, 10K accesses/month)\n\n## License\n\nMIT",
  "bytes": 3971,
  "sha": "680fc51e352883461637106f195370dbc48b121e5301b3cea03a2afe45b0d081",
  "repo_slug": "juanisidoro/securecode-mcp",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_io_github_juanisidoro_securecode_92842dfe/readme"
}