Lifecycle MCP Server

A Model Context Protocol (MCP) server for comprehensive software lifecycle management. This server provides structured tracking of requirements

Local serverstdioPython

What is the Lifecycle MCP MCP server?

Lifecycle mcp mcp server connects Lifecycle MCP to AI assistants that speak the Model Context Protocol. A Model Context Protocol (MCP) server for comprehensive software lifecycle management. This server provides structured tracking of requirements, tasks, and architecture decisions through a SQLite database with full traceability and automated state management.

What Lifecycle MCP does

A Model Context Protocol (MCP) server for comprehensive software lifecycle management. This server provides structured tracking of requirements, tasks, and architecture decisions through a SQLite database with full traceability and automated state management.

Key capabilities

  • Requirements Management — Create and manage software requirements with validation and lifecycle tracking
  • Task Management — Track implementation tasks with hierarchical structure and effort estimation
  • Architecture Decisions — Record ADRs (Architecture Decision Records) with full context
  • Project Dashboards — Real-time project health metrics and status reporting
  • Requirement Tracing — Complete traceability from requirements through implementation
  • State Validation — Automatic validation of lifecycle state transitions
  • Relationship Tracking — Many-to-many relationships between requirements, tasks, and architecture

Tools it exposes

Once connected, the assistant can call these 14 tools directly:

  • create_requirement — The create_requirement tool exposed by this server
  • update_requirement_status — The update_requirement_status tool exposed by this server
  • query_requirements — The query_requirements tool exposed by this server
  • get_requirement_details — Get comprehensive requirement information including all relationships
  • trace_requirement — Trace a requirement through its complete implementation lifecycle
  • create_task — The create_task tool exposed by this server
  • update_task_status — The update_task_status tool exposed by this server
  • query_tasks — The query_tasks tool exposed by this server
  • get_task_details — Get comprehensive task information including dependencies and relationships
  • sync_task_from_github — Sync individual task from GitHub issue changes with conflict detection
  • bulk_sync_github_tasks — The bulk_sync_github_tasks tool exposed by this server
  • create_architecture_decision — The create_architecture_decision tool exposed by this server
  • update_architecture_status — Update the status of an architecture decision with validation
  • query_architecture_decisions — Search and filter architecture decisions by various criteria

Installing the lifecycle mcp mcp server

Setup follows the standard MCP pattern: clone or install the server, then register it in your client's configuration file and restart the client. The configuration snippets on this page cover Claude Desktop, Claude Code and Cursor.

Configuration

The server reads 2 environment variables: LIFECYCLE_DB, LIFECYCLE_PATH. Keep credentials in your client's env block or a secrets manager rather than committing them.

Requirements

If you want to use uv (faster Python package manager): ```bash

Where it fits

Productivity servers pay off through capture: the tasks and notes that never get filed are the ones where opening the app is more friction than the thought is worth. Lifecycle MCP sits in that group, and the shape of its toolset — create_requirement, update_requirement_status, query_requirements among others — tells you what it is really for. Worth comparing against the other productivity servers in this directory before you commit to one, since several overlap in scope but differ sharply in setup cost and permissions.

Practical notes

  • This server runs locally, so it operates with whatever access your machine and its credentials already have. Scope that deliberately rather than by default.
  • With 14 tools exposed, expect a noticeable bump in prompt size — disable it in projects that never use Lifecycle MCP.
  • Maintained by heffrey78, written in Python.
  • MCP clients ask for confirmation before each tool call by default. Keep that on while you learn what the lifecycle mcp mcp server actually does with your data.
  • Every entry in this directory is reviewed by hand before it goes live, and details are checked against the project's own documentation.

Available tools

ToolWhat it does
create_requirementThe create_requirement tool exposed by this server.
update_requirement_statusThe update_requirement_status tool exposed by this server.
query_requirementsThe query_requirements tool exposed by this server.
get_requirement_detailsGet comprehensive requirement information including all relationships.
trace_requirementTrace a requirement through its complete implementation lifecycle.
create_taskThe create_task tool exposed by this server.
update_task_statusThe update_task_status tool exposed by this server.
query_tasksThe query_tasks tool exposed by this server.
get_task_detailsGet comprehensive task information including dependencies and relationships.
sync_task_from_githubSync individual task from GitHub issue changes with conflict detection.
bulk_sync_github_tasksThe bulk_sync_github_tasks tool exposed by this server.
create_architecture_decisionThe create_architecture_decision tool exposed by this server.
update_architecture_statusUpdate the status of an architecture decision with validation.
query_architecture_decisionsSearch and filter architecture decisions by various criteria.

Configuration

If you want to use uv (faster Python package manager): ```bash

VariableDescriptionRequired
LIFECYCLE_DBConfiguration value read at startup.Optional
LIFECYCLE_PATHFilesystem location the server is allowed to use.Optional

Example prompts to try

  • Use Lifecycle MCP to create requirement.
  • Use Lifecycle MCP to update requirement status.
  • Use Lifecycle MCP to query requirements.

Frequently asked questions

It connects Lifecycle MCP to MCP-compatible AI assistants such as Claude and Cursor, exposing 14 tools (create_requirement, update_requirement_status, query_requirements, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Lifecycle MCP directly.