🦅 wpipe-mcp
Transform your AI Agents into expert WPipe Architects.
wpipe-mcp is a professional Model Context Protocol (MCP) server that bridges the gap between AI Agents (Claude, Gemini, OpenCode) and the wisrovi SUITE. It empowers agents to search, design, validate, and deploy high-performance pipelines following strict industry-standard patterns.
✨ Key Features
-
🔍 Expert Catalog Search: Query over 100+ production-ready steps from Official and Community registries.
-
🏗️ Strict Architecture Enforcement: Guides AI to output clean code using mandatory
dto/,states/,pipelines.py, andmain.pyfolder structures, including the internal microserviceapp/layout. -
🚀 Declarative Pipeline Definition (
app/pipelines.py): Dedicated specification and blueprint for standalone pipeline assembly with inline step instantiation (set_steps([MyStep(), ...])) and typed execution helper wrappers. -
🛡️ Project Architectural Validation: Verify that any existing code structure complies with the WPipe standards using
validate_wpipe_projectto check directories, step decorators, and context schemas. -
⚙️ Automated Monolith Refactoring: Automatically split monolithic Python scripts into modular class-based WPipe steps (
@step) and shared contexts withrefactor_monolith_to_wpipe. -
📊 Automatic Pipeline Documentation: Generate complete Mermaid DAG flowcharts and technical markdown specifications directly in the project's root
README.mdwithdocument_wpipe_project. -
🧪 Unit Test Generation: Instantly build boilerplate test files with extensive English descriptions using
generate_wpipe_tests. -
🔍 Static Context Data Flow Analysis: Statically verify that data fields passed and consumed across steps are valid with
validate_context_flow. -
⚙️ Pipeline Dry Run Simulation: Simulate pipeline runs to trace context states without invoking heavy models/APIs using
dry_run_pipeline. -
⚡ Performance & Monitoring Optimization: Statically inspect compliance scores and receive actionable recommendations using
optimize_wpipe_pipeline. -
🏆 WPipe Quality Rules Enforcement: Built-in rules for strict English, Google-style docstrings, type hinting (
mypy), Pylint score >= 9.3, Dockerizedpytestcoverage (>80%), and Black/Isort formatting. -
📘 Architect's Manual: Built-in expertise for Monolith-to-Pipeline refactoring, performance tracking, resilient state management, and mandatory
app/pipelines.pyspecifications. -
💻 Unified CLI: Manage your MCP service with simple commands:
run,start,stop, andconfig. -
🔒 Privacy First: 100% local execution via
stdioorSSE.
🛠️ Key Technologies & Libraries
This MCP server relies on the following key tools and libraries:
- Model Context Protocol (MCP): Server protocol implementation for agent interaction.
- FastMCP (mcp-sdk-python): Framework to declare tools and resources cleanly.
- Pydantic: Structural validation, schema checks, and context enforcement.
- Pytest & Pytest-Cov: Automated unit testing and coverage report analysis.
- Ruff: Modern linting and styling consistency.
🚀 Quick Start
1. Installation
Clone the repository and run the automated installer, or install via pip:
pip install -e .
2. Integration
Get your agent-specific configuration block and installation commands by running:
wpipe-mcp config
The CLI will dynamically detect your Python environment and provide exact copy-paste commands for Gemini CLI (e.g. gemini mcp add ...) and JSON blocks for Claude Desktop.
🧪 Running Tests
Unit tests are written with pytest. You can run them in three ways:
1. Locally (with development dependencies installed)
To execute tests locally with python path environment set up:
PYTHONPATH=src pytest tests/ -v
2. Inside a Docker Container (Recommended)
To run tests in a containerized environment to isolate dependencies:
./run_tests_docker.sh
3. Calculate Code Coverage
To run tests and get a detailed statement of code coverage:
./run_coverage.sh
This generates an HTML report in htmlcov/index.html.
📂 Project Structure
src/wpipe_mcp/: Core server logic and tools.src/wpipe_mcp/catalog.py: Real-time GitHub catalog synchronization.src/wpipe_mcp/templates.py: Professional boilerplate definitions.examples/: Sample implementations and use cases.tests/: Automated unit tests verifying blueprints, scaffolding, and validation.
📄 License
MIT License - Crafted with ❤️ by William Rodriguez (wisrovi).
Metadata
Release files for wpipe-mcp 0.4.2
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| wpipe_mcp-0.4.2.tar.gz | 29.1 kB | Without provenance | Details for wpipe_mcp-0.4.2.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| wpipe_mcp-0.4.2-py3-none-any.whl | Python 3 | none | any | Details for wpipe_mcp-0.4.2-py3-none-any.whl |
Total release size: 54.6 kB
Release files / wpipe_mcp-0.4.2.tar.gz
| Download URL | wpipe_mcp-0.4.2.tar.gz |
|---|---|
| Size | 29.1 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
48a03a0c0b1926edf6a258b4cca0743dc5b547f2bf8e847447b2eee1d9db6594
|
|
BLAKE2b-256 checksum How to use checksums |
0c22a358db27f96e4237a080738591a40605172bd7d160977da79c0e694a75d3
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/7.0.0 CPython/3.13.5
|
Release files / wpipe_mcp-0.4.2-py3-none-any.whl
| Download URL | wpipe_mcp-0.4.2-py3-none-any.whl |
|---|---|
| Size | 25.5 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
b2f0c71bf2036338d433f68dc3d68066829f4374bd286353a6a87af152d0ce3f
|
|
BLAKE2b-256 checksum How to use checksums |
d14fa52fcc0452de08943d59eedb98a2efb62d9df31be9a9af442e8b1f9979f0
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/7.0.0 CPython/3.13.5
|
Security for wpipe-mcp 0.4.2
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.