story-architect-mcp
You can use story-architect-mcp as an MCP server for end-to-end novel project management, writing, continuity auditing, analysis, and export.
Manage projects: list/switch/set projects, initialize with genre/POV/tense metadata, view project info and writing stats, and generate an HTML dashboard.
Author manuscripts: write/overwrite chapters with auto-snapshots, append scenes, and read chapters with word counts and beat headings.
Rescue messy projects: scan files/encodings/duplicates, classify content, export an AI layout brief, apply a validated AI layout verdict, and auto-refactor into standard manuscript/bible/outline/drafts structure with dry-run previews.
Protect data: create snapshots, rollback to snapshots, prune old snapshots, and rely on atomic writes/locks for safety.
Track continuity: log/resolve plot holes, track Chekhov setups/payoffs/unfired items, track character state/location/inventory/secrets, detect timeline conflicts, and render Mermaid timelines.
Analyze craft: pacing/tension, voice drift, sentiment/tone/emotional arcs, and quick emotion tracking on arbitrary text.
Build story knowledge: extract entities to the bible, map character relationships, and query token-budgeted context from graph memory/semantic search.
Generate and export: create optimized writing prompts and export manuscripts to Markdown, HTML, EPUB, or DOCX; PDF is not directly supported.
Use MCP resources/prompts for live status, config, timeline, holes, foreshadowing, relationships, emotions, character/world bible entries, manuscript chapters, and guided workflows like write-next-chapter, continuity-audit, and rescue-project.
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., "@story-architect-mcp Find any timeline inconsistencies in my draft"
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.
💡 The "Novels as Codebases" Paradigm
Software Engineering Concept | Novel Architecture Equivalent |
|
Modules & Packages | Arcs & Chapters | Standardized |
Interfaces & Schemas | Character Bible & Lore | Frontmatter-backed Markdown files in |
Compiler & Linter | Continuity & Pacing Auditing |
|
Bug Tracker | Plot Hole & Chekhov's Gun Registry |
|
Git & Rollback | Point-in-Time Snapshots |
|
Dependency Injection | Context Budgeting |
|
Related MCP server: bible-ecrivain
🆕 What's New in v0.7.0
AI-assisted layout analysis ("AI in-the-loop") — recognition is no longer capped by regex rules.
story_export_layout_brief(tool #31) packages raw evidence — file tree, word counts, content excerpts, plus the heuristic profile as a flagged-not-trusted opinion — for the AI agent in your session to analyze by context: chapter titles without the word "chapter" ("I. Mở màn", "Ngày 17-3"), author-named files (01.txt,t4-bai-viet), epistolary/diary formats, several interleaved novels.story_apply_layout_verdict(tool #32) — the AI submits its verdict as JSON (layout kind, chapter boundaries by line number, folder→arc mapping, per-file classification). The server validates strictly (paths inside the project, destinations limited tomanuscript/ | bible/ | outline/ | drafts_raw/, chapter start lines must exist) and stores it in.story/layout-verdict.json.Refactor & scan prefer the AI verdict:
story_auto_refactor_structure(auto_profile) splits by the AI's chapter boundaries — the regex no longer needs a keyword;story_scan_messy_projectshows the AI verdict with a heuristic cross-check warning when they disagree. Safety unchanged: dry-run preview + auto-snapshot; the AI only directs, the server executes. Delete.story/layout-verdict.jsonto fall back to rules.
