NEXUS AI

by nexusrun

209 downloads

Not rated

GitHub

About

The NEXUS AI MCP server exposes the full deployment platform as Model Context Protocol tools. Connect it to Claude Desktop, Claude Code, Cursor, Codex CLI, or any MCP-compatible client and your AI agent can deploy applications, attach databases and storage, run backups, restore d

Details

Author: nexusrun
Downloads: 209
Categories: Cloud Service, Infrastructure, Database, Other, Developer Tools

Setting up with Highlight

This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:

Download and install Highlight from highlightai.com/download
Navigate to the plugins tab and select "Add Custom Plugin"
Configure the plugin with the settings below

Plugin Name NEXUS AI

Command (node, npx, python, etc.)

Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
Enable "Start Automatically" if you want the plugin to start when Highlight launches

Setting up with Cursor

Open Cursor's settings
Navigate to the MCP section
Click "Add new Global MCP server"
Copy and paste the configuration below based on your operating system

JSON

{
    "mcpServers": {
        "nexus ai": {
            "nexus-ai": {
                "url": "https://api.zollo.livemcp",
                "headers": {
                    "Authorization": "Bearer <your-nexus-token>"
                }
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "nexus ai": {
            "nexus-ai": {
                "url": "https://api.zollo.livemcp",
                "headers": {
                    "Authorization": "Bearer <your-nexus-token>"
                }
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "nexus ai": {
            "nexus-ai": {
                "url": "https://api.zollo.livemcp",
                "headers": {
                    "Authorization": "Bearer <your-nexus-token>"
                }
            }
        }
    }
}

Setting up with Claude Desktop

Open Claude Desktop's settings
Go to the Integrations tab
Click "Add MCP Server"
Use the configuration below based on your operating system

Note: Make sure Claude Desktop is running before attempting to connect.

JSON

{
    "mcpServers": {
        "nexus ai": {
            "nexus-ai": {
                "url": "https://api.zollo.livemcp",
                "headers": {
                    "Authorization": "Bearer <your-nexus-token>"
                }
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "nexus ai": {
            "nexus-ai": {
                "url": "https://api.zollo.livemcp",
                "headers": {
                    "Authorization": "Bearer <your-nexus-token>"
                }
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "nexus ai": {
            "nexus-ai": {
                "url": "https://api.zollo.livemcp",
                "headers": {
                    "Authorization": "Bearer <your-nexus-token>"
                }
            }
        }
    }
}

Setting up with Windsurf

Open Windsurf's preferences
Go to the Integrations section
Click "Add MCP Integration"
Use the configuration below based on your operating system

JSON

{
    "mcpServers": {
        "nexus ai": {
            "nexus-ai": {
                "url": "https://api.zollo.livemcp",
                "headers": {
                    "Authorization": "Bearer <your-nexus-token>"
                }
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "nexus ai": {
            "nexus-ai": {
                "url": "https://api.zollo.livemcp",
                "headers": {
                    "Authorization": "Bearer <your-nexus-token>"
                }
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "nexus ai": {
            "nexus-ai": {
                "url": "https://api.zollo.livemcp",
                "headers": {
                    "Authorization": "Bearer <your-nexus-token>"
                }
            }
        }
    }
}

Setting up with Cline

Open Cline's settings
Navigate to the Integrations section
Click "Add MCP Server"
Copy and paste the configuration below based on your operating system

Note: Make sure to restart Cline after adding the configuration.

JSON

{
    "mcpServers": {
        "nexus ai": {
            "nexus-ai": {
                "url": "https://api.zollo.livemcp",
                "headers": {
                    "Authorization": "Bearer <your-nexus-token>"
                }
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "nexus ai": {
            "nexus-ai": {
                "url": "https://api.zollo.livemcp",
                "headers": {
                    "Authorization": "Bearer <your-nexus-token>"
                }
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "nexus ai": {
            "nexus-ai": {
                "url": "https://api.zollo.livemcp",
                "headers": {
                    "Authorization": "Bearer <your-nexus-token>"
                }
            }
        }
    }
}

Setting up with Goose

Open Goose's preferences
Go to the Integrations tab
Select "MCP Servers"
Click "Add New Server"
Use the configuration below based on your operating system

JSON

{
    "mcpServers": {
        "nexus ai": {
            "nexus-ai": {
                "url": "https://api.zollo.livemcp",
                "headers": {
                    "Authorization": "Bearer <your-nexus-token>"
                }
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "nexus ai": {
            "nexus-ai": {
                "url": "https://api.zollo.livemcp",
                "headers": {
                    "Authorization": "Bearer <your-nexus-token>"
                }
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "nexus ai": {
            "nexus-ai": {
                "url": "https://api.zollo.livemcp",
                "headers": {
                    "Authorization": "Bearer <your-nexus-token>"
                }
            }
        }
    }
}

From the repository

Connect any MCP-compatible client to the endpoint https://nexusai.run/mcp using HTTPS with Bearer-token authentication. No additional configuration keys are required beyond the token.

