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
Ten
Overview
Description from the maker (original English)
Ten formal algebra for machine intelligence — encode, decode, compose, and verify
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
- PyPIPython’s uv installed (for the uvx 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": {
"ten": {
"command": "uvx",
"args": [
"ten-mcp-server"
]
}
}
}Run this in your terminal
claude mcp add ten -- uvx ten-mcp-serverOr copy the settings yourself
Paste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json
{
"mcpServers": {
"ten": {
"command": "uvx",
"args": [
"ten-mcp-server"
]
}
}
}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": {
"ten": {
"type": "stdio",
"command": "uvx",
"args": [
"ten-mcp-server"
]
}
}
}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 6, 2026
- ✓ Pass
Maker matches the repo
The registry name was verified with the GitHub account johnbeans, 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 32417 servers in this category
- Published to the registry more recently than 5% of the other 32417 servers in this category
- Basic checks equal to or better than 100% of the other 32417 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 Ten 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 (0.1.0) reached the registry 7 months ago.
Which apps can use it?
Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. You also need Python (uv) on your computer.
What can I use instead?
In the same category: Spec Driven Development, Remote Desktop Commander, FOGA node
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 yesterday
Install
FOGA node
by garyyang-finchip
A Finch OG Agent cell as an MCP server: read the world, dry-run and take ERC-8414 tenders by policy.
Computer or cloudUpdated 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.
Ten
A formal algebra for machine intelligence communication
Ten is a language designed for machines, not people.
It is a formal algebra whose messages can be composed, projected, filtered, sorted, and verified through mathematical operations — not parsed through natural language understanding. Ten is not human-readable by design.
The problem: AI agents today communicate using natural language or JSON stuffed into protocols like MCP and A2A. This works, but it's profoundly wasteful. Every receiving AI must parse ambiguous text, infer intent, and guess at priority. Sorting a thousand messages by urgency requires parsing all of them.
Ten's answer: A mathematically rigorous message algebra where urgency is a sortable scalar in a fixed-position header, where two messages can be composed into a valid third message, where trust is a computable property of the message itself, and where the language continuously optimizes its own encoding based on real usage patterns.
The Most Important Thing
Ten makes a strong claim: that a formal algebra beats the status quo (natural language + LLM inference, or JSON + custom code) for machine-to-machine communication at scale. Proving this claim transparently — with measured token counts, dollar costs, latency, variance data, and honest accounting of where Ten loses — is the project's primary goal.
The status quo is not weak. LLMs are cheap and getting cheaper. JSON is universal and well-tooled. Ten must earn its place with data, not assertions. The validation plan designs industry-specific stress tests (derivatives portfolios, international supply chains, clinical trials), measures everything, and includes an adversarial comparison against JSON + domain code to isolate what Ten specifically contributes beyond "a schema that domain code reads from."
If Ten's advantages turn out to be narrow, the project will say so. Intellectual honesty is more valuable than marketing.
Key Ideas
Fixed algebra, unbounded vocabulary. The composition rules never change. The vocabulary evolves continuously as AIs discover what they need to say. New concepts are compositions of existing primitives — never breaking changes.
Variable-resolution encoding. Say "medium urgency" in one bit, or "urgency 9537/10000" in fourteen bits. Pay only for the precision you need.
Slang. The most common compound concepts automatically earn short encodings. "Encrypted, private, minimal detail, verified source" becomes a single token. Slang composes algebraically — unlike human idioms.
Self-evolving. A built-in evolution mechanism (Ten Canonica) collects usage telemetry, detects equivalent constructs, and publishes optimized canonical forms. Ten provably converges toward the Shannon limit on AI-to-AI communication efficiency.
Not a protocol — a language. Ten rides *inside* existing protocols (MCP, A2A, ACP) as the payload encoding. It completes them rather than competing with them.
Documentation
- [TEN-SPEC.md](TEN-SPEC.md) — The founding specification. Start here.
- [VALIDATION.md](VALIDATION.md) — Industry stress tests, token economics, and the honest case for (and against) Ten.
- [ROADMAP.md](ROADMAP.md) — Implementation plan. Validation is the critical gate.
- [WHY-TEN.md](WHY-TEN.md) — Elevator pitches for every audience, from platform engineers to type theorists.
- [ARCHITECTURE.md](ARCHITECTURE.md) — Technical architecture: C core, Python wrappers, memory model, performance targets.
Status
libten (C core) is implemented and passing all 49 tests — 6 kernel types, 6 composition operations, facet vectors, recursive validation, arena allocation. Next: binary serialization, Python bindings, MCP server, then the validation phase that determines whether Ten's claims hold up under measurement.
Open Research Problems
- Kernel minimality and sufficiency — Is the proposed type kernel minimal? Is it sufficient to express all necessary concepts?
- Convergence proofs — Does the evolution mechanism provably converge toward optimal encoding?
- Composition complexity — What are the computational bounds on each algebraic operation?
- Slang theory — When should a compound concept earn a dedicated short token?
The Name
Ten = Token + Attention ("Attention Is All You Need"). Also evokes base-ten: a small set of symbols from which all quantities compose.
Contributing
This project is in its earliest stage. If you work in formal language theory, abstract algebra, information theory, protocol design, or AI agent systems — or if you just find this interesting — open an issue or start a discussion. The specification is the starting point, not the final word.
License
Apache 2.0 — see LICENSE.
Website: tenlang.org Ten Canonica: tencanonica.org