Install ddflow in Claude Code
PyPI (uv)
claude mcp add ddflow -- uvx ddflow-mcp{
"mcpServers": {
"ddflow": {
"command": "uvx",
"args": [
"ddflow-mcp"
]
}
}
}Docker
claude mcp add ddflow -- docker run -i --rm docker.io/delian/ddflow-mcp:0.2.9{
"mcpServers": {
"ddflow": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"docker.io/delian/ddflow-mcp:0.2.9"
]
}
}
}Docker
claude mcp add ddflow -- docker run -i --rm ghcr.io/delian/ddflow-mcp:0.2.9{
"mcpServers": {
"ddflow": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"ghcr.io/delian/ddflow-mcp:0.2.9"
]
}
}
}Frequently asked questions
What does the ddflow MCP server do?
Work-queue kernel for AI coding agents: dependencies, worktree isolation, quality gates, recovery
Is the ddflow MCP server free?
Yes, most likely. Open source and no paid account or API key is mentioned in the listing. Check the provider for current pricing.
Does ddflow run locally or remotely?
Local. Runs on your machine (stdio). You install it with npx, uvx, Docker or from source.
How do I add ddflow to Claude Code?
Run: claude mcp add ddflow -- uvx ddflow-mcp
More ai agents & coding agents MCP servers
View allDea
shreyassaw5394/dea
Observe any running process from your agent. strace, py-spy, perf, lsof, tcpdump as evidence.
Data Cleaner Agent
wesseltl/data-cleaner-agent
Clean messy CSVs: an LLM picks the steps, tested code does the work. Data untouched by the model.
Dear Agent
BitmapAsset/dear-agent
Your AI agent keeps your diary for you. Local-first, private, works in any agent.
dashAI (unofficial)
Maarmapa/dashai-mcp
Train, track and query models on a running dashAI instance. Read-oriented, no delete tools.
Dear User
bleedmode/dearuser
Tells you how you and your Claude agent actually work together. Local-only, no API keys.
DarkMatter
darkmatter-hub/mcp
Tamper-evident records of AI agent decisions. Verify offline, or publish a proof link.