Claude Desktop / Cursor

Paste into your MCP client config file to install this server.

{
    "mcpServers": {
        "nexus ai": {
            "nexus-ai": {
                "url": "https://api.zollo.livemcp",
                "headers": {
                    "Authorization": "Bearer <your-nexus-token>"
                }
            }
        }
    }
}

McpServers

{
    "nexus-ai": {
        "url": "https://api.zollo.livemcp",
        "headers": {
            "Authorization": "Bearer <your-nexus-token>"
        }
    }
}

Full-stack application platform. Deploy full-stack apps from a prompt, a repo, or a CLI. Your AI agent runs the rest.

NEXUS AI is anFull-stack application platformthat deploys full-stack containerized applications (app code, Postgres, MySQL, Mongo, Redis, S3-compatible buckets, persistent volumes, background workers, encrypted backups) in about 5 minutes. Every platform action is callable as a Model Context Protocol (MCP) tool, so Claude, Cursor, Codex, or any MCP-compatible agent can 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, ship to a public HTTPS URL with Postgres + Redis + S3 in 5 minutes, then let your AI agent operate the stack on your behalf.

Three equivalent ways to deploy the same app. Pick one or use all three.

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 + nexusai_bucket_attach + nexusai_deploy_redeploy. → Live URL in ~5 minutes. REPO nexus deploy source \ --repo https://github.com/you/my-app.git \ --framework python \ --services postgresql,redis \ --bucket user-uploads --wait 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.

Postgres, MySQL, Mongo, Redis, S3-compatible buckets, persistent volumes, background workers, and your app code. Wired together by onenexus deployand 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.

59 MCP tools cover the full lifecycle. Connect the NEXUS AI MCP server (https://api.zollo.live/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 atio.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.

Connect external Postgres, MySQL, or Mongo databases. Inspect schemas (cached for 5 minutes). Preview queries withEXPLAIN+ 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. 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.

Role-based access control and tenant isolation

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 23 fine-grained OAuth scopes (deployments:read,db:admin,volumes:manage,buckets:manage, etc.) plus four legacy broad scopes preserved for backward compatibility.

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.

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.

Install in any MCP client by searching "NEXUS AI" in the client's MCP marketplace, or via the registry URL above.

- Application Generation Engine
- NEXUS AI managed Container platform (shared runtime)
- 2 concurrent deployments
- Public HTTPS endpoint
- Google Cloud Run single-container deployment target
- Community support

- Everything in Starter
- Multi-cloud single-container deploys (AWS App Runner, Google Cloud Run, Azure Container Apps)
- 5 active deployments, up to 10 concurrent containers
- Versioned deployments + one-click rollback
- Real-time build and runtime observability
- Encrypted secrets vault
- Storage volumes + buckets
- Database backups
- Team access with RBAC
- Email support

- Everything in Pro
- Deploy into customer-owned AWS, Google Cloud, or Azure accounts
- Private build and runtime isolation
- Unlimited deployments and versions
- Advanced audit logs (HIPAA / SOC-ready)
- SSO (SAML / OIDC)
- IP allowlisting and network controls
- Air-gapped and on-premises deployment support
- Dedicated support and SLA

Ship apps generated by Claude Code, Cursor, v0, Bolt, Lovable, or Replit with a real database, real storage, and a real public URL in 5 minutes. Let the same agent that wrote the code operate the deploy.

Expose your platform actions as MCP tools so end-user agents can deploy, operate, and scale on your customers' behalf.

Launch new ideas without spending a week on infrastructure. Stand up new apps with Postgres, Redis, and storage from one command.

Give every internal team a self-service deploy path with audit logs, RBAC, and rollback baked in. No tickets, no glue scripts.

Regulated industries (Healthcare and Fintech)

Deploy into customer-owned cloud infrastructure with HIPAA-aligned controls, full audit trails, tenant isolation, and BAA support.

# macOS curl -fsSL https://nexusai.run/install-mac.sh | bash # Linux curl -fsSL https://nexusai.run/install.sh | bash

2. Deploy a full-stack app from a Git repo

nexus deploy source \ --repo https://github.com/you/my-app.git \ --name my-app \ --provider docker \ --framework python \ --services postgresql,redis \ --start-command "uvicorn app:app --host 0.0.0.0 --port 8000" \ --wait

NEXUS AI builds the container, provisions Postgres + Redis with persistent volumes, opens a public HTTPS URL through Traefik, and starts streaming logs.

nexus bucket create user-uploads nexus bucket attach <bucket-id> <deployment-id> nexus deploy redeploy <deployment-id> --wait

Your app receivesS3_ENDPOINT,S3_BUCKET,S3_ACCESS_KEY,S3_SECRET_KEYas environment variables. Use any S3 SDK against the scoped per-bucket service account.

