A Model Context Protocol (MCP) server for comprehensive software lifecycle management. This server provides structured tracking of requirements
Lifecycle MCP 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.
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.
If you want to use uv (faster Python package manager): ```bash
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.Compare MCP servers by category, or browse hosted MCP servers if you prefer an endpoint over a local process.
Check the linked publisher documentation and your connected client's tool list. Names and availability can vary with the server version and account permissions.
| Tool | What it does |
|---|---|
| create_requirement | Create new requirements |
| update_requirement | Edit a requirement's content (a reason is required at Approved or later) |
| update_requirement_status | Move one or many requirements through lifecycle states, stepping through the allowed path |
| query_requirements | Search and filter requirements, including the ones whose work is done and only the decision is missing; the matching records also come back as structured data |
| trace_requirement | Trace requirement through implementation |
| create_task | Create implementation tasks from requirements |
| update_task | Edit a task's content, move it to another parent or change its requirements |
| update_task_status | Update the progress of one or many tasks; the comment on a move to Blocked is kept as the reason |
| query_tasks | Search and filter tasks, including the ones ready to start; the matching records also come back as structured data |
| sync_github_tasks | Sync one task, or every linked task, from GitHub issues (listed only when LIFECYCLE_GITHUB=on) |
| create_architecture_decision | Record architecture decisions (ADRs) |
| update_architecture | Edit a Proposed architecture decision, or record a dated amendment against an Accepted one |
| update_architecture_status | Update the status of one or many architecture decisions; Superseded comes from a supersedes link |
| query_architecture_decisions | Search and filter architecture decisions; the matching records also come back as structured data |
| get_details | Full details of a record, with its links and comments |
| delete_record | Delete a Draft requirement, Not Started task or Proposed architecture decision created by mistake |
| add_comment | Comment on a record; comments show in its details and history |
| create_relationship | Link two records: dependencies, refinements, blocks, a task implementing an architecture decision, a newer decision superseding an older one, and more |
| delete_relationship | Remove a link between two records |
| query_relationships | Query links: one record's links by direction and type, or every link as JSON for a graph |
| get_entity_history | Show how a record changed: creation, edits with before and after values, status changes, comments and deletion |
| get_project_status | Project health dashboard; the metrics also come back as structured data |
| export_project_documentation | Export comprehensive markdown documentation |
| create_architectural_diagrams | Generate Mermaid diagrams for project visualization |
{
"mcpServers": {
"lifecycle": {
"command": "lifecycle-mcp",
"env": {
"LIFECYCLE_DB": "./lifecycle.db"
}
}
}
}From the project documentation. Replace placeholders and example paths before connecting.
If you want to use uv (faster Python package manager): ```bash
| Variable | Description | Required |
|---|---|---|
| LIFECYCLE_DB | Declared in the maintainer’s client configuration. | Check documentation |
Read, search and edit files inside allowed directories with the Model Context Protocol reference Filesystem server.
Retrieve version-aware library documentation and code examples with Context7 MCP, using resolve-library-id and query-docs.
Use Microsoft’s Playwright MCP server to navigate pages, inspect accessibility snapshots, fill forms and capture browser screenshots.
Connect GitHub MCP to repositories, issues and pull requests with GitHub’s hosted service or a locally run server.
Use the Supabase MCP server to inspect database schemas, query project data and retrieve docs through a project-scoped connection.
Search Linear issues and projects, inspect work context and manage updates through Linear’s hosted MCP server with OAuth.