Production Ready MCP Framework
Build secure MCP servers with SQL and Python. Ship to production in minutes.
Terminal
Build secure MCP servers with SQL and Python. Ship to production in minutes.
Everything you need to build production-ready MCP servers
OAuth, token-based auth, and SSO integration with providers like GitHub, Google, and Keycloak.
Fine-grained access control with input/output policies and role-based permissions.
Complete audit trails with user context, query logging, and compliance tracking.
OpenTelemetry integration for distributed tracing and production monitoring.
Full type validation for parameters and return types with automatic schema generation.
Detect schema and data changes automatically with snapshot comparisons.
Connect to PostgreSQL, MySQL, SQLite, CSV, JSON, and APIs. Powered by DuckDB.
Native dbt integration for data transformation, caching, and pipeline orchestration.
Data tests, tool tests, Python unit tests, and LLM evaluations in one framework.
Test how LLMs interact with your tools automatically with built-in eval framework.
Define tools with simple YAML. Write SQL or Python—no boilerplate required.
Secure credential storage with Vault, 1Password, and environment variable support.
Common questions about MXCP
MXCP (Model eXtension Context Protocol) is an enterprise-grade MCP server built specifically for production environments. Unlike simple data access tools, MXCP provides enterprise security, audit logging, policy enforcement, dbt integration, and comprehensive data governance. It transforms any data source into AI-ready endpoints with full compliance tracking and type safety.
You can get MXCP running in under 60 seconds. Simply install via pip (pip install mxcp), create a project (mxcp init --bootstrap), and start serving (mxcp serve). The bootstrap option creates example configurations and connects to Claude Desktop automatically.
Yes, MXCP is fully compatible with Claude Desktop and any other MCP-compliant AI client. It implements the Model Context Protocol standard, ensuring seamless integration with current and future AI tools.
MXCP supports PostgreSQL, MySQL, SQLite, DuckDB, CSV files, JSON files, APIs, and cloud storage. It also has native dbt integration for data transformation and caching, making it ideal for complex data pipelines.
MXCP includes enterprise-grade security features including OAuth authentication, role-based access control, policy enforcement, audit logging, data masking, and compliance tracking. Every query is logged with full user context.
MXCP has native dbt integration that creates a powerful data pipeline workflow. dbt models transform and cache data locally in DuckDB, while MCP endpoints query the cached tables directly. This provides lightning-fast AI queries with full data governance.
MXCP is released under the Business Source License 1.1 (BSL). It is free to use for development, testing, and most production scenarios. Commercial licensing is required for hosted services or platforms that enable third parties to run models or queries.
Join our Discord community for real-time support, check GitHub Discussions for technical questions, and follow our blog for updates. We also provide comprehensive documentation and tutorials.
Have more questions? We're here to help.