GitHub
GitHub’s official server lets AI read and manage code, issues and pull requests in your account. Use GitHub’s hosted version or run it locally with Docker.
Description from the maker (original English)
Encrypted local vault for API keys. Your AI fetches keys on demand and scans code for leaks.
These three are never merged into one score: opinions, measurements and popularity are different things.
We have not written a plain-language summary for this one yet. Below are the facts we read from the registry.
Pick the AI app you use, then copy the settings.
VAULT_MASTER_PASSWORD, VAULT_HOMEValues marked secret are keys to your account. Never share them or paste them into a chat.
Which app do you use?
Pick your app above. We remember it, so next time the button says “Install in …”.
Download the maker’s .mcpb file
The link goes to the maker’s own file; we do not host or repackage it. Open the file and Claude Desktop installs it.
Run this in your terminal
Fill in the empty values before running it.
Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
This one runs on your computer, and ChatGPT can only connect to servers on the internet. Pick another app.
Your choice stays on this device in a cookie; no account needed.
VAULT_HOME envThese settings are generated from the maker’s registry entry. If the README says otherwise, follow the README.
Runs on your computer; the tool list appears in your AI app after you install it.
We check information anyone can see; we have not read the code. Checks that do not apply are left out of the count. · Checked Nov 8, 2026
The registry name was verified with the GitHub account marstudio360, which owns the repo
We have not read this repo from GitHub yet
We have not read this repo from GitHub yet
This one runs on your computer; there is no internet endpoint
Runs on your computer and uses local settings instead
Runs on your computer; we can only read tool lists from internet endpoints
Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.
It passed 1 of 1 applicable basic checks. We have not read the code. Before adding a key or token, see what access the server asks for and use a key with only the permissions you need.
You need to fill in: VAULT_MASTER_PASSWORD
It runs on your computer. Your AI app starts it when needed, and data does not pass through the maker’s servers (unless it calls an online service itself).
The GitHub repo last changed –, and the latest version (1.1.1) reached the registry 33 days ago.
Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. You also need MCPB on your computer.
In the same category: GitHub, Desktop Commander, Cloudflare MCP
Servers in the same category from other makers, sorted by stars.
Reading a card:↓ Downloads per weeki★ GitHub starsiThree pillars: reviews · checks · usageiUpdated = latest version published to the registryi
GitHub’s official server lets AI read and manage code, issues and pull requests in your account. Use GitHub’s hosted version or run it locally with Docker.
MCP server for terminal commands, file operations, and process management
Copied from the maker’s repo as written. PopNx MCP has not reviewed or endorsed it. HTML, images and scripts are removed. Links lead off this site.
Encrypted local vault for API keys. Your AI fetches keys on demand and scans code for leaks.
Vault keeps every API key, token and password in one encrypted file on your machine (Fernet, with the key derived from your master password by scrypt). The master password is read from your system keyring, or from VAULT_MASTER_PASSWORD on machines with no keyring. Your AI searches the vault and fetches the exact key it needs when it needs it, so keys stop getting pasted into chats. It exports an entry as .env lines, tracks rotation dates, keeps a usage log, ships entry templates for common services, and scans a project folder for keys left in plain text, reporting file and line.
A desktop window (vault_ui.py) and a terminal CLI (vault_core.py) open the same vault with no AI involved. There is no password reset: lose the master password and the file stays unreadable.
Homepage: https://vibedna.ai/store/vault
| Tool | What it does |
|---|---|
credential_exists(name) | Check whether an entry exists before asking the user for a key |
get_credential(name, key) | Return one field of one entry |
list_credentials() | Entry names, categories and field names. No values |
search_credentials(term) | Search by name, category or notes |
add_credential(name, category, fields, notes) | Add an entry (fields is a JSON object) |
edit_credential(name, fields) | Update fields; an empty value removes that field |
delete_credential(name, confirm) | Delete an entry (confirm must equal the name) |
export_env(name) | The entry's fields as KEY=value lines |
add_with_template(service, name, fields, notes) | Add an entry from a service template |
list_templates() | The available templates |
scan_for_leaks(path) | Scan a folder for plaintext keys: your vault's values plus known key patterns |
leak_history() | Recent leak-scan results |
check_rotation_due(days) | Entries not rotated in days |
mark_rotated(name) | Record a rotation |
usage_log(name) | Recent credential-access events |
backup_vault() | Copy the encrypted file to the backup folder |
check_for_update() | Compare this copy with the published version |
git clone https://github.com/marstudio360/vibedna-vault-mcp
cd vibedna-vault-mcp python -m venv .venv
pip install -r requirements.txt python vault_core.py init
Store the master password in your system keyring once, so the MCP server can open the vault:
python -c "import keyring; keyring.set_password('vibedna-vault','master', input('master password: '))"
claude mcp add vault --scope user -- /absolute/path/to/vibedna-vault-mcp/.venv/bin/python /absolute/path/to/vibedna-vault-mcp/server.py
Or in a project's .mcp.json:
{
"mcpServers": { "vault": { "command": "/absolute/path/to/vibedna-vault-mcp/.venv/bin/python", "args": ["/absolute/path/to/vibedna-vault-mcp/server.py"] } } }
On Windows the interpreter is .venv\Scripts\python.exe.
Add the same mcpServers block to ~/.cursor/mcp.json (all projects) or .cursor/mcp.json (one project).
Add the same mcpServers block to claude_desktop_config.json (Settings > Developer > Edit Config), then restart Claude Desktop.
INSTALL.md is a step-by-step guide written so you can paste it into an AI chat and let the AI do the install. It also covers the desktop window and the CLI.
| Variable | Default | What it does |
|---|---|---|
VAULT_HOME | ~/.vibedna-vault | Folder of the encrypted vault file (vault.enc) |
VAULT_MASTER_PASSWORD | (unset) | Master password for machines with no system keyring |
VAULT_BACKUP_HOME | ~/.vibedna-vault/backups | Where backup_vault writes copies (the last 30 are kept) |
The usage log and leak-scan results are written next to the vault file, in logs/.
The vault, the window and the CLI make no network calls. check_for_update is the one tool that does: it asks https://vibedna.ai/api/mcp/latest for the published version number.
MIT, see LICENSE. Copyright (c) 2026 VibeDNA.
Support: admin@vibedna.ai