General-Purpose MCP Tools

v0.3.2Developer Toolsstable

A general-purpose MCP server with utility tools including datetime information, safe math calculations, text statistics, JSON extraction, knowledge base search, and HTTP GET requests. It demonstrates server-side MCP implementation and can be connecte

aiai-agentsgenerative-aillmmcp
Share:
43
Stars
0
Downloads
0
Weekly
0/5

What is General-Purpose MCP Tools?

General-Purpose MCP Tools is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to general-purpose mcp server with utility tools including datetime information, safe math calculations, text statistics, json extraction, knowledge base search, and http get requests. it demonstrates se...

A general-purpose MCP server with utility tools including datetime information, safe math calculations, text statistics, JSON extraction, knowledge base search, and HTTP GET requests. It demonstrates server-side MCP implementation and can be connecte

This server falls under the Developer Tools category on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • A general-purpose MCP server with utility tools including da

Use Cases

Datetime and math utilities
JSON extraction
Knowledge base search
MagarongCandy

Maintainer

LicenseMIT
Languagetypescript
Versionv0.3.2
UpdatedMay 20, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux

Installation

NPM

npx -y mcp-toolz

PIP

pip install mcp-toolz

Manual Installation

npx -y mcp-toolz

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use General-Purpose MCP Tools

The mcp-toolz MCP server is a multi-LLM feedback tool that lets Claude consult ChatGPT, Gemini, and DeepSeek simultaneously through MCP tools. It exposes three tools — ask_chatgpt, ask_gemini, and ask_deepseek — enabling developers to get second and third opinions on code, architecture decisions, and implementation plans directly inside their AI coding workflow. By requiring at least one provider API key, it enables cross-model comparison without switching between different AI interfaces.

Prerequisites

  • Python 3.8 or higher, or Node.js for npx usage
  • At least one API key from: OpenAI (OPENAI_API_KEY), Google (GOOGLE_API_KEY), or DeepSeek (DEEPSEEK_API_KEY)
  • An MCP client such as Claude Desktop or Claude Code
  • pip or uv package manager for installation
1

Install mcp-toolz via pip

Install the mcp-toolz package using pip or uv. This installs the MCP server and its command-line entry point.

pip install mcp-toolz
# or with uv:
uv tool install mcp-toolz
2

Obtain API keys for your desired LLMs

Get API keys for the LLM providers you want to use. You need at least one. OpenAI keys start with sk-, Google API keys come from Google AI Studio, and DeepSeek keys from platform.deepseek.com.

3

Add mcp-toolz to Claude Desktop or Claude Code configuration

Edit your MCP client configuration to add mcp-toolz with your API keys in the env block. Only include keys for providers you have access to.

4

Restart your MCP client

Restart Claude Desktop or reload Claude Code after updating the configuration. The three LLM tools (ask_chatgpt, ask_gemini, ask_deepseek) should now appear.

5

Optionally configure model overrides

Set optional environment variables to pin specific model versions for each provider. The defaults are gpt-5 for OpenAI, gemini-2.0-flash-thinking-exp-01-21 for Google, and deepseek-chat for DeepSeek.

export MCP_TOOLZ_MODEL=gpt-4o
export MCP_TOOLZ_GEMINI_MODEL=gemini-1.5-pro
export MCP_TOOLZ_DEEPSEEK_MODEL=deepseek-coder

General-Purpose MCP Tools Examples

Client configuration

Add mcp-toolz to your Claude Desktop claude_desktop_config.json. Include API keys for each provider you want to enable. All three are optional — only providers with keys will be available.

{
  "mcpServers": {
    "mcp-toolz": {
      "command": "mcp-toolz",
      "env": {
        "OPENAI_API_KEY": "sk-your_openai_key_here",
        "GOOGLE_API_KEY": "your_google_api_key_here",
        "DEEPSEEK_API_KEY": "sk-your_deepseek_key_here"
      }
    }
  }
}

Prompts to try

Use these prompts to get multi-LLM perspectives on your code. Claude will invoke the appropriate ask_* tool and return the other model's response.

- "Ask ChatGPT to review this function for potential bugs"
- "Get Gemini's opinion on whether I should use a microservices or monolith architecture for this use case"
- "Ask DeepSeek to suggest a more efficient algorithm for this sorting implementation"
- "Get all three LLMs to review this API design and summarize their consensus"
- "Ask ChatGPT and Gemini whether this SQL query could have a race condition"

Troubleshooting General-Purpose MCP Tools

ask_chatgpt returns authentication error

Verify OPENAI_API_KEY is set correctly in the env block of your MCP config. The key must start with 'sk-'. Check your OpenAI account billing status at https://platform.openai.com/account/billing as the API requires an active payment method.

mcp-toolz command not found after pip install

The mcp-toolz entry point may not be on your PATH. Try using the full path: run 'which mcp-toolz' or 'python -m mcp_toolz' instead. Alternatively, use 'uvx mcp-toolz' in the command field which handles PATH resolution automatically.

Only some LLM tools appear in Claude

Tools are only registered for providers where an API key is supplied in the env config. If ask_gemini is missing, ensure GOOGLE_API_KEY is set. Restart the MCP client after adding new keys.

Frequently Asked Questions about General-Purpose MCP Tools

What is General-Purpose MCP Tools?

General-Purpose MCP Tools is a Model Context Protocol (MCP) server that general-purpose mcp server with utility tools including datetime information, safe math calculations, text statistics, json extraction, knowledge base search, and http get requests. it demonstrates server-side mcp implementation and can be connecte It connects AI assistants to external tools and data sources through a standardized interface.

How do I install General-Purpose MCP Tools?

Install via npm with the command: npx -y mcp-toolz. Then add the server configuration to your AI client's JSON config file (e.g., claude_desktop_config.json or .cursor/mcp.json).

Which AI clients work with General-Purpose MCP Tools?

General-Purpose MCP Tools works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is General-Purpose MCP Tools free to use?

Yes, General-Purpose MCP Tools is open source and available under the MIT license. You can use it freely in both personal and commercial projects.

Browse More Developer Tools MCP Servers

Explore all developer tools servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

Quick Config Preview

{ "mcpServers": { "mcp-tools": { "command": "npx", "args": ["-y", "mcp-toolz"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

Ready to use General-Purpose MCP Tools?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides