SecureCode
SecureCode is a secrets management MCP server for securely storing, managing, and accessing sensitive data (API keys, tokens, passwords) without exposing raw values in AI conversations. Secrets are encrypted with AES-256-GCM and stored in SecureCodeHQ's cloud.
Secret Management
Get (
get-secret): Retrieves a secret by injecting its value into a local file by default (AI never sees it), or usereveal: truefor audited direct accessList (
list-secrets): View all secrets with tags and expiration status — values never returnedCreate (
create-secret): Store new secrets with optional tags, description, domain, and TTLUpdate (
update-secret): Modify an existing secret's value, description, tags, or domainRenew (
renew-secret): Reactivate expired secrets or change their TTLDelete (
delete-secret): Soft-delete a secret (recoverable)
Import & Export
Import (
import-env): Securely import from.envfiles via a web interface (values bypass the AI)Export (
export-env): Export secrets as a.envfile or CSV
Session Management
Wake (
wake-session): Unlock secret access, optionally scoped to tags with an auto-sleep timerSleep (
sleep-session): Immediately lock the sessionStatus (
session-status): Check active state, scope restrictions, and time remainingByebye (
byebye): Lock session and clean all injected secret files from disk
Access Control & Security
Active rules (
get-active-rules): View tag-based MCP access rules (block, require confirmation, require session, block models, notify) — managed from the dashboardSecurity check (
security-check): Analyze the project for security issues and get hardening recommendationsAll access is logged with AI model, IP, machine identity, and timestamp; secrets never pass through third parties (local stdio transport)
Onboarding, Account & Help
Onboard (
onboard): Guided setup for signup,.envimport, API key creation, and MCP/SDK configurationStatus (
get-status): Check plan, usage limits, secret count, and server versionHelp (
help): Access documentation on tools, SDK, sessions, rules, and troubleshootingCompanion SDK (
@securecode/sdk): Load secrets at runtime in your applications
Allows for the secure import and export of environment variables via .env files, enabling users to migrate existing secrets into the secure vault and manage them within development environments.
@securecode/mcp-server
MCP Server for SecureCodeHQ. Lets Claude Code access your secrets securely without ever seeing them.
Quick Start
claude mcp add securecode -- npx -y @securecode/mcp-serverThen tell Claude Code:
Set up SecureCode in this projectThe onboard tool walks you through account creation, secret import, and configuration. Takes about 2 minutes.
Related MCP server: aarifmms/keyblind
What It Does
Your 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.
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 raw value. This is inject mode, the default.
Tools
Tool | What it does |
| Guided setup: signup, import, API key, config, SDK |
| Get a secret (injected to file by default, |
| List all secrets with tags and expiry status |
| Create a new secret |
| Update value, description, or tags |
| Delete a secret |
| Renew expired secrets or change TTL |
| Import .env via secure web window (values never pass through AI) |
| Export secrets as .env or CSV |
| Check plan, usage, and MCP server version |
| Unlock session with optional scope and auto-sleep timer |
| Lock session and clean injected files |
| Check session state and time remaining |
| Lock session + clean all secrets from disk |
| List active MCP access rules (read-only) |
| Post-setup security hardening checks |
| Docs: tools, SDK, sessions, rules, troubleshooting |
MCP Access Rules
Control how AI agents access your secrets with tag-based policies. Created from the dashboard, enforced server-side.
Action | Effect |
Block Always | Secret only accessible from the dashboard |
Require Confirmation | Agent must acknowledge before accessing |
Require Session | Requires active session (wake-session) |
Block Models | Only allows specific AI models |
Notify | Sends email on access (non-blocking) |
Session Lock
You: "Wake my session for acme staging"
Claude: Session unlocked. Only acme/staging secrets accessible.
You: "byebye"
Claude: Session locked & secrets cleaned from disk.Sessions auto-sleep after configurable inactivity (default: 2 hours).
How It Works
Secret values are written to a local file, the AI never sees them (inject mode)
Explicit
reveal: truereturns value to AI (audited)Injected files are removed on sleep, byebye, or process exit
Multiple Claude Code instances don't collide (hash based on API key + PID)
Encrypted with AES-256-GCM using envelope encryption (Cloud KMS)
Every access is logged with AI model, IP, machine identity, and timestamp
Runs locally via stdio transport, secrets never pass through third parties
Device approval required on first use from each machine
SDK
The companion SDK lets your app load secrets at runtime:
npm install @securecode/sdkimport { loadEnv } from '@securecode/sdk';
await loadEnv(); // all secrets loaded into process.envLinks
Website: https://securecodehq.com
Requirements
Node.js >= 18
A SecureCodeHQ account (free tier: 50 secrets, 10K accesses/month)
License
MIT
Available Tools
17 toolsbyebyeA
End your work session. Locks the session, cleans up all injected secrets from disk, and says goodbye. Use this when you finish working for the day.
Inputs: no named parameters.
create-secretB
Create a new secret. Secrets with the same name can coexist if they have different env tags.
