Skip to main content
Glama

wtinydb-mcp: Model Context Protocol Server for WTinyDB

wtinydb-mcp is an official Model Context Protocol (MCP) server built on top of FastMCP that equips AI agents with tools to architect, validate, scaffold, and generate code for WTinyDB (TinyDB + Pydantic document database engine).

Key Technologies & Libraries

  • MCP Protocol: Open standard connecting AI models to external tools and context.

  • FastMCP: Python framework for fast MCP server implementation.

  • WTinyDB: Pydantic-powered document database engine on top of TinyDB.

  • Pydantic v2: Data schema validation and Python AST inspection.

  • Pytest: Modern Python testing framework.

  • Pytest-Cov: Code coverage measurement for pytest.

  • Docker: Containerized test execution environment.


Related MCP server: Pattern Intelligence MCP

MCP Tools Exposed

  1. validate_model_schema(model_code: str): Validates Pydantic document models for WTinyDB compatibility.

  2. search_wtinydb_pattern(query: str): Searches the official wisrovi SUITE catalog for WTinyDB architectural patterns.

  3. deploy_wtinydb_scaffolding(target_dir: str, project_name: str, scaffold_type: str): Deploys project scaffolding with repository, config, models, and tests.

  4. get_wtinydb_architect_blueprints(): Returns code reference and blueprints for WTinyDB features.

  5. get_wtinydb_architect_manual(): Returns the comprehensive WTinyDB architecting manual.

  6. generate_wtinydb_crud(model_code: str): Automatically generates repository CRUD class for Pydantic models.


Running Unit Tests & Coverage

Local Pytest Execution

# Install editable package
pip install -e .

# Run pytest test suite
pytest tests/

# Calculate code coverage
./scripts/run_coverage.sh

Docker Containerized Test Execution

./scripts/run_tests_docker.sh

Part of the wisrovi SUITE ecosystem.


๐Ÿ‘ค Autor & Afiliaciรณn Oficial

Related MCP Connectors

Related MCP Servers

  • F
    license
    A
    quality
    D
    maintenance
    Enables LLMs to create, query, and manage MongoDB-compatible databases using natural language without actual data storage. Uses statistical modeling to generate realistic data on-the-fly from sample documents or descriptions.
    8
    4
    -
  • A
    license
    A
    quality
    B
    maintenance
    Enables AI coding agents to make evidence-aware design-pattern decisions by analyzing cases, comparing options, detecting misuse, stress-testing assumptions, planning adoption, writing ADRs, and generating evidence plans with transparent scoring.
    8
    5 npm
    2
    MIT
  • A
    license
    A
    quality
    C
    maintenance
    Enables AI coding assistants to read, create, update, delete, and list documents in JayDB and JayDB Cloud databases, with optimistic concurrency, health checks, and direct document URI access.
    5
    8 npm
    MIT