🆕 What's New in v0.6.0
Layout Profiles — novels written before you install story-architect-mcp now get recognized: the scanner reports how your existing novels are actually organized — chapter files nested in custom arc folders ("Quyển 3", "phan 2", "vol 2"...), flat chapter files, one big file containing the whole novel, or unseen multi-novel trees (multiple private novels in one folder tree). Multilingual chapter numbering is parsed: Arabic ("12"), Roman ("XII"), Vietnamese word numbers ("mười hai", "hai mươi mốt"), and CJK ("第十二章").
auto_profilestrategy (new default forstory_auto_refactor_structure): one big file → split into standardch_XXX.mdchapters by their headings (titles preserved for EPUB/DOCX tables of content; original archived indrafts_raw/); custom arc folders → mapped toarc_XXwithout renaming your files; flat chapters → renumbered. Everything stays dry-run preview + auto-snapshot protected.Multi-novel detection:
story_scan_messy_projectflags folders that look like separate novels sharing one tree, so you can pointstory_set_projectat each.
🆕 What's New in v0.5.0
Timeline Absolute Dates:
"2025-01-01"≡"2025-01-01 00:00"in omnipresence checks (format differences no longer hide conflicts); new conflict #4 flags day↔chapter order inversions (with a flashback heads-up); Mermaid diagrams sort by relativeOrder → parsed date → chapter;addEventfeedback tells you whether an ISO date joins conflict detection or is just an in-world display string.BM25 Search Ranking:
story_query_contextterm-level matches are now ranked by BM25 (zero-dep) — rare phrases ("phượng hoàng giáng thế") outweigh common filler words, while exact-name/alias/fuzzy matches keep precedence.story_prune_snapshots(tool #30): safely clean up old snapshots —keepLast(default 10) + optionalolderThanDays, dry-run preview beforeconfirm: true,keepLast < 3requires explicit confirm, orphaned entries are cleaned from the index, and the report shows MB/KB freed.
🆕 What's New in v0.4.0
Auto-Stale Index: The knowledge graph cache (
.cbm/index.json) now carries a stat fingerprint of its sources; editing bible files outside the tools (by hand, in another editor) is detected automatically — no more manualrebuildIndexcalls.State History Diff:
story_track_character_stateaction: "history"now shows what changed between consecutive milestones — inventory lost/acquired (−🎒/+🎒), secrets learned (+🗝️), status/condition/location changes — directly in the report.Sentiment
lexicon-v3: unaccented negators/intensifiers ("khong vui", "rat vui", "vo cung") now match exactly — unaccented prose no longer gets muted polarity. (Method label is transparent.)Cross-Process Lock Regression Test: the on-disk lock layer is now protected by a 4-process × 10-RMW contention test (148 unit tests total).
EPUB Cover + DOCX TOC: exports gain an SVG title cover (metadata-driven, zero-dep) and a real Word TOC field with outline levels for the Navigation pane.
🆕 What's New in v0.3.0
Atomic Writes + Advisory File Locking: Every
.story/*.jsonstate file is written atomically (temp-file + rename — readers never see a half-written file), and all read-modify-write operations are serialized through a two-layer lock (in-process mutex + on-disk lock dir with stale-TTL and fail-fast timeout). Safe for multiple MCP clients writing to the same novel.Project Registry &
story_list_projects: Server now reusesStoryProjectinstances across switches, and a new tool lists every project opened in the session.Diacritics-insensitive + Fuzzy Graph Matching: Character/relationship lookups normalize Vietnamese diacritics (
Trăng≡trang) and fall back to Levenshtein fuzzy match (±1–2 characters) — queries mistyped by the LLM still resolve.Transparent Lexical Analysis:
story_analyze_sentimentnow reports its method (lexicon-v3) and warns when coverage is too low to trust metaphorical/ironic readings.Richer EPUB/DOCX Export: EPUB3 gains
dcterms:modified, richer CSS (justified text, hyphenation, per-section page breaks); DOCX gains page breaks between chapters, justified Normal style, fulldocProps(creator, language, app info), and Times New Roman typography.
