@securecode/mcp-server

@securecode/mcp-server

MCP Server for SecureCodeHQ. Lets Claude Code access your secrets securely — without ever seeing them.

Get Started in 2 Minutes

The fastest way to set up SecureCodeHQ is from Claude Code itself. Just say:

You: "Set up SecureCode for this project"

The onboard tool walks you through everything — account creation, secret import, and MCP configuration — without leaving the terminal.

What happens during onboarding

Step 1: "Create your account"  → Opens signup in your browser (one click)
Step 2: "Import your .env"     → Drag-and-drop in a secure web window (zero-knowledge)
Step 3: API key + MCP config   → Auto-created and configured by Claude
Step 4: Choose your secrets    → Select which project/env to use
Step 5: SDK setup (optional)   → Generates runtime code for your framework

After onboarding, a .securecoderc file is created in your project root with the API key and project/env config. The SDK and MCP server read it automatically.

Already have an account?

If you already have an account and API key, add this to your project's .mcp.json:

{
  "mcpServers": {
    "securecode": {
      "command": "npx",
      "args": ["@securecode/mcp-server"],
      "env": {
        "SECURECODE_API_KEY": "sc_your_key_here"
      }
    }
  }
}

Or add it globally in ~/.claude.json. Then restart Claude Code.

Zero-Knowledge AI Access

By default, secret values are never shown to the AI. When 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 actual value.

You: "Get my Stripe API key"
Claude: ✓ STRIPE_KEY injected → ~/.securecode/.session/a1b2c3d4.env

The value is NOT in this conversation.

This is inject mode — the default. If you explicitly need the AI to work with the value, use reveal: true (every reveal is audited).

What Claude Can Do

Once connected, Claude Code can:

"Get my Stripe API key"              → injects to local file (AI never sees value)
"Get my DB_URL with reveal"          → reveals value to AI (audited)
"List my production secrets"         → shows names and tags, never values
"Save this API key as OPENAI_KEY"    → creates a new secret
"Import my .env.production file"     → opens secure web import (zero-knowledge)
"Lock my session"                    → blocks all access until you wake it
"Set up SecureCode"                  → guided onboarding (see above)
"Add staging environment"            → import secrets for another env
"Set up the SDK for this project"    → generates loadEnv/getSecret code
"byebye"                            → locks session + cleans secrets from disk

Available Tools

Tool	Description
onboard	Guided setup: signup, import, API key, MCP config, SDK setup — all from Claude Code
get-secret	Get a secret — inject to file by default, reveal: true to show to AI
list-secrets	List all secrets with tags, expiry status, and descriptions
create-secret	Create a new secret with tags, TTL, and domain
update-secret	Update value, description, tags, or domain
delete-secret	Soft-delete a secret
renew-secret	Renew expired secrets or change TTL
import-env	Import from .env — opens a secure web window (values never pass through AI)
export-env	Export secrets as .env or CSV format
get-status	Check plan, usage limits, secrets count, and MCP server version
wake-session	Unlock session with optional tag scope and auto-sleep timer
sleep-session	Lock session, block all access, clean injected files
session-status	Check session status, scope, and time remaining
byebye	End session: lock + clean all injected secrets from disk
get-active-rules	List active MCP access rules (read-only)
help	Get SecureCode docs: tools, SDK setup, sessions, rules, troubleshooting

SDK Setup from Claude Code

After onboarding, you can ask Claude to set up the SDK for your project:

You: "Set up the SecureCode SDK for this Next.js project"

The onboard(action: "setup-sdk") tool:

• Lists your imported secrets grouped by project/env
• Lets you choose between loadEnv() (bulk) or getSecret() (granular)
• Generates the correct code for your framework (Next.js, Express, plain Node.js)
• Handles framework-specific quirks (e.g., Next.js instrumentation.ts with NEXT_RUNTIME guard)

Adding more environments

Already set up but need to add staging or production secrets? Just say:

You: "Add staging secrets to this project"

The onboard(action: "add-environment") tool opens the secure import window for a new environment without repeating the full onboarding.

MCP Access Rules

Control how AI agents access your secrets with tag-based policies. Rules are created from the dashboard and enforced server-side.

Action	Effect
Block Always	Secret is only accessible from the dashboard
Require Confirmation	Agent must acknowledge before accessing
Require Session	Requires an active session (wake-session)
Block Models	Only allows specific AI models
Notify	Sends email notification on access (non-blocking)

You: "Read my STRIPE_LIVE_KEY"
Claude: [MCP Rule: "Block production secrets"]
        Access blocked. This secret is only accessible from the dashboard.

Rules are evaluated by priority: Block Always > Require Session > Block Models > Require Confirmation > Notify.

Session Lock

Control access to your secrets per session:

You: "Wake my session for the acme project staging"
Claude: Session unlocked. Only acme/staging secrets accessible.

You: "Lock my session"
Claude: Session locked. All access blocked. Injected files cleaned.

You: "byebye"
Claude: Session locked & secrets cleaned from disk. See you next time!

Sessions auto-sleep after configurable inactivity (default: 2 hours).

Security Tips (Tip Engine)

The MCP server includes an adaptive Tip Engine that shows security best practices:

• First session: Welcome message with best practices
• Production access: Warning when accessing production-tagged secrets
• Stale secrets: Reminder to rotate credentials older than 90 days
• Generic names: Suggestion to use descriptive secret names
• No TTL: Recommendation to set expiration on frequently-used secrets

Tips are throttled (max 3 per session, 1-week cooldown per secret) so they inform without annoying.

Auto-Update Check

The MCP server checks for updates on first use. If your version is outdated, you'll see a warning:

⚠ Your SecureCode MCP server is outdated (v0.13.0 → v0.14.0).
To update, restart Claude Code — it will fetch the latest version automatically if you use npx.

How It Works

• Zero-knowledge by default: Secret values are written to a local file — the AI never sees them
• Reveal mode: Explicit reveal: true returns value to AI (audited as conscious action)
• Auto-cleanup: Injected files are removed on sleep, byebye, process exit, or next inject
• Parallel sessions: Multiple Claude Code instances don't collide (file hash based on API key + PID)
• Secrets are encrypted with AES-256-GCM using envelope encryption (Cloud KMS)
• Every access is logged with AI model, IP, machine identity, access mode, and timestamp
• API keys are scoped to your account with sc_ prefix
• The MCP server runs locally via stdio transport — secrets never pass through third parties
• Device approval required on first use from each machine
• MCP Access Rules enforce tag-based policies server-side before secret delivery

Requirements

• Node.js >= 18
• A SecureCodeHQ account (create one during onboarding)

License

MIT