Skip to main content
Glama
ftezedor

server-hub-mcp

by ftezedor

Server Hub

Server Hub is a Python service that exposes server-management and operational data through two interfaces:

  • REST API, implemented with FastAPI

  • MCP server, providing tools for MCP-aware clients and AI agents

Both interfaces are intended to expose the same underlying application capabilities rather than duplicate business logic.

Architecture

flowchart LR
    RESTClient["REST Client"] --> REST["REST API"]
    MCPClient["MCP Client / AI Agent"] --> MCP["MCP Server"]

    REST --> App["Application Layer"]
    MCP --> App

    App --> Domain["Domain / Models"]
    App --> Persistence["Persistence"]
    Persistence --> DB[("Database")]

REST and MCP are interface boundaries around the application layer. Persistence details remain behind that boundary.

Related MCP server: quads-mcp

MCP tools

The MCP interface exposes:

  • search_servers

  • get_server

  • get_server_metrics

  • get_active_alerts

  • get_system_stats

  • create_alert

The MCP layer maps internal application data into client-oriented responses rather than exposing persistence implementation details.

REST API

The REST interface provides operations for:

  • server discovery and lookup

  • server status

  • server metrics

  • active alerts

  • alert creation

  • system statistics

Testing

Run the complete test suite with:

pytest -q

The repository includes separate tests for the public interfaces and a REST ↔ MCP equivalence suite.

tests/
├── test_api.py
├── test_mcp.py
└── test_rest_mcp_equivalence.py

The REST ↔ MCP equivalence tests verify that the two interfaces expose equivalent capabilities and data without requiring their response envelopes to be identical.

Project structure

app/
├── api/
│   ├── domain/
│   ├── routes/
│   └── ...
├── mcp/
└── ...

tests/
docs/

The implementation is organized around application/domain logic and interface adapters.

Documentation

Additional architecture and decision records can be added under docs/ as the project evolves.

Development

Create a virtual environment, install the project dependencies, and run the tests:

python -m venv .venv
source .venv/bin/activate
pip install -e ".[test]"
pytest -q

The repository also contains scripts/components for running the REST and MCP services locally.

Design principles

  • Keep application behavior independent from transport protocols.

  • Treat REST and MCP as interface adapters.

  • Keep persistence details behind the application boundary.

  • Prefer meaningful domain identifiers in MCP-facing operations.

  • Test public interfaces and their semantic equivalence.

License

No license is specified in the current project materials.

F
license - not found
Not graded
quality - not tested
C
maintenance

Maintenance

Maintainers
Response time
Release cycle
Releases (12mo)
Commit activity

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Servers

  • A
    license
    Not graded
    quality
    B
    maintenance
    Provides comprehensive monitoring and observability for MCP server ecosystems with real-time health checks, performance metrics, distributed tracing, anomaly detection, and automated performance reports using OpenTelemetry and Prometheus.
    1
    MIT
  • A
    license
    Not graded
    quality
    D
    maintenance
    MCP server for interacting with QUADS infrastructure systems via API, enabling resource management and automation through LLM applications.
    MIT
  • F
    license
    Not graded
    quality
    C
    maintenance
    Exposes DevOps/SRE operations like Kubernetes pod status, Prometheus metrics queries, and deploy history as tools for MCP-compatible clients.

View all related MCP servers

Related MCP Connectors

  • Personal assistant MCP server with search, execute, packages, jobs, secrets, and integrations.

  • MCP server for AI access to Swagger by SmartBear.

  • MCP server exposing the Backtest360 engine API as tools for AI agents.

View all MCP Connectors

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/ftezedor/server-hub-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server