I craft unique cereal names, stories, and ridiculously cute Cereal Baby images.

TPC-Server
Plans de pensées ChangeLog est un serveur conforme à la MCP pour le codage avec des agents d'IA
1
Github Watches
0
Github Forks
1
Github Stars
TPC Server - Model Context Protocol (MCP) Implementation
A production-ready MCP server for tracking AI team coordination through Thoughts, Plans, and Changelog (TPC) entries. Built with SQLAlchemy async and FastMCP, optimized for software development collaboration.
Features
✅ Structured Collaboration
- Track decision-making (
Thoughts
), task coordination (Plans
), and progress (Changelog
) - Dependency management for complex workflows
- Uncertainty flagging for critical design decisions
✅ Performance Optimized
- Async SQLAlchemy 2.0 with connection pooling
- Time-ordered UUIDs (UUID7) for chronological traceability
- Cached queries with 5-minute TTL
✅ Developer-Friendly
- Full MCP interface compliance
- REST-like resource endpoints for data access
- Comprehensive Pydantic validation
Quick Start
# 1. Clone repository
git clone https://github.com/suttonwilliamd/tpc-server.git
cd tpc-server
# 2. Install dependencies
pip install -r requirements.txt
# 3. Run server (SQLite auto-created)
uvicorn main:mcp --reload --port 8000
Core Concepts
1. Thoughts
# Log design decisions or uncertainties
create_thought(
content="Choosing React over Vue for frontend",
plan_id="pl_frontend_123",
uncertainty_flag=True
)
2. Plans
# Define tasks with dependencies
create_plan(
description="Implement user authentication",
dependencies=["pl_database_setup", "pl_security_audit"]
)
3. Changelog
# Track implementation progress
log_change(
plan_id="pl_auth_456",
description="Added JWT token endpoints",
thought_ids=["th_design_decision_789"]
)
Advanced Usage
AI Agent Integration
# Example pre-commit hook validation
modified_files = get_git_changes()
tpc_entries = query_tpc_server()
for file in modified_files:
if not has_corresponding_tpc_entry(file, tpc_entries):
raise Exception(f"Missing TPC entry for {file}")
API Reference
Endpoint | Method | Description |
---|---|---|
/mcp/thoughts |
POST | Create new thought |
/mcp/plans |
POST | Define new plan with dependencies |
/mcp/changelog |
POST | Log implementation changes |
/mcp/plans/{id} |
GET | Get plan details with dependencies |
Architecture
graph TD
A[Thoughts] -->|reference| B(Plans)
B -->|depend_on| B
C[Changelog] -->|link| A
C -->|track| B
Production Setup
# Optimal deployment
uvicorn main:mcp \
--host 0.0.0.0 \
--port 8000 \
--workers 1 \ # Recommended for SQLite
--proxy-headers
Contributing
- Fork repository
- Create feature branch (
git checkout -b feature/tpc-enhancements
) - Commit changes (
git commit -am 'Add new feature'
) - Push branch (
git push origin feature/tpc-enhancements
) - Open pull request
Inspired by the Awesome MCP Servers community . For MCP client implementations, see FastMCP documentation.
相关推荐
I find academic articles and books for research and literature reviews.
Confidential guide on numerology and astrology, based of GG33 Public information
Emulating Dr. Jordan B. Peterson's style in providing life advice and insights.
Advanced software engineer GPT that excels through nailing the basics.
Your go-to expert in the Rust ecosystem, specializing in precise code interpretation, up-to-date crate version checking, and in-depth source code analysis. I offer accurate, context-aware insights for all your Rust programming questions.
Take an adjectivised noun, and create images making it progressively more adjective!
Découvrez la collection la plus complète et la plus à jour de serveurs MCP sur le marché. Ce référentiel sert de centre centralisé, offrant un vaste catalogue de serveurs MCP open-source et propriétaires, avec des fonctionnalités, des liens de documentation et des contributeurs.
L'application tout-en-un desktop et Docker AI avec chiffon intégré, agents AI, constructeur d'agent sans code, compatibilité MCP, etc.
Manipulation basée sur Micropython I2C de l'exposition GPIO de la série MCP, dérivée d'Adafruit_MCP230XX
Plateforme d'automatisation de workflow à code équitable avec des capacités d'IA natives. Combinez le bâtiment visuel avec du code personnalisé, de l'auto-hôte ou du cloud, 400+ intégrations.
🧑🚀 全世界最好的 LLM 资料总结 (数据处理、模型训练、模型部署、 O1 模型、 MCP 、小语言模型、视觉语言模型) | Résumé des meilleures ressources LLM du monde.
Une liste organisée des serveurs de protocole de contexte de modèle (MCP)
Reviews

user_1PZPOEot
I've been using tpc-server by suttonwilliamd, and it has been a game-changer for my projects. The implementation and functionality are top-notch, and the documentation is very clear. The fact that it's open-source and available on GitHub makes it even better. Highly recommend!