Connect the NEXUS AI MCP server to Claude Desktop, Claude Code, Cursor, or Codex (https://api.zollo.live/mcp). The agent can then run commands like:

"Take a Postgres backup of my-app, run the migration, and roll back if anything fails."

The agent callsnexusai_db_services_list,nexusai_db_backup, then conditionallynexusai_db_restoreandnexusai_deploy_rollback, all without you opening a terminal.

Full documentation·MCP Server Reference

NEXUS AI exposes a REST API and a full MCP server with59 tools across 9 categories:

OAuth scopes.23 scopes total: 4 legacy broad scopes (deployments:{read,logs,create,delete}) kept for backward compatibility, plus 18 fine-grained scopes (secrets:{read,manage,delete},domains:{read,manage,delete},db:{read,query,admin,source:delete},volumes:{read,manage,delete},buckets:{read,manage,delete},support:{read,write}). Old tokens continue to satisfy fine-grained checks viaSCOPE_SUPERSETS.

Add to~/Library/Application Support/Claude/claude_desktop_config.json(macOS) or%APPDATA%\Claude\claude_desktop_config.json(Windows):

{ "mcpServers": { "nexus-ai": { "url": "https://api.zollo.live/mcp", "headers": { "Authorization": "Bearer <your-nexus-token>" } } } }

claude mcp add nexus-ai \ --url https://api.zollo.live/mcp \ --header "Authorization: Bearer <your-nexus-token>"

Cursor Settings, MCP, Add server with the same URL and Bearer token.

Generate tokens at nexusai.run/app/tokens. Full MCP reference at nexusai.run/docs#mcp-overview.

NEXUS AI is built to keep stateful apps alive across host reboots, backend restarts, and manual stop/start cycles. The reliability layer:

Deep dive:How NEXUS AI keeps your Postgres alive across host reboots.

- Encryption at rest: AES-256-GCM for all secrets, bucket credentials, and sensitive configuration
- Encryption in transit: TLS 1.2+ enforced across all endpoints
- Tenant isolation: per-organization runtime, networks, volumes, and S3 buckets. No shared application runtime or storage between customer organizations.
- Per-bucket IAM: every S3 bucket ships with a scoped MinIO service account, not platform-wide root credentials. Rotatable vianexusai_bucket_rotate_credentials.
- Zero plaintext credentials: Secrets never appear in code, container images, build logs, or runtime logs
- Audit logging: Every action (deployment, secret access, scope use, backup, restore, config change) logged with timestamp, actor identity (user or agent token name), and result
- RBAC + scoped tokens: Role-based access at organization and deployment level, plus 23 fine-grained OAuth scopes for least-privilege automation
- Private runtimes: Enterprise customers run fully isolated build and runtime environments
- IP allowlisting: Network-level access controls for Enterprise deployments

NEXUS AI provides HIPAA-aligned technical safeguards for regulated healthcare environments:

- Infrastructure isolation: Container-level isolation per deployment. No shared runtime between tenants.
- Audit trails: Deployment history, execution logs, change tracking, agent attribution, and user activity visibility
- Secrets management: Runtime injection only. No plaintext credentials in code, images, or logs.
- Customer-owned cloud: Enterprise customers deploy entirely within their own AWS, Google Cloud, or Azure accounts
- Data residency: Choose specific cloud regions for all workloads
- BAA: Business Associate Agreements available for Enterprise and Healthcare Pro customers
- SSO: SAML / OIDC support for Enterprise (satisfies HIPAA workforce access requirements)
- Network controls: IP allowlisting, private networks, and air-gapped environments for Enterprise

Shared responsibility.NEXUS AI provides HIPAA-aligned infrastructure controls and is designed to support customer HIPAA compliance programs. Customers retain responsibility for their overall compliance posture, application logic, data classification, internal policies, and HIPAA program governance.

What is NEXUS AI?NEXUS AI is an MCP-native application platform that deploys full-stack containerized applications (Postgres, MySQL, Mongo, Redis, S3 buckets, persistent volumes, workers, encrypted backups) in 5 minutes. Every platform action is callable as an MCP tool, so Claude, Cursor, Codex, and any MCP-compatible agent can deploy, scale, back up, restore, query the database, and roll back without leaving the chat.

Where can I install the NEXUS AI MCP server?The official MCP Registry lists it atio.github.nexusrun/nexus-ai. Also indexed at mcp.so and Smithery. Direct endpoint:https://api.zollo.live/mcp.