✨ Key Features
🧹 1. Messy Project Rescue & Auto-Refactoring
Smart File Classifier (
story_scan_messy_project): Scans unorganized manuscript folders, auto-detects character encodings (UTF-8, Windows-1252, ISO-8859-1), computes content similarity matrices, and tags files (Manuscript,Lore,Notes,Outline) with confidence scores. v0.6.0 adds a Layout Profile section — recognizes how the novel was arranged before installation (custom arc folders, flat chapters, single big file, separate novels in one tree) with multilingual chapter numbers.Automated Refactoring (
story_auto_refactor_structure): Reorganizes scattered files into a clean project structure with safe dry-run previews (confirm: false). v0.6.0 adds theauto_profilestrategy: a single-file novel is split intomanuscript/arc_01/ch_XXX.mdby its chapter headings (Vietnamese word numbers, Roman, Arabic, CJK supported), original archived intodrafts_raw/; custom arc folders map toarc_XXcontent-preserving.Snapshot & Rollback Protection (
story_snapshot/story_rollback): Creates automatic point-in-time state backups prior to file operations.
🔍 2. Continuity Auditing & Plot Hole Tracking
Plot Hole Manager (
story_log_plot_hole/story_resolve_plot_hole): Tracks unresolved plot holes, severity levels, and proposed fixes directly in.story/unresolved_holes.json.Chekhov’s Gun Tracker (
story_log_setup/story_log_payoff): Ensures planted clues or foreshadowed events are resolved before the story concludes.Timeline Conflict Detector & Parallel Subplots (
story_detect_timeline_conflicts): Audits character omnipresence/teleportation conflicts, event order, and absolute dates across parallel storyline threads, generating interactive Mermaid Flowchart Diagrams.Character State & Inventory Tracker (
story_track_character_state): Tracks characters' geographic location, physical condition, inventory items, and acquired secrets chapter-by-chapter to eliminate continuity errors.
✍️ 3. Safe Manuscript Authoring & Progress Tracking
Direct Chapter Authoring (
story_write_chapter): Saves or updates chapter drafts with automatic pre-write snapshots and real-time word count tracking.Scene Appending (
story_append_scene): Seamlessly appends new scenes and beat breaks without risking the loss of existing chapter text.Manuscript Reader (
story_read_chapter): Retrieves chapter text alongside extracted headings, beats, and statistics.
🧠 4. Knowledge Graph & Story Bible Integration
Automatic Entity Extraction (
story_extract_entities_to_bible): Parses chapter drafts to automatically create structured Markdown profiles inbible/characters/andbible/world/.Dynamic Relationship Graph (
story_map_relationships): Tracks changing relationships between characters across chapters into.story/relationships.json— can be auto-detected from manuscript co-occurrences or updated manually.Token-Budget Context Querying (
story_query_context): Generates optimized context packages for LLMs by combining graph memory traversal with token budget constraints.
📈 5. Pacing, Voice, Sentiment & Analytics Dashboard
Pacing Inspector (
story_analyze_pacing): Measures Action / Dialogue / Description distribution and scene tension curves across chapters.Voice Drift Monitor (
story_analyze_voice): Evaluates sentence complexity, vocabulary richness, POV/tense compliance, and dominant emotions against your.story/style_guide.json.Sentiment & Tone Analyzer (
story_analyze_sentiment/story_track_emotion): Performs lexicon-based emotional arc tracking, polarity calculation, tone classification (8 categories), and tone drift detection across chapters.Visual HTML Dashboard (
story_generate_dashboard): Generates a standalone interactive HTML dashboard (export/dashboard.html) summarizing progress, plot holes, and story assets.Writing Statistics (
story_stats): Real-time word counts, writing velocity, and estimated project completion dates.
📄 6. AI Prompt Generator & Manuscript Export
Context-Rich Prompt Builder (
story_generate_writing_prompt): Automatically compiles lore, recent chapter endings, outline beats, character states, and active Chekhov's guns into an optimized writing prompt.Multi-Format Export (
story_export): Compiles manuscript files into Markdown, HTML, EPUB, or DOCX formats with custom metadata and Table of Contents. (For PDF, export to HTML and print-to-PDF from a browser.)
