Skip to main content
Glama
fenhuayue

local-tools-mcp-server

by fenhuayue
OverviewSchemaRelated ServersScoreDiscussions
JavaScript

local-tools-mcp-server

A minimal, production-ready MCP server that gives AI assistants access to local file system tools — file search, directory listing, system info, and file metadata.

Built for WorkBuddy and any MCP-compatible client.

Tools

Tool

Description

localtools_search_files

Search files by name pattern / extension with recursive depth control

localtools_system_info

OS, CPU, memory, uptime, user, Node.js version

localtools_list_directory

List directory contents with pagination and hidden-file toggle

localtools_get_file_info

File/directory metadata + text file preview (first 1000 bytes)

All tools are read-only. No files are ever created, modified, or deleted.

Related MCP server: ab_mcp

Quick Start

Prerequisites

  • Node.js >= 18

  • npm >= 9

Install & Build

git clone https://github.com/YOUR_USERNAME/local-tools-mcp-server.git
cd local-tools-mcp-server
npm install
npm run build

Configure in WorkBuddy

Add to ~/.workbuddy/mcp.json:

{
  "mcpServers": {
    "local-tools": {
      "command": "node",
      "args": ["E:/path/to/local-tools-mcp-server/dist/index.js"]
    }
  }
}

Then activate the connector in WorkBuddy's Connector Management page.

Configure in Claude Desktop

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "local-tools": {
      "command": "node",
      "args": ["/path/to/local-tools-mcp-server/dist/index.js"]
    }
  }
}

Usage Examples

Once connected, the AI can use these tools naturally:

"Search my D drive for all .py files, max depth 5"

"How much free memory does my system have?"

"List the contents of my Downloads folder"

"Get info on C:\projects\config.json"

Project Structure

local-tools-mcp-server/
├── src/
│   └── index.ts          # All 4 tools + server entry point (~730 lines)
├── dist/                 # Compiled JS output (gitignored)
├── package.json
├── tsconfig.json
└── README.md

Tech Stack

  • Runtime: Node.js

  • Language: TypeScript

  • Validation: Zod

  • Protocol: MCP TypeScript SDK

  • Transport: stdio (local process, zero network config)

Security

  • All file system access is read-only

  • Paths are resolved and validated before any operation

  • Permission errors are caught and reported gracefully

  • No external dependencies beyond the MCP SDK and Zod

License

MIT

Available Tools

1 tool
localtools_system_infoGet System InformationA
Read-onlyIdempotent

Retrieve basic system information including OS, CPU, memory, uptime, and user details.

Useful for understanding the environment the AI is running in. All information is read-only and comes from the Node.js os module.

Args:

  • response_format ('markdown' | 'json'): Output format (default: 'markdown')

Returns:

  • OS type, platform, release version

  • CPU model and core count

  • Total and free memory

  • System uptime

  • Current user and home directory

  • Hostname

ParametersJSON Schema
NameRequiredDescriptionDefault
response_formatNoOutput format: 'markdown' for human-readable or 'json' for machine-readablemarkdown

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already indicate readOnlyHint, idempotentHint, and destructiveHint. The description adds explicit detail: 'All information is read-only and comes from the Node.js os module.' This reinforces the annotations and provides source context, though there is no additional behavioral nuance beyond what annotations already cover.

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

Conciseness4/5

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

The description is well-structured with a clear lead sentence, a usage sentence, and separated Args and Returns sections. It is concise without extraneous text, though the Returns section could be slightly more streamlined. It earns a 4 for good structure and front-loading of purpose.

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 simple read-only tool with one optional parameter and no output schema, the description fully covers the return values by listing all expected fields (OS, CPU, memory, etc.). It also explains the source and behavior. There are no gaps given the tool's simplicity.

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

Parameters3/5

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

Schema coverage is 100% with a description for the single parameter. The description repeats the parameter meaning ('Output format: markdown or json') in the Args section. This adds no new meaning beyond the schema, so a baseline of 3 is appropriate.

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 it retrieves basic system information (OS, CPU, memory, etc.) with a specific verb 'Retrieve'. It distinguishes the tool's purpose from any siblings (none present) and covers the full scope of what the tool does.

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

Usage Guidelines4/5

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

The description provides a clear usage context: 'Useful for understanding the environment the AI is running in.' While it doesn't explicitly state when not to use it or list alternatives, there are no sibling tools to compare against, so this is sufficient guidance.

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. Dates show when Glama detected each change.

  1. 1 tool updatev1.0.0
    • First observedlocaltools_system_info
Install Server
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

A4/5.0
Disambiguation5/5

With only one tool, there is no ambiguity. The tool's purpose is clearly defined.

Naming Consistency5/5

Single tool name is consistent with itself, using a clear snake_case pattern. No inconsistency to evaluate.

Tool Count2/5

The server name 'local-tools-mcp-server' implies multiple tools, but only one is provided. This feels thin for the apparent scope.

Completeness2/5

The single tool covers basic system info, but the domain of 'local tools' is much broader. Obvious gaps exist (e.g., file operations, process management).

Maintenance

ActivitySlowing
ResponsivenessSyncing

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

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

Related MCP Connectors

Related MCP Servers

  • local-mcp

    fan-67
    A
    license
    Not graded
    quality
    C
    maintenance
    A lightweight, stdio-based MCP server enabling AI assistants to perform local file system operations like reading, writing, searching, and executing commands.
    5,122
    MIT

  • ab_mcp

    AvinashBhargav
    A
    license
    A
    quality
    C
    maintenance
    A file system MCP server that confines AI assistant file tools to a single folder, with read-only by default and optional write access.
    7
    MIT

  • mcp-readonly-code-server

    John0615
    F
    license
    B
    quality
    C
    maintenance
    A read-only MCP server that exposes a local code workspace to AI clients via stdio, providing file browsing and text search capabilities with path safety rules.
    1
    -

  • TimeVerse Code Reader

    elimyliu
    A
    license
    Not graded
    quality
    B
    maintenance
    A read-only MCP server for code reading with intelligent caching, line-range selection, and language detection, enabling AI assistants to efficiently and safely explore file systems.
    MIT

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/fenhuayue/local-tools-mcp-server'

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