Admin MCP server
io.github.hellocoop/admin-mcp·v1.5.7·4 starsModel Context Protocol (MCP) for Hellō Admin API.
4 stars38 downloads/wk
Reviews
Write oneNobody has reviewed Admin yet.
If you have run it, two minutes of your experience saves the next person an afternoon.
Admin tools (1)
write = sends, deletes, buys or postsRead from the package source without running it. The installed server may list more.
hello_manage_appManage Hellō applications - create, read, update, create secrets, and upload logos
Public scan report
scanner v0.1.10 · 2026-10-01 · same rubric, same numbers if you re-run it
- Code scan26 source files scanned25/25
- –Live reliabilityno gateway calls yet and no remote to proben/a
- –Tool poisoningtools not inspected (local package is not executed); not countedn/a
- Auth qualitylocal package, no credentials required12/15
- Maintenancelast push 25 days ago15/15
- Maintainer identityregistry namespace matches repository owner; GitHub account older than a year9/10
How Admin compares
Against every graded AI and agents MCP server, from our own scans and uptime checks. Updated after each scan run.
- Safety score
- 94/100
- higher than 96% of 4,460 AI and agents servers
- Tools
- 1
- the typical AI and agents server has 6
- Tools that change things
- 0%
- typical: 0%. Fewer write tools means less an agent can break
- GitHub stars
- 4
- more than 77% of 2,711 AI and agents servers
- Downloads a week
- 38
- more than 30% of 1,538 AI and agents servers with a package
What its tools let an agent do: 1 read
Install Admin in Claude Code, Cursor or VS Code
Runs npx -y @hellocoop/admin-mcp on your machine. Read the scan report first; the gateway never runs local packages.
claude mcp add admin-mcp -- npx -y @hellocoop/admin-mcp
What the publisher says
From the Admin repository's README, as published. We do not edit it. Read it on GitHub
@hellocoop/admin-mcp (BETA)
Model Context Protocol (MCP) server for creating and managing Hellō applications.
🚧 BETA Status: This MCP server is currently in beta. We're actively seeking feedback and welcome contributions! Please report issues, suggest improvements, or submit pull requests to help us improve the developer experience.
Quick Install
📖 Full Documentation & Installation Guide
Quick Configuration
Copy one of these configurations into your MCP client settings:
NPM Package (Latest):
{
"hello-admin-stdio": {
"command": "npx",
"args": ["-y", "@hellocoop/admin-mcp@latest"],
"type": "stdio"
}
}HTTP Transport (Remote):
{
"hello-admin-http": {
"url": "https://admin-mcp.hello.coop/",
"type": "http"
}
}📖 See Local Development Setup for running from source
Usage
This MCP server provides a single powerful tool (hellomanageapp) that lets you create and manage your Hellō applications directly from your AI assistant. Unlike traditional APIs, every operation automatically includes your complete developer context - profile, teams, and applications - making it perfect for AI assistants.
📖 For detailed usage instructions, examples, and troubleshooting, visit: hello.dev/docs/admin-mcp
Features
- 🏢 Context-Aware Operations: Every tool call automatically includes your current developer profile, teams, and applications for seamless context
- 📱 Unified Application Management: Single powerful tool for all app operations (create, read, update, secrets, logos)
- 🔐 Secure OAuth Integration: Browser-based authentication with JWT token validation
- 🌐 Multi-Transport Support: Works with both stdio (local) and HTTP (remote) MCP transports
- 📊 Built-in Analytics: Usage tracking and performance monitoring for optimization
- 🎨 Logo Management: Upload logos with automatic light/dark theme support
- ⚙️ Environment Flexibility: Configurable domains and admin servers
Available Tools
🎯 Core Tool:
- hellomanageapp - The main tool for all application management
- Actions: create, read, update, createsecret, updatelogofromdata, updatelogofrom_url
- Always includes: Your current profile, teams, and applications in every response
- Auto-context: Automatically uses your default team if none specified
- Smart defaults: Generates app names from your profile if not provided
Key Benefits
🔄 Always In Context: Unlike traditional APIs, every tool response includes your complete developer context:
- Your user profile (name, email, picture)
- All your teams/organizations with roles
- All your applications with team associations
- Current team and application state
This means you never lose context between operations - perfect for AI assistants that need to understand your complete development environment.
Tool Actions & Response Structure
hellomanageapp Actions:
📝 create - Create new applications
- Auto-generates team if none exists
- Creates smart default names from your profile
- Returns: { profile, application, action_result }
👁️ read - Read application details
- Without client_id: Returns your complete profile context
- With client_id: Returns profile + specific application
- Returns: { profile, application?, action_result }
✏️ update - Update application settings
- Modify any application property
- Returns: { profile, application, action_result }
🔑 createsecret** - Generate client secrets
- Creates secure OAuth client secrets
- Returns: { profile, application, clientsecret, actionresult }
Shortened. The full README is on GitHub.
Nothing above is checked by us. What we check is on the safety report.
Admin: common questions
- Is Admin MCP server safe?
- Yes, by our scan: it is graded A (94/100). Read the Admin safety report
- How do I install Admin?
- It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
- Does Admin need an API key?
- Not as far as the registry entry and our scan can tell: no credentials are declared or required.
- Is Admin maintained?
- The last commit was 59 days ago (2026-09-06). The latest release is v1.5.7.
- How does Admin compare with other AI and agents MCP servers?
- safety score 94/100 (higher than 96% of 4,460 AI and agents servers); tools 1 (the typical AI and agents server has 6); tools that change things 0% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.