gd-specflow
SpecFlow MCP server and CLI — spec-driven AI code generation from your IDE.
SpecFlow is an agent harness that automates specification analysis, implementation planning, and large-scale parallel code generation. This package provides the MCP server (specflow-mcp) and the terminal UI (specflow tui).
Requires Python 3.13, Docker, and uv (install).
Local agentic harness sandbox setup
Codegen runs against a local Docker backend in the main SpecFlow repository — installing this package alone is not enough.
Entry point: README.md
Short instructions:
-
Clone the repo and enter it:
git clone https://github.com/griddynamics/specflow.git cd specflow
-
Install Specflow (includes the Terminal UI that guides you through onboarding)
uv tool install --editable "./mcp_server"
-
Bootstrap the sandbox - interactive wizard
specflow tui
MCP tools
| Tool | Description |
|---|---|
check_specification_completeness |
Analyze specs for gaps and contradictions (local) |
run_planning |
Generate a phased implementation plan (local) |
read_document |
Extract PDF/DOCX/PPTX/XLSX/CSV to markdown (local) |
run_generation |
Upload and launch parallel codegen on the backend |
check_status |
Poll generation progress |
download_outputs |
Download artifacts from a completed run |
retry_generation |
Retry a failed generation |
Documentation
License
MIT — Copyright (c) 2024 Grid Dynamics International, Inc.
2 maintainers
Release files for gd-specflow 0.7.1
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| gd_specflow-0.7.1.tar.gz | 171.9 kB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| gd_specflow-0.7.1-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 305.0 kB
Release files / gd_specflow-0.7.1.tar.gz
| Download URL | gd_specflow-0.7.1.tar.gz |
|---|---|
| Size | 171.9 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
8cd672634206208396abff15a0945c3b8c9d3572511916313451f751b9037515
|
|
BLAKE2b-256 checksum How to use checksums |
c86527d6f81619475190160839a81e9fd6819514dbddda977566daa57a2da1b4
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/6.1.0 CPython/3.13.12
|
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.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Jul 3, 2026.
Transparency logRelease files / gd_specflow-0.7.1-py3-none-any.whl
| Download URL | gd_specflow-0.7.1-py3-none-any.whl |
|---|---|
| Size | 133.2 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
1b09971e95b87d2a481015ee797ef41288e623f48846387af5f743aa2e4e8436
|
|
BLAKE2b-256 checksum How to use checksums |
03b9c396e251dd3256a8383e76388c4ef6759eda63faacdfbfc168b09644f3da
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/6.1.0 CPython/3.13.12
|
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.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Jul 3, 2026.
Transparency log