📁 Standard Project Architecture
story-architect-mcp organizes novel projects into a standardized layout:
my-epic-novel/
├── .story/ # Project metadata & state tracking
│ ├── config.json # Title, Author, Genre, POV, Tense
│ ├── status.json # Word counts & progress tracking
│ ├── timeline.json # Event chronology, dates & parallel threads
│ ├── unresolved_holes.json # Active plot hole registry
│ ├── character_states.json # Location, condition & inventory timeline
│ ├── relationships.json # Character relationship matrix
│ ├── foreshadowing.json # Chekhov's gun tracker (Setups & Payoffs)
│ ├── style_guide.json # Voice, tone, sentence rules & reference excerpts
│ └── snapshots/ # Version snapshots for rollback protection
├── .cbm/ # Knowledge Graph cache & index
│ └── index.json # Precomputed entity/relationship index
├── bible/ # Story Bible & Worldbuilding Lore
│ ├── characters/ # Character profiles with YAML frontmatter
│ ├── world/ # Locations, factions, magic/tech systems
│ └── subplots/ # Subplot tracking & arc objectives
├── manuscript/ # Official Manuscript Drafts
│ └── arc_01/
│ ├── ch_001.md
│ └── ch_002.md
├── outline/ # Master Outline & Chapter Beats
│ ├── synopsis.md # High-level story synopsis
│ ├── themes.md # Themes & key motifs
│ └── arc_01/
│ ├── overview.md # Arc overview
│ └── ch_001_outline.md # Scene beats per chapter
└── drafts_raw/ # Loose, unorganized writing snippets⚙️ MCP Client Configuration (Manual Setup)
Nếu bạn muốn cấu hình thủ công thay vì chạy npx story-architect-mcp setup:
💡 Zero-Config Project Switching: Bạn không bắt buộc phải cố định đường dẫn novel project trong tham số khởi động. Khi server chạy, AI có thể tự chọn hoặc chuyển đổi dự án tại runtime bằng tool
story_set_project.
Claude Desktop (claude_desktop_config.json)
{
"mcpServers": {
"story-architect": {
"command": "npx",
"args": ["-y", "story-architect-mcp"]
}
}
}Antigravity / Cursor / Windsurf / VS Code (mcp.json / cline_mcp_settings.json)
{
"mcpServers": {
"story-architect": {
"command": "npx",
"args": ["-y", "story-architect-mcp"]
}
}
}🛠️ MCP API Reference
1. MCP Tools (32 Tools)
🔹 Project & Structure Management
Tool Name | Key Parameters | Description |
|
| Sets or switches the target novel project directory dynamically at runtime. |
| none | Lists all novel projects opened in this server session (parameter v0.3.0 — project registry + instance reuse). |
| none | Returns status, path, configuration, and word count of the active project. |
|
| Initializes project directory with predefined genre templates. |
| none | Computes total manuscript word count, writing velocity, and estimated completion date. |
|
| Generates a comprehensive interactive visual HTML dashboard ( |
🔹 Manuscript Authoring Suite
Tool Name | Key Parameters | Description |
|
| Writes or overwrites a chapter draft with automatic snapshot and writing progress recording. |
|
| Appends a new scene or beat to an existing chapter draft. |
|
| Reads chapter draft content, word count, and scene beat structure. |
🔹 Rescue & Refactoring Suite
Tool Name | Key Parameters | Description |
|
| Scans unorganized directories, detects encoding, and classifies loose files. |
|
| Refactors messy files into the standard novel structure (supports dry-run). |
|
| Creates a point-in-time state snapshot in |
|
| Restores project state to a designated snapshot. |
|
| Prunes old snapshots (preview by default; requires |
🔹 Continuity & Management Suite
Tool Name | Key Parameters | Description |
|
| Registers an unresolved narrative plot hole or inconsistency. |
|
| Resolves or dismisses a logged plot hole. |
|
| Logs a foreshadowing setup (Chekhov's Gun). |
|
| Marks a foreshadowing setup as paid off. |
| none | Lists all planted foreshadowing items that haven't been resolved yet. |
|
| Tracks character geographic location, status, physical condition, secrets, and inventory timeline. |
