Securecode

io.github.juanisidoroPublished by GitHub account juanisidorov0.15.2Updated Oct 24, 2026

Secrets vault for Claude Code with audit logs, access rules, and AES-256 encryption.

VerifiedSTDIODesktop onlyDeveloper ToolsSecurity & Monitoring

Overview

AI-generated overview

Local MCP server that lets Claude Code use secrets from an encrypted SecureCode vault without exposing their values in chat.

What you can do
  • Set up the vault and import secrets: guided onboarding, .env import through a secure web window, and .env or CSV export
  • Create, read, update, delete and renew secrets, and list them with tags and expiry status
  • Control access sessions: wake a scoped session, check remaining time, lock it, or wipe injected files from disk
  • Inspect access rules, run post-setup security checks, and check plan, usage and server version
When to use it
Useful when an assistant needs API keys, tokens or passwords for a project but you do not want the raw values to appear in the conversation. Suited to developers who want audited, rule-governed secret access from Claude Code on their own machine.
Requirements
Runs locally over stdio, typically via npx, and needs Node.js 18 or newer. Requires a SecureCodeHQ account (free tier: 50 secrets, 10K accesses per month) and device approval on first use from each machine. No environment variables or headers are declared.
Before you install
The server handles real credentials: API keys, tokens and passwords. With reveal set to true, a secret value is returned to the AI, so use inject mode unless necessary. Secret values are written to local files on your machine and removed on sleep, byebye or process exit. Access is logged with AI model, IP, machine identity and timestamp, and rules can email on access. Creating, updating, deleting and exporting secrets change stored data.

Installation

In SourceWeft

  1. Open Securecode in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

@securecode/mcp-server

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

[SecureCode MCP server]

Quick Start

bash
claude mcp add securecode -- npx -y @securecode/mcp-server

Then tell Claude Code:

Set up SecureCode in this project

The onboard tool walks you through account creation, secret import, and configuration. Takes about 2 minutes.

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

ToolWhat it does
onboardGuided setup: signup, import, API key, config, SDK
get-secretGet a secret (injected to file by default, reveal: true to show to AI)
list-secretsList all secrets with tags and expiry status
create-secretCreate a new secret
update-secretUpdate value, description, or tags
delete-secretDelete a secret
renew-secretRenew expired secrets or change TTL
import-envImport .env via secure web window (values never pass through AI)
export-envExport secrets as .env or CSV
get-statusCheck plan, usage, and MCP server version
wake-sessionUnlock session with optional scope and auto-sleep timer
sleep-sessionLock session and clean injected files
session-statusCheck session state and time remaining
byebyeLock session + clean all secrets from disk
get-active-rulesList active MCP access rules (read-only)
security-checkPost-setup security hardening checks
helpDocs: 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.

ActionEffect
Block AlwaysSecret only accessible from the dashboard
Require ConfirmationAgent must acknowledge before accessing
Require SessionRequires active session (wake-session)
Block ModelsOnly allows specific AI models
NotifySends 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: true returns 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:

bash
npm install @securecode/sdk
typescript
import { loadEnv } from '@securecode/sdk';await loadEnv(); // all secrets loaded into process.env

SDK on npm

Links

Requirements

  • Node.js >= 18
  • A SecureCodeHQ account (free tier: 50 secrets, 10K accesses/month)

License

MIT

Source: README.md at commit 0fe1cc1

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v0.15.2LatestSep 16, 2026

Score

50% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts