AIBase
EN
Explore
MCP Toolz
M

MCP Toolz

MCP Toolz is an MCP server tool for Claude Code that supports cross-session context and to-do list saving and can obtain feedback from multiple AI models such as ChatGPT, Claude, Gemini, and DeepSeek.
Developer toolsKnowledge management and memory#Session Management#AI Feedback#To-do List#Context Storage.Python
2.5 points
10.8K
Open Site

Overview

Installation

Content Details

Alternatives

What is MCP Toolz?

MCP Toolz is an intelligent development assistant specifically designed for Claude Code. It allows you to save important conversations, code snippets, architectural decisions, and error information and retrieve them at any time when needed. More importantly, it enables you to obtain opinions and suggestions from multiple AI models such as ChatGPT, Claude, Gemini, and DeepSeek simultaneously, helping you make more informed technical decisions.

How to use MCP Toolz?

Using MCP Toolz is very simple: 1) Install the Python package and configure the API keys; 2) Set up the MCP server in Claude Code; 3) Restart Claude Code and you can use all the tools. You can use functions through natural language commands such as 'Save this context' or 'Ask ChatGPT about this error'.

Use Cases

MCP Toolz is particularly suitable for the following scenarios: needing to maintain context continuity across multiple work sessions, wanting to compare the views of different AI models on the same problem, needing to save and restore work to-do lists, and sharing technical decisions and lessons learned across multiple projects.

Main Features

Cross-session Context Saving
Automatically save technical discussions, code snippets, and decisions in Claude Code conversations, ensuring they are not lost even when the application is restarted. All content is organized by project directory for easy retrieval.
Multi-AI Model Feedback
Get analysis and suggestions from ChatGPT, Claude, Gemini, and DeepSeek on the same problem with one click. Compare the perspectives of different AIs to make more comprehensive technical decisions.
Intelligent To-do List Management
Save snapshots of work to-do lists and support cross-session restoration. Each to-do list item contains status, content, and activity form information and is automatically organized by project.
Full-text Intelligent Search
Search for saved contexts and to-do lists by content, tags, project, or session ID. Support fuzzy matching and keyword filtering to quickly find the required information.
Session Automatic Tracking
Each Claude Code session automatically gets a unique ID, and all saved content is marked with session information. Easily view 'What was I doing in my last session'.
Cross-project Knowledge Sharing
Share technical decisions and solutions across different projects. Experiences learned in one project can be easily applied to other projects.
Advantages
Seamlessly integrate with Claude Code, allowing you to use all functions without leaving the development environment
Support multiple mainstream AI models, providing diverse technical perspectives
Automatically organize content, classify by project and session for clear management
Store data persistently, ensuring work progress is not lost when the application is restarted
Open source and free, with an active community and continuous updates and improvements
Limitations
Require configuration of multiple API keys (OpenAI, Anthropic, Google, DeepSeek)
Currently only support Claude Code, with limited support for other IDEs
Require a Python environment, which poses a certain threshold for pure front-end developers
Advanced synchronization functions (such as cross-device synchronization) require manual configuration

How to Use

Install MCP Toolz
Install the MCP Toolz package via pip or install the development version from the source code.
Configure API Keys
Set the API key for at least one AI service. You can set it in the environment variables or create a.env file.
Configure Claude Code
Add the MCP Toolz server configuration in the MCP settings of Claude Code.
Restart and Use
Restart Claude Code, and the MCP Toolz tools will be automatically available. Use natural language commands in the conversation to call functions.

Usage Examples

Architectural Decision Comparison
When choosing a technical solution, obtain suggestions from multiple AI models simultaneously to make a more comprehensive decision.
Cross-session Work Restoration
Save the to-do list before ending a day's work and quickly restore the work state the next day.
Multi-AI Debugging Assistance
When encountering a complex bug, obtain debugging suggestions from different AIs and integrate multiple solutions.
Knowledge Base Construction
Save important technical decisions and solutions as a searchable knowledge base.

Frequently Asked Questions

Do I need API keys for all AI services?
Where is the data stored? How can I back it up?
Which versions of Claude Code does MCP Toolz support?
How can I share contexts across different projects?
Is there a size limit for saved contexts?
How can I delete unwanted contexts or to-do lists?

Related Resources

GitHub Repository
Source code, issue tracking, and contribution guidelines for MCP Toolz
PyPI Package Page
Published versions of MCP Toolz on the Python Package Index
Model Context Protocol Official Website
Official documentation and specifications for the MCP protocol
Claude Code Documentation
Official usage documentation for Claude Code
Issue Feedback and Discussion
Report bugs, request features, or participate in discussions

Installation

Copy the following command to your Client for configuration
{
  "mcpServers": {
    "mcp-toolz": {
      "command": "python",
      "args": ["-m", "mcp_server"],
      "env": {
        "OPENAI_API_KEY": "sk-...",
        "ANTHROPIC_API_KEY": "sk-ant-...",
        "GOOGLE_API_KEY": "...",
        "DEEPSEEK_API_KEY": "sk-..."
      }
    }
  }
}

