Spec Driven Development
by formulahendry
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Runs on your computer★ 440MITUpdated 14 months ago
Install
Safehold
Overview
Description from the maker (original English)
Local, encrypted MCP vault for passports, IDs, visas and photos. You control access.
PopNx MCP’s three pillars
These three are never merged into one score: opinions, measurements and popularity are different things.
- User voiceiNo reviews yetReviews open together with accounts in a later step
- Our basic checksi1 of 1 passedChecked from public information; code not scanned yet
- UsageiNot measured yet★ –
What you can do with it
We have not written a plain-language summary for this one yet. Below are the facts we read from the registry.
- Connection: Runs on your computer
- Transport: stdio
- Category: Other
Install
Pick the AI app you use, then copy the settings.
Before you install
- Basic checks: 1 of 1 passed
- Runs on your computer with your user’s permissions (files, network, apps).
- The registry lists no key to fill in.
You need
- npmNode.js installed (for the npx command)
Which app do you use?
Pick your app above. We remember it, so next time the button says “Install in …”.
Open Claude Desktop → Settings → Developer → Edit Config, and paste this into claude_desktop_config.json
{
"mcpServers": {
"safehold": {
"command": "npx",
"args": [
"-y",
"safehold"
]
}
}
}Run this in your terminal
claude mcp add safehold -- npx -y safeholdOr copy the settings yourself
Paste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json
{
"mcpServers": {
"safehold": {
"command": "npx",
"args": [
"-y",
"safehold"
]
}
}
}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.
Or copy the settings yourself
Paste into .vscode/mcp.json in your project
{
"servers": {
"safehold": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"safehold"
]
}
}
}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.
These settings are generated from the maker’s registry entry. If the README says otherwise, follow the README.
What it can do
Runs on your computer; the tool list appears in your AI app after you install it.
Basic checksi
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 7, 2026
- ✓ Pass
Maker matches the repo
The registry name was verified with the GitHub account Spacetime-Technology, which owns the repo
- … Not checked yet
Still maintained
We have not read this repo from GitHub yet
- … Not checked yet
Has a licence
We have not read this repo from GitHub yet
- – Not applicable
Endpoint responds
This one runs on your computer; there is no internet endpoint
- – Not applicable
Sign-in with OAuth
Runs on your computer and uses local settings instead
- … Not checked yet
No hidden instructions in tool descriptions
Runs on your computer; we can only read tool lists from internet endpoints
Compared with others in Otheri
- More stars than 0% of the other 32680 servers in this category
- Published to the registry more recently than 9% of the other 32680 servers in this category
- Basic checks equal to or better than 100% of the other 32680 servers in this category
Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.
Common questions
Is Safehold safe?
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.
What keys or codes does it need?
The registry does not list a required key, though some servers ask you to sign in on first use.
Does it run on my computer or in the cloud?
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).
Is it still maintained?
The GitHub repo last changed –, and the latest version (1.2.0) reached the registry 6 months ago.
Which apps can use it?
Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. You also need Node.js on your computer.
What can I use instead?
In the same category: Spec Driven Development, Remote Desktop Commander, EmbeddedCI BenchPod
Alternatives
Servers in the same category from other makers, sorted by stars.
Reading a card:★ GitHub starsiThree pillars: reviews · checks · usageiUpdated = latest version published to the registryi
Remote Desktop Commander
by desktop-commander
Remote Desktop Commander: use files, terminal and processes on your own computers from any AI app.
Runs in the cloud★ 211Updated 2 days ago
Install
EmbeddedCI BenchPod
by embeddedci-com
Drive a BenchPod hardware-in-the-loop bench: power, flash, UART, I2C, CAN, analog and logic.
Runs on your computerUpdated today
Install
README from the maker
Open the README
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.
Safehold
Your identity documents, on your machine, shared only when you say so.