🔹 Graph Memory & Context Suite
Tool Name | Key Parameters | Description |
|
| Automatically extracts characters and locations from chapter drafts into |
|
| Builds and updates inter-character relationship matrix across chapters. |
|
| Extracts context packages using knowledge graph memory + vector search. |
🔹 Analysis & Prompt Generator Suite
Tool Name | Key Parameters | Description |
|
| Audits event chronology & character omnipresence across parallel subplots, rendering Mermaid Flowchart diagrams. |
|
| Computes Action / Dialogue / Description ratio and scene tension curves. |
|
| Checks sentence length, vocabulary richness, and POV/tense compliance against style guide. |
|
| Analyzes chapter/arc sentiment, dominant emotions, tone classification, emotional arcs, and detects tone drift. |
|
| Standalone emotion and tone tracker for quick drafting feedback on arbitrary text passages. |
|
| Compiles lore, outlines, recent endings, and style rules into an optimized prompt. |
|
| Compiles manuscript into Markdown, HTML, EPUB, or DOCX formats. |
2. MCP Resources (8 Static & 4 Templates)
Static Resources
Resource URI | Description | MIME Type |
| Live project word counts, progress, and status |
|
| Project settings (Title, Author, Genre, POV, Tense) |
|
| Story timeline events, dates & parallel subplots |
|
| Character locations, physical conditions, and inventory history |
|
| List of unresolved plot holes and continuity warnings |
|
| Unfired Chekhov's guns and foreshadowing setups |
|
| Character relationship matrix and interaction states |
|
| Project-wide cached sentiment and emotional arc summary |
|
Resource Templates
Template URI | Description | MIME Type |
| Profile, frontmatter, and lore for a specific character |
|
| Description, history, and lore for a location or faction |
|
| Latest location, condition, and inventory snapshot for a character |
|
| Manuscript text for a specific chapter in an arc |
|
3. MCP Workflow Prompts (5 Prompts)
Prompt Name | Required Arguments | Workflow Description |
|
| Gathers lore, preceding chapter endings, outline beats, character states, and style rules into an optimized prompt for writing the next chapter. |
|
| Aggregates a character's Bible entry alongside all scene appearances across the manuscript for deep analysis. |
|
| Scans an entire arc to detect timeline errors, term inconsistencies, and unresolved setups. |
|
| Step-by-step guided workflow for scanning, previewing, and refactoring chaotic manuscript folders. |
|
| Generates 3–5 distinct scene execution options based on current outline and plot state. |
🛡️ Data Integrity & Safety Protocol
Writing a novel takes months or years; story-architect-mcp is designed with strict data preservation measures:
Dry-Run Mode First (
confirm: false): All destructive or structural refactoring tools run in Preview mode by default. You can inspect exact proposed file moves and edits before confirming execution (confirm: true).Automated Pre-Refactor & Pre-Write Snapshots: Executing structural changes or overwriting existing chapters automatically triggers snapshots to create a rollback checkpoint prior to file operations.
Transparent File Formats: All metadata is stored as standard JSON in
.story/, and all story content is stored in plain Markdown with YAML frontmatter—ensuring zero vendor lock-in.
📄 License
Distributed under the MIT License. See LICENSE for more information.
Available Tools
32 toolsstory_analyze_pacingAnalyze Pacing & Tension CurveB
Đo lường tỷ lệ Action / Dialogue / Description, đường cong căng thẳng (Tension curve) và cấu trúc nhịp cảnh (Scene beats).
Inputs: arc (required), chapter.
story_analyze_sentimentAnalyze Sentiment & ToneB
Phân tích cảm xúc (sentiment), giọng văn (tone), và emotional arc của chương/arc. Phát hiện tone drift giữa các chương.
