Skip to main content
Glama
Sign In
Shellagent MCP Server

Shellagent MCP Server

by myshell-joe
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Hybrid

shellagent-mcp MCP Server

NPM Downloads

A Model Context Protocol (MCP) server for shellagent-mcp

Requirements

  • Node.js 18 or newer

  • VS Code, Cursor, Windsurf, Claude Desktop or any other MCP client

Getting started

Local (Stdio)

First, install the Commands MCP server with your client. A typical configuration looks like this:

{
  "mcpServers": {
    "shellagent-mcp": {
      "command": "npx",
      "args": [
        "mcp-server-shellagent-mcp@latest"
      ]
    }
  }
}

You can also install the shellagent-mcp MCP server using the VS Code CLI:

# For VS Code
code --add-mcp '{"name":"shellagent-mcp","command":"npx","args":["mcp-server-shellagent-mcp@latest"]}'

After installation, the Commands MCP server will be available for use with your GitHub Copilot agent in VS Code.

Go to Cursor Settings -> MCP -> Add new MCP Server. Name to your liking, npx mcp-server-shellagent-mcp. You can also verify config or add command like arguments via clicking Edit.

{
  "mcpServers": {
    "shellagent-mcp": {
      "command": "npx",
      "args": [
        "mcp-server-shellagent-mcp@latest"
      ]
    }
  }
}

Follow Windsuff MCP documentation. Use following configuration:

{
  "mcpServers": {
    "shellagent-mcp": {
      "command": "npx",
      "args": [
        "mcp-server-shellagent-mcp@latest"
      ]
    }
  }
}

Follow the MCP install guide, use following configuration:

{
  "mcpServers": {
    "shellagent-mcp": {
      "command": "npx",
      "args": [
        "mcp-server-shellagent-mcp@latest"
      ]
    }
  }
}

Remote (SSE / Streamable HTTP)

At the same time, use --port $your_port arg to start the browser mcp can be converted into SSE and Streamable HTTP Server.

# normal run remote mcp server
npx mcp-server-shellagent-mcp --port 8089

You can use one of the two MCP Server remote endpoint:

  • Streamable HTTP(Recommended): http://127.0.0.1::8089/mcp

  • SSE: http://127.0.0.1::8089/sse

And then in MCP client config, set the url to the SSE endpoint:

{
  "mcpServers": {
    "shellagent-mcp": {
      "url": "http://127.0.0.1::8089/sse"
    }
  }
}

url to the Streamable HTTP:

{
  "mcpServers": {
    "shellagent-mcp": {
      "type": "streamable-http", // If there is MCP Client support
      "url": "http://127.0.0.1::8089/mcp"
    }
  }
}

In-memory call

If your MCP Client is developed based on JavaScript / TypeScript, you can directly use in-process calls to avoid requiring your users to install the command-line interface to use Commands MCP.

import { Client } from '@modelcontextprotocol/sdk/client/index.js';
import { InMemoryTransport } from '@modelcontextprotocol/sdk/inMemory.js';

// type: module project usage
import { createServer } from 'mcp-server-shellagent-mcp';
// commonjs project usage
// const { createServer } = await import('@agent-infra/mcp-server-commands')

const client = new Client(
  {
    name: 'test commands client',
    version: '1.0',
  },
  {
    capabilities: {},
  },
);

const server = createServer();
const [clientTransport, serverTransport] = InMemoryTransport.createLinkedPair();

await Promise.all([
  client.connect(clientTransport),
  server.connect(serverTransport),
]);

// list tools
const result = await client.listTools();
console.log(result);

// call tool
const toolResult = await client.callTool({
  name: 'test_tool',
  arguments: {
    hello: 'hello'
  },
});
console.log(toolResult);

Developement

Access http://127.0.0.1:6274/:

npm run dev

Available Tools

1 tool
get_app_infoC

Get application information using app_id

Inputs: app_id (required).

Tool Schema Changelog

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

Loading tool schema changelog…

    Deploy Server
    One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

    TDQS

    B3/5.0

    Scored across 1 tool

    Disambiguation5/5

    With only one tool, there is no possibility for confusion or overlap between tools. The tool 'get_app_info' has a clear, singular purpose that cannot be misselected against other tools.

    Naming Consistency5/5

    Since there is only one tool, naming consistency is inherently perfect. The tool name 'get_app_info' follows a clear verb_noun pattern, and there are no other tools to compare it against for inconsistency.

    Tool Count2/5

    A single tool is too few for a server named 'Shellagent MCP Server', which suggests a broader scope related to shell operations or agent management. This minimal toolset feels thin and incomplete for such a domain, limiting functionality significantly.

    Completeness1/5

    The tool surface is severely incomplete. For a shell agent server, obvious gaps include basic operations like executing commands, listing processes, managing files, or interacting with the system. The single tool 'get_app_info' does not cover the expected domain at all, leading to dead ends for agents.

    Resources

    Related MCP Connectors

    Related MCP Servers