Skip to main content
Glama

mcp-avangenio-services

npm version CI License: MIT

MCP server (stdio transport) that exposes the status of Avangenio's services. It downloads the plain text published at https://status.avangenio.com/data.txt, parses it, and returns it as normalized JSON.

Tool

avangenio_get_status

Takes no arguments. Returns the current status with normalized values (booleans and numbers) plus a raw object with the original pairs exactly as they arrive from the source.

{
  "lastUpdate": "Tue Aug  4 07:30:01 CDT 2026",
  "internetStatus": "OK",
  "internetOk": true,
  "bandwidthMbps": 31.8,
  "batteryPercent": 21,
  "electricalServiceOk": false,
  "raw": {
    "Ultima actualizacion": "Tue Aug  4 07:30:01 CDT 2026",
    "Internet Status": "OK",
    "Ancho de Banda por Usuario": "31.80 Mbps",
    "Estado de las baterías": "21.00%",
    "Servicio Eléctrico Estatal": "NO"
  }
}

Any missing or uninterpretable field is returned as null; unknown keys are kept only in raw, so the tool does not break if the source adds new lines.

Related MCP server: Red Hat Status MCP Server

Installation

The server is published to npm, so you don't need to clone or build anything — point your MCP client at it with npx and it will be downloaded on first use.

Claude Code

Add it with the CLI:

claude mcp add avangenio -- npx -y mcp-avangenio-services

Or add it manually to your .mcp.json:

{
  "mcpServers": {
    "avangenio": {
      "command": "npx",
      "args": ["-y", "mcp-avangenio-services"]
    }
  }
}

Claude Desktop

Edit claude_desktop_config.json (Settings → Developer → Edit Config):

{
  "mcpServers": {
    "avangenio": {
      "command": "npx",
      "args": ["-y", "mcp-avangenio-services"]
    }
  }
}

Then restart Claude Desktop.

Other MCP clients

Any stdio-capable MCP client works. Use:

  • command: npx

  • args: ["-y", "mcp-avangenio-services"]

Global install (optional)

If you prefer a fixed binary instead of npx:

npm install -g mcp-avangenio-services

The command is then available as mcp-avangenio-services, so your MCP config becomes "command": "mcp-avangenio-services" with no args.

Requirements

  • Node.js 18 or higher (uses native fetch and AbortSignal.timeout).

  • Network access to the status endpoint. The panel may be IP-restricted on the server (nginx); if you get a 403 error, run the MCP from a network with allowed access to status.avangenio.com.

Try it out

Launch the MCP Inspector against the published package and call avangenio_get_status:

npx @modelcontextprotocol/inspector npx -y mcp-avangenio-services

Development

Built with TypeScript + @modelcontextprotocol/sdk over stdio, bundled with tsdown, tested with Vitest, and managed with pnpm. It mirrors the structure and conventions of mcp-server-redmine.

git clone https://github.com/jesusr00/mcp-avangenio-services.git
cd mcp-avangenio-services
pnpm install
pnpm build          # generates dist/index.mjs (ESM) and dist/index.js (CJS)

To run your local build from an MCP client, point it at the built entry point:

{
  "mcpServers": {
    "avangenio": {
      "command": "node",
      "args": ["/absolute/path/to/mcp-avangenio-services/dist/index.mjs"]
    }
  }
}

Scripts

pnpm dev            # build in watch mode
pnpm test           # tests (Vitest)
pnpm test:coverage
pnpm typecheck      # tsc --noEmit
pnpm lint           # eslint (zero warnings)
pnpm format         # prettier --write

Structure

src/
├── index.ts                 # entry: McpServer + StdioServerTransport
├── client/avangenio.ts      # downloads the data.txt
├── tools/
│   ├── index.ts             # registerAllTools
│   ├── shared.ts            # ok / err / withErrorHandling
│   └── status/
│       ├── definition.ts    # tool metadata
│       ├── index.ts         # server registration
│       ├── parse.ts         # pure parser (text -> AvangenioStatus)
│       ├── schema.ts        # input schema (zod)
│       └── status.ts        # handler
└── types/                   # ToolResult, AvangenioStatus

Contributing

Contributions are welcome! Please read CONTRIBUTING.md for the development workflow and guidelines. To report a vulnerability, follow SECURITY.md.

License

MIT

Available Tools

1 tool
avangenio_get_statusA
Read-only

Gets the current status of Avangenio's services (Internet, bandwidth per user, battery level, and state electrical service), read from https://status.avangenio.com/data.txt. Returns JSON with normalized values (booleans and numbers) plus a 'raw' object with the original pairs. Takes no arguments.

ParametersJSON Schema
NameRequiredDescriptionDefault

No parameters

TDQS

A4.3/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint and openWorldHint, so the description only needs to add extra context. It does that by revealing it reads from an external URL and returns both normalized and raw data. This adds non-obvious behavioral details beyond the annotations, though it doesn't describe potential errors or rate limits.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, front-loaded with a specific verb and resource, and no filler. Every sentence provides meaningful information about input, output, and data source.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a parameterless read-only tool with no output schema, the description covers the essential context: what it reads, from where, and what the return structure looks like. It is complete enough for an agent to invoke it and understand the result.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool has zero parameters and the description explicitly states 'Takes no arguments,' which is consistent with the empty schema. Since there are no parameters to clarify, the baseline 4 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool 'Gets the current status of Avangenio's services' and enumerates the specific service types (Internet, bandwidth, battery level, electrical service). It also names the data source URL. With no siblings, it fully disambiguates the tool's function.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage for retrieving service status but does not explicitly state when to use it vs alternatives. Since there are no sibling tools, this is less critical, but the absence of explicit 'when-to-use' direction keeps it at a minimum viable level.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

  1. 1 tool updatev0.1.1
    • First observedavangenio_get_status

TDQS

A4.4/5.0

Scored across 1 tool

Disambiguation5/5

Only one tool exists, so there is no possibility of confusing it with another tool. The single tool has a clear, specific purpose.

Naming Consistency4/5

The tool name follows a clear verb_noun pattern ('avangenio_get_status'), but with only one tool there is no broader pattern to evaluate. Still, the name is descriptive and consistent with common MCP conventions.

Tool Count4/5

A single tool is minimal but fully appropriate for the narrow scope of retrieving service status. It feels slightly thin compared to richer servers, but the count matches the stated purpose without being wasteful.

Completeness5/5

The tool covers all aspects of the described purpose: internet status, bandwidth, battery, and electrical state. Returns both normalized and raw values, so no obvious gaps in the domain.

Maintenance

ActivitySlowing
ResponsivenessNo issues

Related MCP Connectors

Related MCP Servers