{
  "mcpServers": {
    "mcp-toolz": {
      "command": "python",
      "args": ["-m", "mcp_server"],
      "cwd": "/absolute/path/to/mcp-toolz",
      "env": {
        "PYTHONPATH": "/absolute/path/to/mcp-toolz/src"
      }
    }
  }
}

{
  "mcpServers": {
    "mcp-toolz": {
      "command": "python",
      "args": ["-m", "mcp_server"],
      "cwd": "/absolute/path/to/mcp-toolz",
      "env": {
        "PYTHONPATH": "/absolute/path/to/mcp-toolz/src",
        "MCP_TOOLZ_DB_PATH": "/Users/you/Dropbox/mcp-toolz-shared/contexts.db"
      }
    }
  }
}
Note: Your key is sensitive information, do not share it with anyone.

Alternatives

A
Airweave
Airweave is an open - source context retrieval layer for AI agents and RAG systems. It connects and synchronizes data from various applications, tools, and databases, and provides relevant, real - time, multi - source contextual information to AI agents through a unified search interface.
Python
7.7K
5 points
V
Vestige
Vestige is an AI memory engine based on cognitive science. By implementing 29 neuroscience modules such as prediction error gating, FSRS - 6 spaced repetition, and memory dreaming, it provides long - term memory capabilities for AI. It includes a 3D visualization dashboard and 21 MCP tools, runs completely locally, and does not require the cloud.
Rust
6.4K
4.5 points
M
Moltbrain
MoltBrain is a long-term memory layer plugin designed for OpenClaw, MoltBook, and Claude Code, capable of automatically learning and recalling project context, providing intelligent search, observation recording, analysis statistics, and persistent storage functions.
TypeScript
5.1K
4.5 points
B
Bm.md
A feature-rich Markdown typesetting tool that supports multiple style themes and platform adaptation, providing real-time editing preview, image export, and API integration capabilities
TypeScript
4.3K
5 points
S
Security Detections MCP
Security Detections MCP is a server based on the Model Context Protocol that allows LLMs to query a unified security detection rule database covering Sigma, Splunk ESCU, Elastic, and KQL formats. The latest version 3.0 is upgraded to an autonomous detection engineering platform that can automatically extract TTPs from threat intelligence, analyze coverage gaps, generate SIEM-native format detection rules, run tests, and verify. The project includes over 71 tools, 11 pre-built workflow prompts, and a knowledge graph system, supporting multiple SIEM platforms.
TypeScript
6.5K
4 points
P
Paperbanana
Python
6.8K
5 points
B
Better Icons
An MCP server and CLI tool that provides search and retrieval of over 200,000 icons, supports more than 150 icon libraries, and helps AI assistants and developers quickly obtain and use icons.
TypeScript
6.6K
4.5 points
A
Assistant Ui
assistant - ui is an open - source TypeScript/React library for quickly building production - grade AI chat interfaces, providing composable UI components, streaming responses, accessibility, etc., and supporting multiple AI backends and models.
TypeScript
6.7K
5 points
G
Gitlab MCP Server
Certified
The GitLab MCP server is a project based on the Model Context Protocol that provides a comprehensive toolset for interacting with GitLab accounts, including code review, merge request management, CI/CD configuration, and other functions.
TypeScript
26.0K
4.3 points
D
Duckduckgo MCP Server
Certified
The DuckDuckGo Search MCP Server provides web search and content scraping services for LLMs such as Claude.
Python
73.6K
4.3 points
N
Notion Api MCP
Certified
A Python-based MCP Server that provides advanced to-do list management and content organization functions through the Notion API, enabling seamless integration between AI models and Notion.
Python
20.6K
4.5 points
M
Markdownify MCP
Markdownify is a multi-functional file conversion service that supports converting multiple formats such as PDFs, images, audio, and web page content into Markdown format.
TypeScript
35.0K
5 points
F
Figma Context MCP
Framelink Figma MCP Server is a server that provides access to Figma design data for AI programming tools (such as Cursor). By simplifying the Figma API response, it helps AI more accurately achieve one - click conversion from design to code.
TypeScript
64.4K
4.5 points
U
Unity
Certified
UnityMCP is a Unity editor plugin that implements the Model Context Protocol (MCP), providing seamless integration between Unity and AI assistants, including real - time state monitoring, remote command execution, and log functions.
C#
32.8K
5 points
G
Gmail MCP Server
A Gmail automatic authentication MCP server designed for Claude Desktop, supporting Gmail management through natural language interaction, including complete functions such as sending emails, label management, and batch operations.
TypeScript
22.2K
4.5 points
C
Context7
Context7 MCP is a service that provides real-time, version-specific documentation and code examples for AI programming assistants. It is directly integrated into prompts through the Model Context Protocol to solve the problem of LLMs using outdated information.
TypeScript
97.6K
4.7 points
AIBase
Zhiqi Future, Your AI Solution Think Tank
English简体中文繁體中文にほんご
© 2026AIBase