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)
Compile your own business capabilities from declarative YAML and serve them as MCP tools.
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 …”.
Open Claude Desktop → Settings → Developer → Edit Config, and paste this into claude_desktop_config.json
{
"mcpServers": {
"archstone": {
"command": "npx",
"args": [
"-y",
"@archstone/cli",
"serve"
]
}
}
}Run this in your terminal
claude mcp add archstone -- npx -y @archstone/cli serveThis one needs values on its command line, so copy the settings and fill them in.
Paste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json
{
"mcpServers": {
"archstone": {
"command": "npx",
"args": [
"-y",
"@archstone/cli",
"serve"
]
}
}
}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 needs values on its command line, so copy the settings and fill them in.
Paste into .vscode/mcp.json in your project
{
"servers": {
"archstone": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@archstone/cli",
"serve"
]
}
}
}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.
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 7, 2026
The registry name was verified with the GitHub account Archstone-Romania, 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.
The registry does not list a required key, though some servers ask you to sign in on first use.
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 (0.26.0) reached the registry 38 days ago.
Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. You also need Node.js 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:★ 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
Cloudflare MCP servers
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.
A compiler for AI capabilities. Describe what your business can do once, in business terms. Archstone compiles it into tools an AI agent can discover and call — MCP today, other protocols as they arrive. Nobody hand-writes integration code.
Open source, Apache-2.0.
| I want to… | Go to |
|---|---|
| See it working in 60 seconds | Try it |
| Generate a manifest from my OpenAPI spec | Start from an API you already have |
| Install the CLI and know what each command does | Install · Commands |
| Understand the model (CDL → IR → tools) | How it works |
| Call capabilities from my own agent loop | Embed it |
| Know what Archstone guarantees | Guarantees |
| Learn the language | CDL specification · glossary |
| Walk through it end to end | Onboarding guide |
| Know what is free and what is sold | Open source and commercial |
| Contribute | Contributing |
A capability compiled by Archstone is running live:
https://demo.archstone.dev/mcp
claude mcp add --transport http archstone-tourism https://demo.archstone.dev/mcp
The read-only tools need no key. The demo's booking tools do; its two public keys are listed in the showcase. To send one, add the server with the header after the name and URL (--header takes every word that follows it, so placed earlier it swallows them):
claude mcp add --transport http archstone-tourism https://demo.archstone.dev/mcp \
--header "Authorization: Bearer "
The whole integration behind it is 12 lines of business YAML — no HTTP, no JSON Schema, no MCP SDK. Everything else was generated.
Want this in front of your own systems? hello@archstone.dev.
archstone init openapi.yaml --out manifest --company acme --domain catalog
init drafts a manifest from an OpenAPI document, asks you what no spec can answer, and writes nothing unless the result compiles.
Details: onboarding → archstone init. The spec in the recording is examples/demo/stays-openapi.yaml.
npm install -g @archstone/cli # or: npx @archstone/cli <command>
Node 22+. Your manifest lives in your own repository; the CLI is a stateless compiler that needs no checkout of this one (why).
| Command | What it does |
|---|---|
archstone init | Draft a manifest from an OpenAPI document (or, with --source postgres --dsn-env , from a Postgres catalog) |
archstone apply | Validate and compile to IR; --exposure lists what a model sees and what it never sees, and which capabilities are exposed, unlisted or not exposed (retired, unbound) |
archstone build | Write a portable IR artifact for embedding |
archstone serve | Serve MCP tools over stdio; --http --token for HTTP |
archstone verify | Replay recorded fixtures against the live backend and report drift; --json for CI |
archstone doctor | Offline pre-production checklist |
archstone adopt | Declare a field the backend started returning (interactive) |
archstone record | Record a contract: for an existing manifest's read bindings, one live request each (interactive); --rerecord replaces one |
archstone audit | Read back the execution audit trail |
apply also warns about what an irreversible capability still lacks — here, removing its declared failures adds a warning, and restoring them clears it:
Each command is covered in the onboarding guide. Working from a checkout of this repository instead? Use pnpm apply, pnpm serve, … — see contributor onboarding.
capabilities.yaml → *.capability.yaml → bindings/*.binding.yaml
(what the company (each capability: (how a capability maps offers — the index) business shape only) to a real backend)
└──────── archstone apply ────────┘ └── archstone serve ──┘ parse → validate → compile → IR emit MCP tools → agent
Change the protocol and you regenerate instead of rewriting. Change the backend and the CDL does not move. A worked example: examples/manifests/booking/.
