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)
Query a curated YAML semantic concept graph for codebase invariants and cross-cutting facts.
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": {
"koncept": {
"command": "npx",
"args": [
"-y",
"@yourtechtribe-labs/koncept-mcp-server"
]
}
}
}Run this in your terminal
claude mcp add koncept -- npx -y @yourtechtribe-labs/koncept-mcp-serverPaste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json
{
"mcpServers": {
"koncept": {
"command": "npx",
"args": [
"-y",
"@yourtechtribe-labs/koncept-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.
Paste into .vscode/mcp.json in your project
{
"servers": {
"koncept": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@yourtechtribe-labs/koncept-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.
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 yourtechtribe-labs, 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 (0.2.0-alpha.7) reached the registry 4 months 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.
Semantic concept graph MCP server for codebases — what your code means, not just what it does.
Code graphs (Aider repomap, GitNexus, Sourcegraph) capture structural relations: who imports who, who calls who. They miss semantic invariants — the cross-cutting concepts that live in code not related by imports:
SectorAssignment.sector keys exactly"koncepto is the curated semantic layer. Concepts in YAML, queryable via MCP tools, read at Step 0 before editing.
Pre-alpha (v0.1.0-alpha.3 on npm). Schema and tool surface may break before 0.1.0 final. See roadmap.
Dogfooded against this repo itself: 5 concepts in .koncept/concepts/ cover the schema, the registry, the MCP tool contract, the monorepo shape, and the kebab-id naming convention. pnpm dogfood = koncepto verify against its own registry.
# Install in your project
pnpm add -D @yourtechtribe-labs/koncept-cli@alpha
npx koncepto init
$EDITOR .koncept/concepts/my-concept.yaml
npx koncepto verify
claude mcp add --scope user koncepto -- \ npx -y @yourtechtribe-labs/koncept-mcp-server@alpha "$PWD"
An invariant is advisory by default — surfaced to agents via koncept_for_file, but never evaluated. Give it a check and it becomes an enforced gate that koncepto verify fails on:
invariants:
if, it must also match then over: { role: writer } if: "BankingCacheService" then: "CacheInvalidationService|on_full_sync"
Static kinds (implication, symbol_present, forbidden, grep) run on koncepto verify by default (fast, read-only; --no-checks to skip). The shell escape hatch (kind: command) runs only on koncepto check. This turns a "completion-contract" concept into both the checklist and its enforcement gate — the loose end can't be skipped under momentum.
3 packages under pnpm workspace:
@yourtechtribe-labs/koncept-core — Zod schema, YAML parser, indexer@yourtechtribe-labs/koncept-mcp-server — MCP stdio server (4 tools)@yourtechtribe-labs/koncept-cli — init, verify, list, linkMIT — see LICENSE.