Tpm MCP
A localized technical project management MCP server that provides project, feature, and task tracking capabilities for Claude. Data is stored in a local SQLite database, supporting a hierarchical organizational structure and progress management.
2.5 points
6.9K

What is TPM-MCP?

TPM-MCP is a local MCP (Model Context Protocol) server that endows Claude with project management capabilities. You can regard it as a dedicated technical project manager that can remember your work in different sessions, break down complex features into manageable tasks, track progress and obstacles, and provide instant status updates.

How to use TPM-MCP?

After installing TPM-MCP, you can have project-related conversations with Claude in natural language. For example, you can inquire about project status, add new features, mark tasks as completed, etc. Claude will use TPM-MCP's tools to manage your project data.

Applicable scenarios

TPM-MCP is well-suited for individual developers, small teams, or any scenario that requires AI-assisted project management. It is particularly useful for: - Tracking the progress of multiple projects - Breaking down large features into executable tasks - Conducting daily stand-up meetings or progress synchronization - Managing technical debt and bug fixes - Generating project status reports

Main Features

Fast and Localized
Achieve sub-millisecond queries using SQLite + WAL mode. All data is stored locally in ~/.local/share/tpm-mcp/tpm.db to ensure privacy and security.
Natural Language Interaction
Simply converse with Claude as you would with a human project manager, without the need to remember complex commands.
Hierarchical Project Management
Support a multi-level structure of organization → project → work order → task for clear management of complex projects.
Rich Metadata
Support various metadata such as priority, tags, assignees, complexity, and remarks to comprehensively describe the project status.
Import and Export Function
Support full JSON export/import for easy backup, migration, or integration with other tools.
PDF Status Reports
Generate beautiful and shareable PDF reports containing progress overviews, project breakdowns, key milestones, and risk items.
Advantages
Privacy protection: All project data is stored locally and will not leave your machine.
High-speed response: The SQLite database provides extremely fast query performance.
Offline work: All functions can be used without an internet connection.
Simple and reliable: A single database file, easy to backup and synchronize.
No API limitations: Not affected by third - party API rate limits or service interruptions.
Limitations
Only for Claude: Currently only supports integration with Claude.
Requires local installation: Needs a Python environment and related dependencies.
No multi - user collaboration: Mainly designed for individual or single - user use.
Learning curve: Requires understanding of basic MCP server concepts.

How to Use

Clone and Install
Download the TPM-MCP code and install the dependencies.
Add to Claude
Configure TPM-MCP as Claude's MCP server.
Enable TPM Agent Behavior (Optional)
To get the full experience, add the TPM agent instructions.
Start Using
Start using natural language to manage projects in Claude.

Usage Examples

Create a New Feature
Add user authentication functionality to the backend project.
Break Down Tasks
Break down a large feature into manageable subtasks.
Update Progress
Mark tasks as started and completed.
Generate a Status Report
Create a shareable PDF report of the project status.

Frequently Asked Questions

Which AI assistants does TPM-MCP support?
Where is the data stored? How can I back it up?
Is an internet connection required?
How can I migrate from other project management tools?
Does it support team collaboration?

Related Resources

GitHub Repository
The source code and latest version of TPM-MCP.
Model Context Protocol Documentation
Official MCP documentation to understand how the protocol works.
Claude Desktop Application
Download the Claude desktop application to use MCP features.
SQLite Documentation
Understand the database technology used by TPM-MCP.

Installation

Copy the following command to your Client for configuration
{
  "mcpServers": {
    "tpm": {
      "command": "uv",
      "args": ["run", "--directory", "/path/to/tpm-mcp", "tpm-mcp"]
    }
  }
}

{
  "mcpServers": {
    "playwright-headless": {
      "command": "npx",
      "args": ["@playwright/mcp@latest", "--headless"]
    }
  }
}
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
15.4K
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
8.7K
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
9.4K
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
15.2K
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
9.1K
4 points
P
Paperbanana
Python
9.2K
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
8.9K
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
10.3K
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
27.9K
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
23.4K
4.5 points
D
Duckduckgo MCP Server
Certified
The DuckDuckGo Search MCP Server provides web search and content scraping services for LLMs such as Claude.
Python
81.2K
4.3 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
38.7K
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#
38.8K
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
71.8K
4.5 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
24.5K
4.5 points
M
Minimax MCP Server
The MiniMax Model Context Protocol (MCP) is an official server that supports interaction with powerful text-to-speech, video/image generation APIs, and is suitable for various client tools such as Claude Desktop and Cursor.
Python
56.3K
4.8 points
AIBase
Zhiqi Future, Your AI Solution Think Tank
© 2026AIBase