No MCP server process needed — load a built IR with @archstone/agent:
import { fromIR } from "@archstone/agent";
const archstone = fromIR(compiledIR); const tools = archstone.tools("anthropic"); // or "openai-chat", "openai-responses", "gemini", "json-schema" const result = await archstone.execute("tourism.search", { location: "Paris" });
A mountable Streamable-HTTP MCP handler is available at @archstone/agent/mcp. Full API: packages/agent.
These are ratified decisions, not implementation details — each links to its reasoning.
| Guarantee | Decision |
|---|---|
| A provider field your manifest does not declare never reaches a model | ADR-0008 |
| A field a model invents never reaches your system | ADR-0011 |
build and serve never need a network call, an account or a key | ADR-0005 |
| No feature that is free today becomes paid | ADR-0005 |
| Ranking in any selection Archstone performs is not for sale | ADR-0006 |
effect (read / write / irreversible) is confirmed by a person, never inferred | Onboarding |
All decision records: docs/adr/.
[ArtVinci](https://artvinci.ro), a custom-framing business, answers customer questions through a capability compiled by Archstone — real catalog, prices computed live by their own backend. Case study.
The first MCP server is an afternoon's work. The fifth — ChatGPT, Gemini and whatever ships next, each shaped slightly differently, all on top of an API that keeps changing — is the real cost. Archstone is a compiler that, in its first release, generates an MCP server, so that maintenance does not multiply with every new protocol.
Everything needed to turn a manifest into something an agent can call — language, compiler, IR, emitters, embedded SDK and CLI — is Apache-2.0 and stays that way. What we will sell is *operating* it for you: hosted audit retention, managed rate limits, drift monitoring and multi-tenant hosting. See ADR-0005.
| Topic | Where |
|---|---|
| Onboarding (providers, embedders, contributors) | docs/ONBOARDING.md |
| CDL specification (normative, 1.0, frozen) | docs/cdl-specification.md |
| Why CDL looks the way it does | RFC-0002 |
| Machine schema | cdl.schema.json |
| Glossary | docs/glossary.md |
| Identity and principals | docs/IDENTITY.md |
| Architecture decisions | docs/adr/ |
A Postgres database as a backend (sql connector) | docs/guides/sql-connector.md |
| End-to-end demo with Claude | examples/demo/README.md |
| Supported versions | SUPPORT.md |
| Reporting a vulnerability | SECURITY.md — never a public issue |
| Changes | CHANGELOG.md |
packages/
schema/ load and shape-validate manifests (cdl.schema.json) compiler/ semantic validation, lowering to IR emitter-support/ shared substrate for every emitter runtime/ registry, MCP emitter and transport, verify agent/ embedded SDK init/ OpenAPI → manifest drafting cli/ the archstone command providers/ rest/ sql/ backend adapters examples/ manifests and the Claude demo docs/ spec, ADRs, RFCs, onboarding
Archstone is written with substantial AI assistance — Anthropic's Claude, through Claude Code — for implementation, tests and documentation. The decisions are not generated: every structural choice is an ADR, argued and ratified by an accountable person before the code, and a patch nobody can explain does not merge. Commits with generated code name the model in their co-authorship trailer. What we ask of contributors: CONTRIBUTING.md.
CONTRIBUTING.md and the contributor onboarding. Node 22+, pnpm 11+; pnpm typecheck && pnpm test green before you open a PR.
Copyright 2026 NousVigil LLC. Licensed under Apache-2.0; see also NOTICE.