Which AI tools generate apps that NEXUS AI deploys?NEXUS AI deploys from any Git repository. Apps generated by Claude Code, Cursor, v0, Bolt, Lovable, Replit, Windsurf, or any other tool work the same way: push the result to GitHub and runnexus deploy source --repo <url>.

Where do full-stack deploys actually run?Full-stack deploys (app + databases + storage + workers) run on the NEXUS AI managed Container platform with org-level isolation. Single-container deploys can also target AWS App Runner, Google Cloud Run, or Azure Container Apps.

Does NEXUS AI require a DevOps team?No. NEXUS AI is designed so individual developers and small teams can deploy production-grade containerized applications without dedicated DevOps expertise. The platform handles container builds, deployment orchestration, secrets management, health checks, observability, and the database / storage / backup layer.

Can I deploy from a GitHub repository?Yes. NEXUS AI supports deployments from GitHub repositories, container images, local source code, or AI-generated code through the same unified workflow.

Is NEXUS AI HIPAA compliant?NEXUS AI provides HIPAA-aligned technical safeguards including tenant isolation, AES-256-GCM encrypted secrets, encrypted backups, scoped per-bucket IAM, full audit logs, and customer-owned cloud deployments. BAAs are available for Enterprise and Healthcare Pro plans.

Can I use my own cloud account?Yes. Enterprise customers can deploy NEXUS AI entirely within their own AWS, Google Cloud, Azure, or on-premises infrastructure with no data leaving their environment.

How does rollback work?Every deployment is versioned and immutable. You can restore any previous version with a single click from the deployment dashboard, the CLI (nexus deploy rollback), or an MCP call (nexusai_deploy_rollback). No manual re-deployment or downtime required.

What happens to my secrets?Secrets are encrypted with AES-256-GCM and injected at container runtime only. They are never stored in plaintext, never appear in container images, and never appear in build or runtime logs. A full access audit trail is maintained.

What happens to my data if the host reboots?Persistent volumes survive container restarts and host reboots. Boot reconciliation restarts any deployments the reboot did not bring back. Postgres / MySQL / Mongo crash recovery happens via their own journaling on next start. Full deep dive:How NEXUS AI keeps your Postgres alive across host reboots.

How is NEXUS AI different from Vercel, Render, Railway, or Fly.io?NEXUS AI is the only platform that combines (1) full-stack deploys in one command, (2) 59 MCP tools for AI agents to operate the platform end-to-end, (3) AI-powered database schema fixes from runtime logs, (4) per-bucket IAM out of the box, (5) HIPAA-aligned controls with customer-owned cloud deployments. See the comparison table above.

- Your AI app is generated. Now how do you deploy it?. The deploy gap for AI-generated apps and how NEXUS AI closes it.
- MCP-driven deploys: 5 tasks your Claude agent should be running for you. Concrete operations to hand to an agent today.
- From v0 prototype to production database in 5 minutes. Tutorial.
- How NEXUS AI keeps your Postgres alive across host reboots. Reliability deep dive.
- Deploy a full-stack Python app with Postgres, Redis, and workers in 5 minutes. Hands-on FastAPI tutorial.
- Database backup and restore on NEXUS AI. Backup mechanics.

- Support:support@nexusai.run
- Sales:nexusai.run/contact
- LinkedIn:linkedin.com/company/nexusai-run

Navigate your Aiven projects and interact with the PostgreSQL®, Apache Kafka®, ClickHouse® and OpenSearch® services

Manage Aiven cloud services like Kafka, PostgreSQL, and Redis via its API.

Generate and execute AWS CLI commands using natural language.

A natural language interface to manage AWS services like RDS, S3, EC2, and VPC.

Integrate with the Coolify API to manage your servers, applications, and databases.

Deploy production backends, APIs, cron jobs and automations from any AI assistant. Database, auth, storage and 24+ integrations included.

An MCP server for managing databases and services on the Tembo Cloud platform.

Interact with the Neon serverless Postgres platform

Full-stack backend platform MCP — provision apps, manage databases, deploy functions, and more.

Interact with Neon Postgres databases using natural language to manage projects, branches, queries, and migrations via the Neon API.

No reviews yet — be the first

Use Google, GitHub, or an email account so ratings stay tied to real people.

Email sign in

No reviews posted yet.

About

Details

Jump to

Setting up with Highlight

From the repository

Claude Desktop / Cursor

McpServers

Role-based access control and tenant isolation

Regulated industries (Healthcare and Fintech)

2. Deploy a full-stack app from a Git repo

Install

More like this

Aws Kb Retrieval Server

Redis

Sqlite

PostgreSQL

Npx Y convex@latest mcp start

AWS MCP Servers