MCP Worktree Voting Server
Implements a voting pattern for parallel development using git worktrees, allowing users to create multiple implementations of the same task across different branches, evaluate them, and select the best one for merging
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@MCP Worktree Voting Servercreate voting worktrees to add Redis caching to the user service"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
MCP Servers
A collection of local MCP (Model Context Protocol) servers for data engineering and development workflows. All servers run locally via uv — no cloud accounts required.
Servers
Data Engineering
Server | File | Purpose |
|
| Query execution, schema inspection, data import/export |
|
| SQL transformation — model execution, planning, lineage |
|
| Orchestration — assets, jobs, schedules, sensors, runs |
|
| Data pipelines — sources, destinations, load operations |
|
| Data quality contracts — verify, validate, scaffold, history |
Infrastructure
Server | File | Purpose |
|
| Container lifecycle, logs, exec, images, Compose-aware |
|
| Git worktree creation and management for parallel development |
Related MCP server: multi-agent-mcp
Setup
All servers are registered in .mcp.json and run via:
uv run --no-project --with fastmcp --with <deps> ./mcp-servers/<server>.pyRestart Claude Code after any changes to .mcp.json.
Server Notes
duckdb
Manages multiple named DuckDB connections. Supports querying local files (CSV, Parquet, JSON) and remote files (HTTP, S3, GCS). State persisted to .duckdb_state/.
sqlmesh
Wraps the SQLMesh CLI for model management. Requires a SQLMesh project directory set via SQLMESH_STATE_DIR. Supports plan generation, model execution, audits, and lineage introspection.
dagster
Wraps the Dagster CLI for asset and job management. Requires a Dagster workspace file. Supports asset materialization, job execution, schedule/sensor triggering, and run monitoring.
dlt
Manages dlt pipelines for loading data from REST APIs, databases, and files into destinations (DuckDB, etc.). State persisted to .dlt_state/.
soda
Runs Soda Core data quality contract verifications locally (no Soda Cloud). Expects a ./soda/ directory with:
soda/
datasources/ # datasource YAML configs
contracts/ # contract YAML files
results/ # scan results (auto-created)docker
Connects to Docker via Colima on macOS (~/.colima/default/docker.sock). Includes Compose-aware tools that read com.docker.compose.* labels.
worktrees
Creates isolated git worktrees branching from origin/main for running parallel Claude sessions on independent tasks.
This server cannot be deployed
Maintenance
Related MCP Connectors
AI-native git hosting — repos, PRs, issues, CI gates, and AI code review over MCP (60 tools).
Plain-English git via MCP: 22 tools to branch, commit, push, and tag. No git jargon.
- OolkinOAuthcom.oolkin
AI colleagues that keep your standards, your project and their reasoning between sessions
Git-backed platform for skills, tools, and context for AI agents
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceA git worktree manager that enables AI agents to work on different branches simultaneously with automatic coordination, locking, and merge management. Supports creating, managing, and merging git worktrees with setup automation and conflict resolution.6 npm6MIT
- AlicenseCqualityBmaintenanceManages multiple AI CLI instances (Claude Code, Codex, Gemini, Cursor) in tmux sessions for parallel task execution, with optional git worktree support.90MIT
- AlicenseBqualityDmaintenanceManages parallel Git worktrees, enabling work on multiple branches simultaneously without stashing or context switching.141MIT
- AlicenseNot gradedqualityCmaintenanceEnables AI coding agents to manage Git worktrees by creating, listing, removing, and cleaning isolated workspaces through MCP tools.MIT