Inputs: arc (required), chapter, windowSize, compareToStyleGuide.
story_analyze_voiceAnalyze Writing Voice & DriftB
Phân tích giọng văn (độ dài câu, vốn từ, POV, Tense, cảm xúc chủ đạo) và kiểm tra hiện tượng trôi văn phong (Voice drift) so với style_guide.json.
Inputs: arc (required), chapter.
story_append_sceneAppend Scene to ChapterA
Nối thêm một phân cảnh (scene) vào cuối chương truyện hiện có mà không làm mất nội dung trước đó.
Inputs: arc (required), chapter (required), content (required), sceneHeading.
story_apply_layout_verdictApply AI Layout VerdictA
Nộp phán đoán bố cục (verdict JSON) — kết quả đọc story_export_layout_brief bằng AI. Server XÁC THỰC nghiêm ngặt (đường dẫn phải nằm trong dự án, đích giới hạn trong manuscript/bible/outline/drafts_raw, dòng chương phải tồn tại) rồi lưu vào .story/layout-verdict.json. story_auto_refactor_structure (auto_profile) và story_scan_messy_project sẽ ưu tiên dùng. Xóa file để quay về heuristic.
Inputs: verdict (required), projectPath (required).
story_auto_refactor_structureAuto Refactor Novel StructureB
Phân loại và chuẩn hóa cấu trúc thư mục dự án tiểu thuyết theo layout chuẩn. Hỗ trợ dry-run mode (confirm=false) để preview trước khi thực hiện.
Inputs: projectPath (required), confirm, strategy.
story_detect_timeline_conflictsDetect Timeline Conflicts & Generate Mermaid Parallel TimelineB
Phân tích các mốc thời gian tuyệt đối & tương đối, sự kiện, địa điểm và nhân vật để phát hiện mâu thuẫn timeline (như phân thân xuất hiện ở 2 nơi cùng lúc, đảo ngược thứ tự sự kiện). Hỗ trợ các tuyến truyện song song (Threads/Subplots) và xuất biểu đồ Mermaid trực quan.
Inputs: addEvent.
story_exportExport Story ManuscriptA
Đóng gói và xuất bản toàn bộ tác phẩm thành file Markdown, HTML, EPUB hoặc DOCX kèm mục lục và thông tin tác giả.
Inputs: format, outputPath, includeOutline.
story_export_layout_briefExport Layout Brief for AI AnalysisA
Gói bằng chứng thô của dự án (cây file + trích nội dung + heuristic profile) để BẠN/AI phân tích bố cục bằng ngữ cảnh thay vì quy tắc regex cứng. Luồng: gọi tool này → bạn đọc brief và suy đoán → gọi story_apply_layout_verdict nộp phán đoán. Sau đó story_auto_refactor_structure (strategy auto_profile) sẽ dùng phán đoán của bạn.
Inputs: projectPath (required).
story_extract_entities_to_bibleExtract Entities to BibleA
Phân tích văn bản chương, tự động phát hiện nhân vật và địa danh, tạo đề xuất hoặc tự động tạo các file Markdown trong bible/ với YAML frontmatter chuẩn.
Inputs: arc (required), chapter (required), confirm.
story_generate_dashboardGenerate Visual HTML Story DashboardA
Xuất một trang Dashboard trực quan hóa dạng HTML độc lập tại export/dashboard.html, tổng hợp số từ, tiến độ, danh sách plot holes, Chekhov guns và nhân vật.
Inputs: outputPath.
story_generate_writing_promptGenerate Optimized Writing PromptB
Đọc chương trước + Dàn ý + Lore + Style Guide + Chekhov Guns → Tạo System Prompt gọt giũa hoàn hảo cho lượt viết tiếp theo.
