What is Context Portal (ConPort)?

Context Portal (ConPort) is a memory bank for your software project. It's a tool that helps AI assistants understand your specific software project better by storing important information like decisions, tasks, and architectural patterns in a structured way.

How does ConPort improve AI assistant performance?

ConPort improves AI assistant performance by providing a structured and easily accessible knowledge base of project-specific information. This allows AI to deliver more accurate and helpful responses.

What are the key features of ConPort?

Key features include structured context storage, MCP server implementation, multi-workspace support, STDIO deployment mode, dynamic project knowledge graph, vector data storage, semantic search, RAG backend, prompt caching, and database schema evolution.

What is Model Context Protocol (MCP)?

MCP is an open protocol that standardizes how applications provide context to LLMs.

What is Retrieval Augmented Generation (RAG) and how does ConPort support it?

RAG is a framework that improves the quality of AI-generated text by retrieving relevant information from an external knowledge source and incorporating it into the generation process. ConPort acts as a backend for RAG by storing project-specific knowledge and enabling AI to retrieve this information for contextualized responses.

How do I install and configure ConPort?

The recommended way to install and run ConPort is by using `uvx` to execute the package directly from PyPI. Alternatively, you can install it from the Git repository.

What is the purpose of the `--workspace_id` command-line argument?

The `--workspace_id` argument provides the server process with the absolute path to the project workspace, performs a safety check to prevent database creation in the installation directory, and signals the client which project is being launched.

How can I optimize LLM agents to work with ConPort?

Optimize LLM agents by providing custom instructions or system prompts that guide them on how to use ConPort's tools for context management. This repository includes tailored strategy files for different environments.

How does prompt caching work with ConPort?

ConPort helps to identify cacheable content and provide instructions on structuring prompts for different LLM providers to reduce token costs and latency by reusing frequently used parts of prompts.

Where can I find the strategy files for LLM agents?

You can find the strategy files in the `conport-custom-instructions` directory of this repository. There are specific strategies for Roo Code, CLine, Windsurf Cascade, and general use.

Context Portal MCP Server: Unleash Context-Aware AI in Your Development Workflow

In today’s rapidly evolving software development landscape, artificial intelligence (AI) is increasingly playing a pivotal role. However, the effectiveness of AI assistants and tools hinges on their ability to access and understand the specific context of a project. This is where the Context Portal MCP (ConPort) server steps in, revolutionizing how AI interacts with your codebase and development environment.

What is Context Portal MCP (ConPort)?

Context Portal (ConPort) is a memory bank for your software project. This innovative Model Context Protocol (MCP) server structures project-specific knowledge, enabling AI assistants to deliver more accurate and helpful responses. ConPort acts as a project-specific knowledge graph that AI can easily access to provide context-aware assistance.

ConPort functions as a robust database-backed system that manages structured project context. It’s designed to integrate seamlessly with AI assistants and developer tools within Integrated Development Environments (IDEs) and other interfaces.

ConPort helps AI understand the project and provide better, more relevant support. It:

Tracks decisions, progress, and system designs.
Stores custom project data, such as glossaries and specifications.
Enables AI to quickly find relevant project information.
Empowers AI to use project context for better responses through Retrieval Augmented Generation (RAG).
Offers efficient context management, searching, and updating compared to file-based systems.

It goes beyond simple file-based context management by offering a reliable, queryable SQLite database backend for each workspace. Designed as a generic context backend, ConPort is compatible with various IDEs and client interfaces that support the MCP protocol.

Key Features of ConPort

Structured Context Storage: ConPort utilizes SQLite databases to store project context in a structured manner. Each workspace has its own database, created automatically. This ensures organized and easily accessible data.
MCP Server Implementation: Built with Python and FastAPI, the context_portal_mcp server provides a comprehensive suite of defined MCP tools for interaction.
Multi-Workspace Support: The server supports multiple workspaces through the use of workspace_id, allowing developers to manage context for different projects simultaneously.
STDIO Deployment Mode: ConPort’s primary deployment mode is STDIO, which ensures tight integration with IDEs.
Dynamic Project Knowledge Graph: ConPort enables the creation of a dynamic project knowledge graph with explicit relationships between context items. This allows AI to understand the connections between different aspects of the project.
Vector Data Storage and Semantic Search: ConPort includes vector data storage and semantic search capabilities, empowering advanced Retrieval Augmented Generation (RAG).
RAG Backend: ConPort serves as an ideal backend for Retrieval Augmented Generation (RAG), providing AI with precise, queryable project memory.
Prompt Caching: ConPort provides structured context that AI assistants can leverage for prompt caching with compatible LLM providers. This optimizes performance and reduces costs.
Database Schema Evolution: ConPort manages database schema evolution using Alembic migrations, ensuring seamless updates and data integrity.