What it is
Safehold is a local MCP server that stores passports, visas, driving licences, and other identity documents. When an AI agent needs your passport number to book a flight, it asks Safehold. You see what's being requested and why, then approve or deny. Nothing leaves your device.
Why it exists
Your identity data is scattered across dozens of services you don't control: banks, airlines, government portals, SaaS products. Each one holds a copy and decides for itself how to store it, whether to sell it, and how long it'll stick around. AI agents make this worse. Anything an agent can access, every API it touches can reach too.
Safehold is the alternative. The agent gets a field value. You get a consent prompt instead of a privacy policy. Your files stay where they are.
Open source, so none of this requires trust.
What it isn't
A few things that get confused with safehold but solve a different problem.
1Password, Bitwarden, op CLI
You can stuff a passport into 1Password. The op CLI can read specific fields. There's even an official 1Password MCP server now. So yes, parts of this overlap.
What's different is the trust model. Once your 1Password vault is unlocked, anything with that session can read anything in it. No per-field consent, no "why are you asking for this?" prompt. The vault is built for humans typing passwords, not for agents pulling structured fields with a stated reason.
Safehold gates each field individually, every time, with a purpose attached.
Browser autofill, Apple Passwords, iCloud Keychain
Works fine if your agent is a browser filling a form. Doesn't help when it isn't. Agents working over APIs, CLI tools, or other MCP servers never see the autofill layer, so you end up copy-pasting from a passwords app into a chat anyway. Safehold gives a non-browser agent a way to request a passport number without that detour.
Apple Wallet, Google Wallet, government digital ID apps
Locked to the platform. Apple Wallet won't hand your boarding pass to a third-party agent. mDL pilots and the EU eIDAS wallet are issuer-controlled and narrow in scope. None of them speak MCP, and none will let an agent on your laptop request a field from your driving licence.
Pasting it into the chat
People do this. They drop their passport number into a system prompt, or type it into a message and trust the agent to handle it. The number then lives in chat history, gets shipped to the model provider, and sticks around in their logs. You also have no record of which agent used it for what.
Safehold keeps the document on disk, encrypted, and only releases the one field the agent asked for. Nothing extra ends up in the conversation.
A plain JSON file plus the filesystem MCP
Tempting if you're a developer. ~/identity.json plus the filesystem MCP is three lines of config and done. It also gives every other agent on the box the same access, with no encryption at rest, no logging, and no consent step. The first time that file shows up in a backup or a screen share, you have a problem.
Persona, Stripe Identity, Onfido, Plaid
KYC vendors. You send them your documents, they store them, and partner services query them on your behalf. The model assumes you don't hold the keys. Safehold takes the other direction: documents stay on your machine and you approve every release.
HashiCorp Vault, AWS Secrets Manager, Doppler, Infisical
Built for service secrets, not personal identity. No human-facing consent flow, no schema for documents, and operationally heavy for someone who just wants their passport readable by an agent on their laptop.
How it works
Safehold runs as a stdio MCP server. Documents go into ~/.safehold/vault/ as individual encrypted files. Every retrieval is logged to ~/.safehold/access-log.enc.
Encryption is XChaCha20-Poly1305 via @noble/ciphers, audited by Cure53, no external dependencies. On first run a 32-byte key is written to ~/.safehold/master.key (mode 0600).
Other MCP clients can request specific fields from your documents. You control what gets shared, every time.
Tools (v1)
| Tool | Description |
|---|---|
add_document | Add a document to the vault |
list_documents | List stored documents (metadata only) |
update_document | Update fields on an existing document |
delete_document | Permanently delete a document |
get_passport | Retrieve specific fields from a passport |
get_national_id | Retrieve specific fields from a national ID |
get_driving_license | Retrieve specific fields from a driving licence |
get_visa | Retrieve specific fields from a visa |
get_photo | Retrieve a stored photo (passport style, selfie, or signature) |
get_document | Retrieve fields from any document type |
get_access_log | View what was accessed, by which client, and when |
Every retrieval tool accepts a purpose parameter. That purpose is shown to you at consent time so you always know why a field is being requested.
