MCP Server for Flow Framework
A Model Context Protocol (MCP) server that brings the Flow development methodology to any Claude session.
What is Flow?
Flow is a spec-driven iterative development methodology combining Domain-Driven Design principles with Agile philosophy. It helps developers build complex features with minimal refactoring through structured planning and iterative implementation.
Features
flow_init()- Initialize Flow framework in your projectflow_status()- View current development position- More tools coming soon...
Installation
Install via uvx (no setup needed):
uvx mcp-server-flow
Configuration
Add to your Claude Desktop config file:
Location:
- macOS:
~/Library/Application Support/Claude/claude_desktop_config.json - Windows:
%APPDATA%/Claude/claude_desktop_config.json
Config:
{
"mcpServers": {
"flow": {
"command": "uvx",
"args": ["mcp-server-flow"]
}
}
}
Usage
After configuration, restart Claude Desktop and try:
-
Initialize Flow in your project:
"Initialize Flow framework in this project"This creates
.flow/directory with framework docs and optionally.claude/commands/with slash commands. -
Check your status:
"Show me my Flow development status"
Available Tools
-
flow_init(create_slash_commands=True)- Initialize Flow framework- Creates
.flow/directory with framework documentation - Optionally creates
.claude/commands/slash commands (for Claude Code users)
- Creates
-
flow_status()- Show current development position- Returns dashboard with active phase, task, and iteration
- Suggests next steps
Development
# Clone the repo
git clone https://github.com/khgs2411/flow
cd flow/mcp-server-flow
# Install dependencies
uv add fastmcp
# Run locally
uv run mcp_server.py
Roadmap
This is an early release with basic functionality. Future updates will add:
- All 28 Flow commands as MCP tools
- Automated generation from slash command definitions
- Full integration with Flow methodology
License
MIT
Links
- Flow Framework: https://github.com/khgs2411/flow
- Documentation: See
.flow/DEVELOPMENT_FRAMEWORK.mdafter runningflow_init() - Example Plan: See
.flow/EXAMPLE_PLAN.mdfor reference implementation
Metadata
Release files for mcp-server-flow 1.2.17
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 | |
|---|---|---|---|---|
| mcp_server_flow-1.2.17.tar.gz | 174.5 kB | Without provenance | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| mcp_server_flow-1.2.17-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 356.3 kB
Release files / mcp_server_flow-1.2.17.tar.gz
| Download URL | mcp_server_flow-1.2.17.tar.gz |
|---|---|
| Size | 174.5 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
c6095240615221ba7f0c5004bc2d41fddb01727baf805c19bfa659754518b6d1
|
|
BLAKE2b-256 checksum How to use checksums |
efe005bed203f5e8a79c136c0e4a7f89a73feadca90607bcb517b50f2a706ba0
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
uv/0.8.4
|
Release files / mcp_server_flow-1.2.17-py3-none-any.whl
| Download URL | mcp_server_flow-1.2.17-py3-none-any.whl |
|---|---|
| Size | 181.9 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
d5a9554861acc4ddf18fd611de3944d56161d33f3f84f521ee66ebb638633227
|
|
BLAKE2b-256 checksum How to use checksums |
abe643eb313dbdc8039b94284f699a15512cd65c6b7c2b3719145ef080a6bf77
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
uv/0.8.4
|
Security for mcp-server-flow 1.2.17
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.