Spec Driven Development
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Description from the maker (original English)
Headless benchmarks for digital sovereignty, scored on Innovation, Control and Scale.
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.
You need
Which app do you use?
Pick your app above. We remember it, so next time the button says “Install in …”.
Works in Claude on the web, desktop and mobile:
https://graph.sovrnti.io/mcpRun this in your terminal
claude mcp add --transport http graph https://graph.sovrnti.io/mcpPaste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json
{
"mcpServers": {
"graph": {
"url": "https://graph.sovrnti.io/mcp"
}
}
}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.
Paste into .vscode/mcp.json in your project
{
"servers": {
"graph": {
"type": "http",
"url": "https://graph.sovrnti.io/mcp"
}
}
}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.
ChatGPT connects only to servers on the internet:
https://graph.sovrnti.io/mcpMenu names can differ slightly by plan and over time.
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.
We have not read this server’s tool list yet; we check endpoints in rotation.
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 6, 2026
The registry name was verified against the domain sovrnti.io (the registry checks domain ownership)
We have not read this repo from GitHub yet
We have not read this repo from GitHub yet
Not checked yet; we check endpoints in rotation
Not checked yet; we check endpoints in rotation
Not checked yet; we read the tool list when we check the endpoint
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.
The registry does not list a required key, though some servers ask you to sign in on first use.
It runs in the maker’s cloud. Connect over the internet with nothing to install, but what you send passes through the maker’s servers.
The GitHub repo last changed –, and the latest version (1.0.0) reached the registry 30 days ago.
Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. It connects by URL, so apps that accept remote MCP servers work too, such as ChatGPT in developer mode.
In the same category: Spec Driven Development, Remote Desktop Commander, Symantec Cloud DLP AIops
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
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Remote Desktop Commander: use files, terminal and processes on your own computers from any AI app.
Governed Symantec Cloud DLP — 14 MCP tools, read-only with audit.
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.
Compare sovereign products in AI tools you already use. Every product is scored on Innovation, Control and Scale, for your market and your country.
Make the technology decision. Not just the sovereignty argument.
Vendor claims are not easy to compare. A good choice depends on your specific context. And your evidence still has to survive procurement, finance, security and executive scrutiny.
Sovrnti reviews every option through three lenses: Innovation, Control and Scale. We test products beyond contracts and decks, so that trade-offs are out in the open.
Bring benchmark data into the AI tools you already use. Query any market, geography or snapshot on demand.
Ask questions like "who leads this market", "what holds up if sovereignty is non-negotiable" and "how do these 2 products compare". Look at a market head-on (Snapshot), ranked by raw capability (Capability Index), ranked under full sovereignty rules (Sovrnti Max), or as the gap between the two (Delta). Pin any view to a country, a region or the world view.
Every score rests on public, checkable evidence and, where we can, our own hands-on testing.
Three skills guide your AI assistant through common workflows with the Sovrnti tools:
A free Sovrnti account to get started. Discovery tools and snapshots are free; deeper views use credits from your account.
In Claude, add Sovrnti from the directory. Then connect it on the plugin's Connectors tab and sign in with your Sovrnti account.
In any other MCP client, use the server URL https://graph.sovrnti.io/mcp. The quickstart shows each client.
This plugin contains no code. It holds one connector, the Sovrnti MCP server at https://graph.sovrnti.io/mcp, and three skills: written instructions your AI assistant follows when it uses that connector.
When your AI assistant calls a Sovrnti tool, we receive the tool's name, its inputs and your token. We also see the assistant's software name and the connection's IP address. We do not receive your conversation with the assistant. We keep a record of each call (who, which tool, when, the result) and a one-way hash of the inputs. We do not store the inputs themselves. Our tools never return personal data.
The files in this repository are under the MIT License. The Sovrnti service and its data are covered by the Sovrnti Terms.