adins-prd-mcp

# adins-prd-mcp MCP server for reading Confluence PRD pages and rendering SRS/URS documents as Word files. Built for use with AI agents in the AdIns SDLC toolchain. ## Tools ### Confluence tools | Tool | Description | |---|---| | `get_confluence_page` | Fetch a page by numeric ID. Returns markdown or raw HTML in context. | | `get_confluence_page_to_file` | Fetch a page and write content directly to a local file. Returns path and size only. | | `search_confluence` | Search using CQL. | | `list_confluence_attachments` | List attachments on a page. | | `download_confluence_attachment` | Download an attachment to a local path. | | `get_confluence_page_ancestors` | Return the ancestor chain (root → immediate parent). | | `get_confluence_page_siblings` | Return sibling pages sharing the same parent. | ### Database tools | Tool | Description | |---|---| | `init_document_db` | Create the SQLite DB and store module-level metadata. | | `store_feature` | Parse and store one PRD feature (and its menus) into the DB. | | `store_feature_from_file` | Same as `store_feature` but reads the payload from a local JSON file. | | `raw_query_exec` | Execute a raw SQL statement against the DB. Read-only by default; pass `write=True` for DML/DDL. Results capped at 200 rows. | ### Render tools | Tool | Description | |---|---| | `render_srs_docx` | Render an SRS Word document from the DB. | | `render_urs_docx` | Render a URS Word document from the DB. | --- ## Workflow ``` init_document_db(db_path, meta) ↓ get_confluence_page_to_file(page_id, output_path) ← subagent fetches its page to disk ↓ store_feature(db_path, feature_data) ← subagent stores parsed data ↓ (up to 5 parallel subagents, one per feature page) render_srs_docx(template_path, output_path, db_path) or render_urs_docx(template_path, output_path, db_path) ``` The main agent sets `service_order`. Each subagent sets `feature_order` from its sibling position in the Confluence page tree. Menu order…