dsh-novel-writer
Related Servers
Alternatives to dsh-novel-writer
No user-submitted related servers found.
Related Servers
- AlicenseNot gradedqualityCmaintenanceExposes 30+ novel-writing tools over stdio or HTTP so external agents such as Claude Code or WorkBuddy can use their own models and API keys to read chapters, write prose, manage characters, foreshadowing, story arcs and worldbuilding, run local semantic search, and launch review sub-agents. Supports one-click enabling with configurable port, token, and approval mode.AGPL 3.0
- AlicenseNot gradedqualityAmaintenanceEnables AI agents to draft long-form web novels with persistent, disk-backed memory, assembling a pre-writing task brief from structured settings, outlines, foreshadowing ledgers, and timelines, then committing post-chapter fact increments. It also audits pacing, checks per-chapter six-dimension consistency, gates commits on unresolved review findings, and can replay the commit chain to rebuild state when records and manuscripts disagree.1MIT
- AlicenseNot gradedqualityAmaintenanceEnables AI-driven long-form novel creation and management, including chapter generation, character and timeline tracking, semantic memory retrieval, version savepoints, and deep consistency checking across multiple projects through MCP tools, with support for local LM Studio or any OpenAI-compatible API.15MIT
- AlicenseAqualityBmaintenanceEnables authors to automate publishing and managing their own Qimao (七猫) novel author-backend works through an MCP client, covering login and status, book creation and metadata, chapter add/edit/delete and batch publishing, short stories, read-only statistics and income, plus a local manuscript library, originality checks, and a genre knowledge base. Write operations follow a two-stage preview-then-confirm flow and it runs over stdio or Streamable HTTP with 30 tools and 8 read-only resources.3058 npmMIT
- AlicenseAqualityBmaintenanceEnables human-like non-fiction authoring by training custom voices, applying tone presets, auditing drafts for AI tells, and managing dictionaries, all locally.19199 npm9MIT
- AlicenseNot gradedqualityAmaintenanceLocal-first markdown vault with a built-in MCP server (streamable HTTP). 16 tools and 2 resources for Claude Code / Desktop / Cursor: read/write/search plus context_for_query, find_orphans, weekly_digest, compare_notes, semantic_outline. Per-folder agent permissions, LanceDB vectors, local Xenova ONNX embedder swappable to Ollama. Single Bun binary. AGPL.34AGPL 3.0
TDQS
Scored across 21 tools
Descriptions go to unusual lengths to draw boundaries (style_check vs style_report vs sentence_analysis vs fix_plan each explicitly state their distinct question, and lexicon explicitly disowns courtesy of continuity_check). The remaining overlap is conceptual rather than lexical: novel_outline, novel_settings, novel_plot and novel_lexicon all store per-book metadata, and an agent must read long text to pick correctly. Mostly distinct, with a couple of clusters that could still be confused.
Every tool shares the novel_ prefix and snake_case, which gives a predictable family. Verb style is inconsistent though: verb-first (novel_read, novel_delete_book, novel_new_chapter, novel_import) coexists with noun-only names (novel_books, novel_chapters, novel_outline, novel_settings) and create/delete use different patterns (new_chapter vs delete_book).
21 tools for a single novel-writing workflow is on the heavy side; the writing surface, four separate analysis engines, a config tool, and a diagnostics tool all earn some place but push into the 16-25 'heavy' band. A few (novel_sentence_config, novel_diagnose) feel like maintenance extras rather than core writing capabilities.
Coverage is broad — create chapter, read, import, settings, foreshadowing, summaries, style/continuity auditing, semantic search, deletion with trash. But the lifecycle is asymmetric: there is no tool to update/append/rewrite an existing chapter's body (only novel_new_chapter accepts initial text), no chapter delete/rename/move, and no book create/rename, leaving real dead ends for an agent asked to edit content.