Inputs: arc (required), chapter (required), strategy.
story_get_project_infoGet Current Project InfoA
Xem thông tin dự án tiểu thuyết hiện tại đang được trỏ đến.
Inputs: no named parameters.
story_initInitialize Story ProjectA
Khởi tạo dự án tiểu thuyết mới: tạo cấu trúc thư mục chuẩn (.story/, bible/, manuscript/, outline/...) và metadata ban đầu.
Inputs: name (required), pov, genre, tense, +3 more.
story_list_projectsList Session ProjectsA
Liệt kê mọi dự án tiểu thuyết đã mở trong phiên server (kèm trạng thái khởi tạo và dự án đang active). Dùng story_set_project để chuyển đổi.
Inputs: no named parameters.
story_list_unfiredList Unfired Chekhov GunsA
Liệt kê tất cả các "khẩu súng Chekhov chưa bắn" — chi tiết đã cài cắm nhưng chưa được giải gỡ.
Inputs: no named parameters.
story_log_payoffLog Payoff (Chekhov Gun)A
Đánh dấu một chi tiết cài cắm đã được giải gỡ (payoff) — "khẩu súng Chekhov đã bắn".
Inputs: id (required), payoff (required), payoffChapter (required).
story_log_plot_holeLog Plot HoleB
Ghi nhận một điểm mâu thuẫn hoặc lỗ hổng cốt truyện mới vào hệ thống theo dõi.
Inputs: title (required), description (required), chapters, severity.
story_log_setupLog Setup (Chekhov Gun)C
Đánh dấu một chi tiết cài cắm mới (Chekhov's Gun) — một setup sẽ cần được payoff sau này.
Inputs: setup (required), setupChapter (required), setupLine, importance.
story_map_relationshipsMap Character Relationships GraphA
Phân tích bản thảo và tự động cập nhật Đồ thị quan hệ nhân vật vào .story/relationships.json. Nếu bỏ trống source/target sẽ tự quét toàn bộ manuscript để phát hiện các cặp nhân vật đồng xuất hiện. Mỗi quan hệ mang nhãn nguồn gốc: EXTRACTED (người khẳng định) hoặc INFERRED (máy suy ra).
Inputs: type, source, target, chapter, +2 more.
story_prune_snapshotsPrune Old SnapshotsA
Dọn dẹp các snapshot cũ trong .story/snapshots/ (mỗi snapshot là full-copy nên dễ phình đĩa). Giữ lại N snapshot mới nhất; dry-run preview trước khi confirm. Snapshot mới nhất và backup pre-rollback gần đây luôn an toàn vị trí — chỉ bị xóa khi vượt ngưỡng được chọn.
Inputs: confirm, keepLast, olderThanDays.
story_query_contextQuery Context BudgetB
Trích xuất và tổng hợp Context Budget tối ưu nhất bằng Knowledge Graph (Bible + Relationships + Timeline) kết hợp ngân sách token. Truyền from+to để hỏi đường liên hệ ngắn nhất giữa hai nhân vật.
Inputs: query (required), to, from, maxDepth, +2 more.
story_read_chapterRead Chapter Content & MetadataB
Đọc toàn bộ nội dung của một chương truyện, kèm thống kê số từ và danh sách tiêu đề phân cảnh.
Inputs: arc (required), chapter (required).
story_resolve_plot_holeResolve Plot HoleB
Đánh dấu một plot hole đã được giải quyết hoặc won't-fix.
Inputs: id (required), resolution (required), status.
story_rollbackRollback SnapshotC
Khôi phục dự án về snapshot trước đó từ .story/snapshots/.
Inputs: confirm, snapshotId.
story_scan_messy_projectScan Messy Novel ProjectB
Quét toàn bộ dự án tiểu thuyết lộn xộn: phát hiện trùng lặp, nhận diện encoding, phân loại file vào 4 nhóm (Manuscript, Notes, Lore, Outline) kèm confidence score.