Inputs: name (required), value (required), description, tags, +2 more.
delete-secretA
Delete a secret (soft delete, can be recovered)
Inputs: name (required), tags.
export-envC
Export all secrets as .env or CSV format. Returns the full content with decrypted values.
Inputs: format, tags.
get-active-rulesA
List active MCP access rules. Read-only — rules can only be created or modified from the dashboard. Use this to understand why access to a secret was blocked.
Inputs: no named parameters.
get-secretA
Get a secret by name. By default, injects the value into a local file so it never appears in the AI conversation. Use reveal:true to see the raw value (audited as conscious action). Use cleanup:true to remove all injected secrets from disk.
Inputs: name, tags, reveal, cleanup.
get-statusA
Get your SecureCodeHQ account status: plan, usage limits, secrets count, and MCP server version. Useful to check remaining capacity and verify the server is up to date.
Inputs: no named parameters.
helpB
Get SecureCode documentation: available tools, usage patterns, SDK setup, and common workflows. Use this to understand how to help the user with SecureCode.
Inputs: topic.
import-envA
Import secrets from .env files into SecureCode. For security, .env import must be done through the web interface — the AI agent never sees secret values during import. This tool provides the link to the import page.
Inputs: no named parameters.
list-secretsA
List all available secrets with their tags and expiration status. Returns names and metadata, never values.
Inputs: tags.
onboardA
Start or continue the SecureCode onboarding. Guides the user through signup, .env import, API key creation, MCP configuration, and optional SDK setup — all from Claude Code. Call this tool multiple times to progress through the steps.
Inputs: action, configPath, selectedProject, selectedEnv.
renew-secretA
Renew an expired secret or change its TTL. Use this to reactivate expired secrets or extend expiration.
Inputs: name (required), ttlHours, tags.
security-checkA
Analyze the project for security issues after SecureCode setup. Returns a list of actions the agent MUST execute to protect secrets. Call this after SDK installation.
Inputs: no named parameters.
session-statusA
Check the current session status: active or sleeping, scope restrictions, and time remaining before auto-sleep.
Inputs: no named parameters.
sleep-sessionA
Lock the session immediately. All secret access will be blocked until you wake it again. Use this when you finish working.
Inputs: no named parameters.
update-secretC
Update an existing secret's value, description, tags, or domain. Only provided fields are changed.
Inputs: name (required), value, description, tags, +2 more.
wake-sessionB
Wake (unlock) the session to start accessing secrets. Optionally restrict access to specific tag scope and set auto-sleep timer.
Inputs: scope, autoSleepMinutes.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 17 tools
Most tools have distinct purposes, but some potential confusion exists between 'byebye' and 'sleep-session' (both end sessions) and 'get-secret' and 'list-secrets' (both retrieve secret info). Descriptions help clarify differences, but overlap in session management and secret retrieval could cause misselection.
Tools follow a consistent verb-noun pattern (e.g., create-secret, delete-secret, update-secret) with clear, descriptive names. Minor deviations include 'byebye' (informal) and 'onboard' (single word), but overall naming is predictable and readable.
17 tools is slightly high but reasonable for a secrets management domain, covering operations like CRUD for secrets, session control, onboarding, and security checks. It feels comprehensive without being overly bloated, though some tools like 'help' and 'get-status' might be borderline essential.
The toolset provides complete coverage for secrets management: full CRUD (create, get, list, update, delete, renew), session lifecycle (sleep, wake, status), onboarding, import/export, security analysis, and documentation. No obvious gaps exist for the stated purpose, enabling agents to handle end-to-end workflows.
Maintenance
Related MCP Connectors
A vault for .env files and project credentials: one encryption key per project, a second factor before protected values open, an audit row for every reveal, and scoped MCP access for coding agents.
Secrets for developers and agents—secure context and workflows without exposing secret values.
Encrypted secret store and rotation for autonomous agent credentials
A second brain for Claude: remembers your work, plans your day, encrypted under a key only you hold.
Related MCP Servers
- AlicenseAqualityBmaintenanceLocal AES-256-GCM encrypted vault for AI agents. Resolve {{PLACEHOLDER}} secrets in prompts at runtime — LLMs never see real API keys. Argon2id key derivation, zero cloud.270 npm7MIT
- AlicenseBqualityBmaintenanceEncrypted secrets vault that blinds AI agents to API keys. Stores secrets in AES-256-GCM encrypted SQLite vault, resolves them at runtime via MCP values never appear in LLM conversation transcripts. Sandbox .env files with deterministic fakes.27133 npm3MIT
- FlicenseAqualityDmaintenanceEncrypted token store for Claude Code sessions, providing MCP tools for secure secret management with macOS Keychain integration, per-project allowlists, and native dialog input.656 npm6-
- AlicenseNot gradedqualityDmaintenanceEnables AI agents to securely manage API keys and secrets via the MCP protocol, with encrypted storage at rest and a simple CLI and Python SDK.1MIT