Prompts (v1)
Safehold also ships ready-made workflow prompts. These show up as slash commands in MCP clients (Claude Desktop, Cursor, Claude Code, Zed) so common tasks don't have to be re-prompted from scratch.
| Prompt | Description |
|---|---|
onboard_document | Guided intake to add or update a passport, national ID, driving licence, or visa |
travel_preflight | Check passport and visa validity for an upcoming trip |
selective_share | Share the minimum a service actually needs, with an explicit consent purpose |
expiry_audit | Surface anything expiring soon (metadata only, no consent prompts) |
Prompts don't access your data themselves. They tell the calling agent which Safehold tools to call, in what order, and with what purpose. Every retrieval still goes through the normal consent flow.
Skills
safehold-skills is a companion package of Claude Code skills that turn Safehold from a vault into finished workflows: airline check-in, ESTA applications, KYC forms, and so on. Each skill pairs Safehold with a browser MCP and asks for fields one at a time with a precise purpose string.
npx safehold-skills installQuick Install
Requires Node.js >=20. No build step.
Most clients use the same JSON config — just the file path differs:
{"mcpServers": { "safehold": { "command": "npx", "args": ["-y", "safehold@latest"] } } }
| Client | Config file |
|---|---|
| Claude Desktop (macOS) | ~/Library/Application Support/Claude/claude_desktop_config.json |
| Claude Desktop (Windows) | %APPDATA%\Claude\claude_desktop_config.json |
| Cursor (project) | .cursor/mcp.json |
| Cursor (global) | ~/.cursor/mcp.json |
| Windsurf | ~/.codeium/windsurf/mcp_config.json |
| Amazon Q Developer (global) | ~/.aws/amazonq/mcp.json |
| Amazon Q Developer (project) | .amazonq/mcp.json |
Clients with slightly different config formats:
Claude Code (CLI)
claude mcp add safehold npx -- -y safehold@latestVS Code (GitHub Copilot) — uses "servers" key, enable Agent mode in Copilot Chat. Edit .vscode/mcp.json (project) or ~/Library/Application Support/Code/User/mcp.json (global, macOS):
{"servers": { "safehold": { "command": "npx", "args": ["-y", "safehold@latest"] } } }
Zed — uses "context_servers" key in ~/.config/zed/settings.json:
{"context_servers": { "safehold": { "command": "npx", "args": ["-y", "safehold@latest"] } } }
OpenAI Codex CLI — TOML format in ~/.codex/config.toml:
[mcp_servers.safehold]command = "npx" args = ["-y", "safehold@latest"]
Continue.dev — create .continue/mcpServers/safehold.json (enable Agent mode):
{"command": "npx", "args": ["-y", "safehold@latest"] }
Hermes (Nous Research) — YAML format in ~/.hermes/config.yaml:
mcp_servers:safehold: command: npx args: ["-y", "safehold@latest"]
OpenClaw — uses "servers" key in ~/.openclaw/mcp.json:
{"servers": { "safehold": { "command": "npx", "args": ["-y", "safehold@latest"] } } }
Roadmap
get_travel_authorization- ESTA, eTA, UK ETA, and similarget_vaccination_certificate- international vaccination recordsget_residency_permit- BRP, Green Card, and equivalentsget_birth_certificateget_tax_id- NI number, SSN, TFN, and equivalentsget_proof_of_address- utility bills, bank lettersget_travel_insurance
Development
npm installnpm test # run tests npm run typecheck # type check npm run build # compile to dist/ npm run dev # run directly with tsx (no build step)
Releasing
npm version patch # bug fix (0.1.0 → 0.1.1)npm version minor # feature (0.1.0 → 0.2.0) npm version major # breaking (0.1.0 → 1.0.0)
Checks that you're on a clean, up-to-date main branch, bumps the version, commits, tags, and pushes. CI publishes to npm.