Inputs: path (required), detectDuplicates.
story_set_projectSet Story Project PathA
Thiết lập hoặc chuyển đổi dự án tiểu thuyết đích. Tự động phát hiện và từ chối dự án code (Node.js, Python, Rust, v.v.) để tránh lãng phí tài nguyên. Dùng force=true để bỏ qua kiểm tra.
Inputs: projectPath (required), force.
story_snapshotCreate SnapshotA
Lưu snapshot trạng thái dự án hiện tại vào .story/snapshots/ để có thể rollback khi cần.
Inputs: label, description.
story_statsStory StatisticsA
Thống kê tổng số từ (word count), tốc độ viết (writing velocity), phần trăm hoàn thành mục tiêu, và chi tiết từng arc/chương.
Inputs: no named parameters.
story_track_character_stateTrack & Query Character State, Location & InventoryB
Ghi nhận hoặc truy vấn trạng thái nhân vật theo từng mốc chương (vị trí hiện tại, vật phẩm/vũ khí mang theo, tình trạng thương tích, bí mật đã biết) để đảm bảo tính liên tục (continuity).
Inputs: character (required), state, action, chapter.
story_track_emotionQuick Emotion TrackerB
Phân tích nhanh cảm xúc và giọng văn của một đoạn text. Không cần context dự án — chỉ cần đưa vào đoạn văn cần kiểm tra.
Inputs: text (required).
story_write_chapterWrite or Update Chapter DraftA
Lưu hoặc cập nhật nội dung chương truyện vào manuscript//.md. Tự động snapshot backup an toàn nếu sửa chương cũ và ghi nhận tiến độ viết.
Inputs: arc (required), chapter (required), content (required), title, +1 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 32 tools
Most tools have distinct purposes, but several analysis tools overlap heavily: story_analyze_voice, story_analyze_sentiment, and story_track_emotion all deal with tone/emotion, while story_scan_messy_project, story_auto_refactor_structure, and the layout brief/verdict pair require careful reading to choose correctly. The descriptions help, but an agent can still misselect among these clusters.
Nearly all tools use the story_ prefix with snake_case and a verb_noun pattern (e.g., story_write_chapter, story_log_plot_hole, story_analyze_pacing). Minor deviations like story_init, story_export, story_stats, and story_snapshot are still readable and do not break the convention.
With 32 tools, the surface is heavy for a single MCP server and exceeds the typical well-scoped range of roughly 3-15 tools. Several specialized analysis and layout tools could likely be consolidated without losing core capability.
The server covers project setup, chapter writing/reading, continuity tracking, analysis, export, and snapshot rollback, which is a broad lifecycle for novel architecture. There are minor gaps such as no explicit outline/bible CRUD tools and no dedicated list-open-plot-holes operation, but agents can work around most of these via existing tools.
Maintenance
Related MCP Connectors
MCP Server for Slima - AI Writing IDE for Novel Authors with AI Beta Reader.
MCP server for generating rough-draft project plans from natural-language prompts.
MCP book-writing server: 81 classics, genre recipes, drafting pipelines.
An MCP server that integrates with Discord to provide AI-powered features.
Related MCP Servers
- AlicenseNot gradedqualityFmaintenanceA Model Context Protocol server that manages character knowledge and relationships for creative writing projects, offering semantic search and AI-powered analysis.4MIT
- FlicenseNot gradedqualityDmaintenanceMCP server for managing a writer's bible, a structured and searchable knowledge base of a narrative universe with tools for characters, places, events, and semantic search.-
- AlicenseBqualityDmaintenanceA MCP server that acts as a structural secretary for novel writing, enabling project management, scene checklists, foreshadowing tracking, draw.io import, progress suggestions, and Task Master PRD export.21MIT
- AlicenseAqualityDmaintenanceMCP server that analyzes your writing style to generate personal voice rules, scores drafts for AI slop, and verifies authorship, enabling LLMs to write in your specific voice.7MIT