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)
Deploy full-stack apps with databases, storage, backups, logs, scaling, and rollback. 74 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 …”.
Works in Claude on the web, desktop and mobile:
https://mcp.nexusai.run/mcpRun this in your terminal
claude mcp add --transport http nexus-ai https://mcp.nexusai.run/mcpPaste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json
{
"mcpServers": {
"nexus-ai": {
"url": "https://mcp.nexusai.run/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": {
"nexus-ai": {
"type": "http",
"url": "https://mcp.nexusai.run/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://mcp.nexusai.run/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 8, 2026
The registry name was verified with the GitHub account nexusrun, which owns the repo
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 (1.1.0) reached the registry 44 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: 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.
The AI creation platform. Describe an app, watch it build, preview and share it, then deploy the full stack to production. Your AI agent runs the rest.
NEXUS AI is an agentic AI app builder and deployment platform. You describe what you want in plain words, and NEXUS AI builds it, verifies it, shows you a live preview you can share or remix, and deploys it when you're ready.
Every deploy ships the whole stack, already connected: app code, Postgres, MySQL, Mongo or Redis, S3-compatible buckets, persistent volumes, background workers, and encrypted backups, plus Stripe payments when your app needs them. Run it on NEXUS AI managed infrastructure or in your own AWS, Google Cloud, or Azure account.
It also includes standalone managed databases, an AI Gateway for routing model traffic, and 74 MCP tools, so Claude, Cursor, Codex, or any MCP-compatible agent can build, deploy, scale, back up, restore, query the database, and roll back without leaving the chat or IDE.
The problem it solves. AI tools like Claude Code, Cursor, v0, Bolt, Lovable, and Replit can generate working application code in minutes. Getting that code into production still requires the rest of a real stack: a database, a queue, storage, secrets, scaling, health checks, backups, rollbacks. NEXUS AI is the deploy layer that closes that gap and exposes every operation to the agent that wrote the code.
In one sentence. Describe what you want to build, preview it live, ship to a public HTTPS URL with Postgres + Redis + S3 in 5 minutes, then let your AI agent operate the stack on your behalf.
Four equivalent ways to get the same app running. Pick one or use all of them.
PROMPT
Tell Claude in chat: "Deploy this repo with Postgres, Redis, and a bucket called user-uploads." → The agent calls nexusai_deploy_source + nexusai_bucket_create
REPO nexus deploy source \ --repo https://github.com/you/my-app.git \ --framework python \ --services postgresql,redis \ --bucket user-uploads --wait
BUILDER Describe the app at https://nexusai.run/builder. Watch it render in a live preview, edit the code or click an element to change it, then press Deploy. Same pipeline as the CLI.
DASHBOARD Click through the same operations at https://nexusai.run/app. Same engine, same result.
After deploy, the agent (or you) operates the running stack: stream logs, scale replicas, snapshot the database, restore from backup, run a sandboxed SQL query, apply an AI-proposed schema fix, roll back to a previous release. Every action is an MCP tool, a CLI command, and a dashboard button.
Chat-driven app builder with a live, sandboxed preview. Generates React apps and full-stack Next.js + Prisma apps, including an auto-provisioned managed Postgres database and built-in email/password auth. The preview self-heals (up to two automatic AI fix attempts on build errors), and a "Fix with AI" action repairs a failed deploy and redeploys against the same database. Also included:
nexusai_builder_push sends files generated in Claude, Cursor, or ChatGPT into the builder for a free instant preview, and nexusai_builder_pull reads edits backPostgres, MySQL, Mongo, Redis, S3-compatible buckets, persistent volumes, background workers, and your app code. Wired together by one nexus deploy and live at a public HTTPS URL in 5 minutes. Framework detection covers FastAPI, Flask, Django, Express, Next.js, Rails, Laravel, Symfony, PHP, Ruby, Go, Java, and any container.
74 MCP tools cover the full lifecycle. Connect the NEXUS AI MCP server (https://mcp.nexusai.run/mcp) to Claude Desktop, Claude Code, Cursor, Codex, or any MCP client. The same agent that generated the code can deploy, scale, back up, restore, query the database, and roll back. Listed on the official MCP Registry at io.github.nexusrun/nexus-ai.
Org-scoped volumes that survive container restarts, redeploys, and host reboots. Multi-attach S3-compatible buckets backed by MinIO, each with its own scoped IAM service account (not platform-wide root credentials). Per-bucket credential rotation, signed download URLs (30 seconds to 1 hour TTL), streaming uploads.
