mrkplt/shared-project-context
If you are the rightful owner of shared-project-context and would like to certify it and/or have it hosted online, please leave a comment on the right or send an email to henry@mcphub.com.
The Model Context Protocol (MCP) server is a production-ready system designed for managing persistent AI assistant contexts, offering tools for storing, retrieving, and validating context across AI collaboration sessions.
The MCP Context Server is a sophisticated system designed to manage AI assistant contexts in a production environment. It provides a robust architecture for storing, retrieving, and validating context across multiple AI collaboration sessions. The server is organized on a project basis, ensuring that each project maintains isolated contexts, templates, and configurations. It supports six specialized context types, each optimized for different content patterns and behaviors, and offers advanced markdown structure validation with project-specific customization. The system includes an archive feature for automatic data preservation during destructive operations, ensuring data integrity and safety. With full ES module compatibility, the server supports modern JavaScript dependencies and includes a comprehensive test suite for real filesystem validation. This makes it an ideal solution for persistent AI assistant collaboration, enabling context preservation and sharing across multiple AI sessions.
Features
- Production-Ready Architecture: A mature, tested system with comprehensive error handling and validation.
- Project-Based Organization: Each project maintains isolated contexts, templates, and configuration.
- Sophisticated Context Types: Six specialized context types supporting different content patterns and behaviors.
- Template Validation: Advanced markdown structure validation with project-specific customization.
- Archive System: Automatic data preservation during destructive operations.
Usages
usage with local development
python mcp.run(transport='stdio') # Tools defined via @mcp.tool() decorator
usage with remote deployment
python mcp.run(transport='sse', host="0.0.0.0", port=8000) # Specify SSE endpoint
usage with platform integration
{ "mcpServers": { "weather": { "command": "python", "args": ["weather.py"] } } }
usage with production environments
yaml paths: /mcp: post: x-ms-agentic-protocol: mcp-streamable-1.0 # Copilot Studio integration
usage with ai toolchains
{"command": "docker", "args": ["run", "-e", "GITHUB_PERSONAL_ACCESS_TOKEN", "ghcr.io/github/github-mcp-server"]}
usage with enterprise saas
{ "contextTypes": [ { "baseType": "templated-log", "name": "session_summary", "description": "Development session chronological log", "template": "session_summary", "validation": true } ] }
Tools
list_projects
Discover all available projects.
create_project
Create a new project with default configuration.
list_contexts
Discover available context types and existing content for a project.
get_context
Retrieve context content.
update_context
Create or update context with automatic validation.
clear_context
Clear context with automatic archiving for data safety.
get_project_templates
Retrieve templates for validated context types.