Use Cases

ConPort enhances a variety of development workflows. ConPort:

AI-Powered Code Completion: AI assistants can leverage ConPort to provide more accurate and context-aware code suggestions, reducing errors and improving developer productivity.
Intelligent Debugging: By understanding the project’s architecture and past decisions, AI can assist in debugging by suggesting potential causes of errors and guiding developers to relevant code sections.
Automated Documentation Generation: ConPort can be used to automatically generate project documentation, ensuring that it is always up-to-date and reflects the current state of the codebase.
Streamlined Code Reviews: AI assistants can use ConPort to identify potential issues and inconsistencies in code reviews, improving code quality and reducing the time required for reviews.
Enhanced Project Onboarding: New team members can quickly get up to speed on a project by leveraging ConPort to understand its architecture, key decisions, and ongoing tasks.
Context-Aware Chatbots: Integrate ConPort with chatbots to provide developers with instant access to project information, enabling them to resolve issues and answer questions more quickly.

Installation and Configuration

Installing and configuring ConPort is designed to be straightforward. The recommended approach involves using uvx to execute the package directly from PyPI, eliminating the need for manual virtual environment management. For developers who prefer a more hands-on approach, ConPort can also be installed from the Git repository.

How ConPort Powers Retrieval Augmented Generation (RAG)

ConPort excels as a backend for Retrieval Augmented Generation (RAG) systems. Here’s how:

Knowledge Graph Construction: ConPort captures project knowledge, including decisions, progress, and architecture, and represents them as entities and relationships within a knowledge graph.
Vector Embeddings: ConPort enhances its knowledge representation with vector embeddings, enabling semantic search capabilities.
Precise Information Retrieval: AI agents can query ConPort’s knowledge graph and vector embeddings to retrieve specific, up-to-date project information.
Contextualized Responses: The retrieved information augments the AI agent’s generation process, resulting in more context-aware and accurate responses.

Optimizing LLM Agents with Custom Instructions

To maximize ConPort’s effectiveness, it’s crucial to provide specific custom instructions or system prompts to the LLM agent. This repository includes tailored strategy files for different environments. This ensures the AI understands how to use ConPort’s tools for effective context management.

Leveraging Prompt Caching for Efficiency

ConPort facilitates prompt caching, enabling AI assistants to reduce token costs and latency by reusing frequently used parts of prompts. By managing your project’s knowledge and providing the LLM assistant with a prompt caching strategy, you can enhance the efficiency and cost-effectiveness of your AI interactions.

Available ConPort Tools

ConPort offers a comprehensive set of tools via MCP, empowering interaction with the underlying project knowledge graph. These tools facilitate semantic search, powered by vector data storage, which is crucial for Retrieval Augmented Generation (RAG).

ConPort and the UBOS Platform

ConPort seamlessly integrates into the broader UBOS ecosystem, which is a full-stack AI Agent Development Platform focused on bringing AI Agents to every business department. UBOS allows you to orchestrate AI Agents, connect them with enterprise data, build custom AI Agents with your LLM model and Multi-Agent Systems. UBOS and ConPort working together:

Centralized AI Agent Management: The UBOS platform provides a central hub for managing and deploying AI agents, making it easy to integrate ConPort into your AI-powered workflows.
Data Connectivity: UBOS enables AI agents to connect to various enterprise data sources, allowing them to leverage a wealth of information to provide more accurate and insightful responses.
Custom AI Agent Development: UBOS empowers you to build custom AI agents tailored to your specific needs, enabling you to create AI-powered solutions that are perfectly aligned with your business objectives.
Multi-Agent System Orchestration: UBOS facilitates the creation of multi-agent systems, where multiple AI agents collaborate to solve complex problems. ConPort can provide these agents with a shared understanding of the project context, enabling them to work together more effectively.

Conclusion

Context Portal (ConPort) represents a significant advancement in AI-assisted software development. By providing a structured and easily accessible knowledge base for AI agents, ConPort empowers developers to build more intelligent, efficient, and reliable software. As AI continues to transform the software development landscape, ConPort is poised to become an indispensable tool for teams looking to leverage the full potential of AI.