Databases are their own resource, not part of an app. Create PostgreSQL or Redis on NEXUS AI (--local), or PostgreSQL and MySQL on AWS RDS, Google Cloud SQL, or Azure Database. Set your own database name, username, and password, attach to any deployment (env vars are injected on the next deploy, REDIS_URL for Redis), detach without losing data, and snapshot or restore into a new database. Private cloud databases are reached through an in-VPC/VNet proxy, so they are never exposed publicly. Run SQL from the CLI (nexus managed-db query shop "SELECT ..."), the dashboard, or MCP. Redeploying or deleting an app leaves the database untouched.
An OpenAI- and Anthropic-compatible gateway (/v1, /v1/messages) with failover and routing, virtual model aliases, caching, budgets and rate limits, usage and cost tracking, guardrails, audit logs, and an MCP gateway that aggregates servers behind one endpoint. Provider keys stay in the gateway. Supports Anthropic, OpenAI, Google Gemini, xAI Grok, OpenRouter, and any OpenAI-compatible endpoint. Self-hostable on NEXUS AI. nexusai.run/ai-gateway
Connect external Postgres, MySQL, or Mongo databases. Inspect schemas (cached for 5 minutes). Preview queries with EXPLAIN + safety analysis. Execute sandboxed SELECT statements with statement timeouts and row caps. Apply AI-proposed DDL fixes generated from runtime error logs (with review and audit).
Scheduled or on-demand backups for Postgres (pg_dump), MySQL (mysqldump), Mongo (mongodump), and Redis (BGSAVE). Encrypted at rest. Scheduled backups default to 7-day retention and prune automatically (configurable, never below 7 days). Download via short-lived signed URLs (TTL 30s to 1h) or restore directly. Cross-deployment restore (seed staging from production) supported.
Soft stop preserves containers, networks, volumes, and the port reservation so the next start brings everything back. Boot reconciliation restarts deployments the host reboot did not bring back. Versioned rollback in seconds. Replica count preserved across restart.
Dashboard, CLI (nexus deploy), or MCP tool call from your agent. Same engine, same result. Switch between them in the same project without anything getting out of sync.
Full-stack deploys run on the NEXUS AI managed Container platform with org-level isolation. Single-container apps can also target AWS App Runner, Google Cloud Run, or Azure Container Apps from the same dashboard, CLI, or MCP call.
Streaming build and runtime logs over WebSocket. Health checks with configurable endpoints. Tail logs directly from your agent (nexusai_deploy_logs) to triage failures without leaving chat.
AES-256-GCM encryption. Injected at container start, never written to images, never returned over the API, never appear in logs. Scoped per organization and environment with full audit trail on every read, write, and deletion.
Org-level roles (Owner, Admin, Developer). Per-org isolated runtime, networks, volumes, and S3 buckets. SAML / OIDC SSO available on Enterprise. Independently scoped and revocable API tokens with fine-grained OAuth scopes (deployments:read, db:admin, managed_db:manage, volumes:manage, buckets:manage, etc.) plus four legacy broad scopes preserved for backward compatibility.
Custom domains on Starter and above. Support by plan: community on Free, email and tickets on Starter, plus phone on Pro, dedicated SLA on Enterprise. Agents can open and reply to support tickets over MCP. See the customer support page.
Tenant isolation, encrypted secrets, encrypted backups, scoped per-bucket IAM, full audit logs, customer-owned cloud deployments for Enterprise, BAA available for Healthcare Pro and Enterprise.
| Provider | Type | Plans |
|---|---|---|
| NEXUS AI managed Container platform | Full-stack (app + DB + storage + workers) | All plans |
| AWS App Runner | Single-container | Pro, Healthcare Pro, Enterprise |
| Google Cloud Run | Single-container | Starter+, all plans |
| Azure Container Apps | Single-container | Pro, Healthcare Pro, Enterprise |
| Self-hosted / on-prem | Customer-owned Docker hosts | Enterprise |
Full-stack deploys (app + databases + storage + workers + backups) run on the NEXUS AI managed Container platform. The cloud-provider targets are for single-container apps that do not need the full managed stack.
| Registry | URL |
|---|---|
| Official MCP Registry | io.github.nexusrun/nexus-ai |
| mcp.so | mcp.so/servers/nexusai |
| Smithery | smithery.ai/servers/sali/nexusai |
| mcpservers.org | mcpservers.org/servers/nexusrun/nexusai |
| Glama | glama.ai/mcp/connectors/io.github.nexusrun/nexus-ai |
Install in any MCP client by searching "NEXUS AI" in the client's MCP marketplace, or via the registry URL above.
| Plan | Price | Best For |
|---|
| Free | $0 | Testing, developm
Only the beginning is shown; read the rest in the repo