Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Ping Host MCP ping google.com to check connectivity"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Servidor MCP minimo para usar desde VS Code Chat con una sola tool: ping_host.
Este proyecto vive fuera del repo prueba_skills, pero el workspace de prueba_skills lo referencia mediante .vscode/mcp.json. Asi puedes seguir en este prompt y dejar que el host de chat descubra la herramienta.
Related MCP server: Code MCP Server
ping_host: hace ping a un host o IP indicado por el usuario.
npm installnpm startNota: al ser un servidor MCP por stdio, no debes escribir logs a stdout. Si necesitas depurar, usa stderr.
Una vez que VS Code cargue el servidor MCP del workspace, deberias poder pedir algo como:
Usa la herramienta ping_host para hacer ping a 8.8.8.8o
Hace ping a github.com con 2 intentosLa tool usa execFile, no shell, para evitar inyeccion de comandos.
El host se valida como nombre de host o IP simple.
El numero de intentos se limita a un rango chico.
En Windows usa ping -n; en Unix usa ping -c.
Hace ping a un host o direccion IP usando el comando del sistema.
| Name | Required | Description | Default |
|---|---|---|---|
| host | Yes | ||
| count | No | ||
| timeoutMs | No |
| Name | Required | Description |
|---|---|---|
| ok | Yes | |
| command | Yes | |
| stdout | Yes | |
| stderr | Yes | |
| message | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true and idempotentHint=true, indicating safe, repeatable operations. The description adds that it uses system commands, which provides useful context about implementation, but doesn't disclose additional behavioral traits like execution time, error conditions, or output format.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, efficient sentence that directly states the tool's function without unnecessary words. It's appropriately sized and front-loaded with the core action.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's low complexity (simple ping operation), rich annotations (readOnlyHint, idempotentHint), and existence of an output schema, the description is reasonably complete. It could benefit from more behavioral context, but the structured fields cover most needs.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
With 0% schema description coverage, the description doesn't add any parameter-specific information beyond what the schema provides (host, count, timeoutMs). However, the schema fully documents parameters with types, constraints, and defaults, so the baseline 3 is appropriate as the schema carries the burden.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('Hace ping') and target ('a un host o direccion IP'), specifying it uses system commands. It's specific about what the tool does, though it doesn't need to distinguish from siblings since none exist.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives or in what context it's appropriate. The description only states what it does, not when it should be used.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v0.1.0ping_hostScored across 1 tool
With only one tool, there is no possibility of ambiguity or overlap between tools. The tool 'ping_host' has a clearly defined and singular purpose.
There is only one tool, so naming consistency is inherently perfect. The tool name 'ping_host' follows a clear verb_noun pattern.
A single tool is generally too few for most server purposes, making the set feel thin and potentially incomplete. For a 'Ping Host MCP', one tool might suffice, but it limits functionality and could indicate a narrow scope.
The tool 'ping_host' covers the basic action implied by the server name, but there are notable gaps. For example, no tools for checking multiple hosts, setting ping parameters, or handling network diagnostics beyond a simple ping.
Security scanner for MCP servers. Detect vulnerabilities, prompt injection, and tool poisoning.
Official IPinfo MCP Server - IP intelligence tools for AI assistants
A simple MCP server built with FastMCP and python
