context-portal
Verified Safeby GreatScottyMac
Overview
A database-backed Model Context Protocol (MCP) server for managing structured project context, designed to be used by AI assistants and developer tools within IDEs and other interfaces for Retrieval Augmented Generation (RAG) and prompt caching.
Installation
uvx --from context-portal-mcp conport-mcp --mode stdio --log-level INFOSecurity Notes
The server uses Pydantic for robust input validation, mitigating common injection risks. FTS (Full-Text Search) queries are pre-processed to prevent FTS5-specific injection vulnerabilities. No hardcoded secrets were identified in the provided source. When run in HTTP mode (via FastAPI/Uvicorn), it has standard web security considerations. When run in STDIO mode, the attack surface is significantly reduced. The `chromadb.PersistentClient` uses `allow_reset=True` during initialization, which is acceptable for development but should be reviewed for production if strict data immutability is required.
Similar Servers
memory-graph
Provides intelligent, persistent graph-based memory capabilities for AI assistants and coding agents in Claude Code environments.
django-ai-boost
Provides a Model Context Protocol (MCP) server for Django applications, enabling AI assistants to introspect and interact with Django codebases.
mcp-ai-agent-guidelines
This MCP server provides a comprehensive suite of tools for AI agent development, including automated design processes, code analysis, prompt engineering, and inter-agent orchestration, enforcing guidelines and consistency across projects.
tenets
The Tenets MCP Server provides intelligent code context aggregation and automatic guiding principles injection for AI coding assistants. It helps LLMs understand codebases by ranking relevant files, optimizing for token budgets, and maintaining consistency across interactions.