Storywright MCP
Storywright MCP
Ein Multi-Agenten-MCP-Server zum Schreiben von Büchern für Cursor, Claude Desktop, OpenCode oder jeden Host, der MCP über stdio unterstützt. Er kombiniert eine geschützte Kapitel-Pipeline (Autor → Lektor → konfigurierbare Drittanbieter-Durchläufe → Freigabe), JSON/Markdown-Projekte auf der Festplatte, Planung der Buch-Bibel, Kontinuitätsverfolgung, Manuskriptsuche, Marker-Scans, Kontext-Budgetierung für vorherige Kapitel sowie Export- und Diff-Hilfsmittel.
Der goldene Pfad (erste Stunde)
Installieren (aus diesem Repo):
cd C:\Apps\claude_plugins\storywright-mcp uv sync --extra devAPI-Schlüssel festlegen (Benutzer-Umgebung oder MCP
env-Block):ANTHROPIC_API_KEYund/oderANTHROPIC_AUTH_TOKEN— erforderlich für Autor/Lektor/Drittanbieter-Durchläufe (MiniMax verwendet normalerweise Bearer +ANTHROPIC_BASE_URL).
MCP in Cursor registrieren — erstellen oder bearbeiten Sie die
mcp.json:Bereich
Pfad (Windows)
Benutzer (alle Workspaces)
%USERPROFILE%\.cursor\mcp.jsonNur dieses Repo
<repo>\.cursor\mcp.jsonFügen Sie
storywrightin das bestehende"mcpServers"-Objekt ein, falls die Datei bereits andere Server enthält.Anthropic API-Schlüssel (Geheimnisse über Windows-Umgebung — Benutzer-Umgebungsvariablen festlegen, dann darauf verweisen):
{ "mcpServers": { "storywright": { "command": "uv", "args": ["run", "--directory", "C:/Apps/claude_plugins/storywright-mcp", "storywright-mcp"], "env": { "ANTHROPIC_API_KEY": "${env:ANTHROPIC_API_KEY}", "STORYWRIGHT_PROJECTS_ROOT": "C:/Users/you/Documents/writing", "STORYWRIGHT_ANTHROPIC_MODEL": "claude-sonnet-4-20250514" } } } }MiniMax (identisch mit Ihrer funktionierenden Shell — Bearer + Basis-URL + Modell):
{ "mcpServers": { "storywright": { "command": "uv", "args": ["run", "--directory", "C:/Apps/claude_plugins/storywright-mcp", "storywright-mcp"], "env": { "ANTHROPIC_BASE_URL": "https://api.minimax.io/anthropic", "ANTHROPIC_AUTH_TOKEN": "${env:ANTHROPIC_AUTH_TOKEN}", "STORYWRIGHT_ANTHROPIC_MODEL": "MiniMax-M2.7", "STORYWRIGHT_PROJECTS_ROOT": "C:/Users/you/Documents/writing" } } } }Legen Sie
ANTHROPIC_AUTH_TOKENin den Windows-Umgebungsvariablen (Benutzer) fest oder betten Sie den Wert nur vorübergehend ein, wenn Sie das Risiko in Kauf nehmen, dass er auf der Festplatte gespeichert wird. Bearbeiten SieSTORYWRIGHT_PROJECTS_ROOT, um festzulegen, wobook_projects/gespeichert werden soll.MCP neu laden: Befehlspalette → “Cursor: Reload MCP Servers” (oder Cursor neu starten).
uvmuss imPATHdes Terminals vorhanden sein, in dem Cursor die Server startet.Führen Sie im Chat die Tools in der richtigen Reihenfolge aus:
check_environment— bestätigt Schlüssel + Modell + Version.`create_book_project(project_name="mein-roman", book_title="Mein Roman", third_agents=["comedy","pacing"])
plan_book()… durch die Phasen (optional) oder direkt zu den Kapiteln springen.add_chapter/add_characternach Bedarf.get_pipeline_status— zeigt das genaue nächste Tool pro Kapitel an.Pro Kapitel:
start_chapter→run_writer_agent→run_editor_review→ jedesrun_third_agent→approve_chapter.
Wichtige Artefakte:
briefs/revision_queue.json— Notizen ausrequest_revision(der Autor-Prompt liest diese).reports/chapter-NN-editor-meta.json— geparstes Urteil + Meta-Block vom Lektor.manuscript/chapter-NN-draft.prev.md— Backup vor jedem Überschreiben durch den Autor; verwenden Siediff_chapter.EXPORT-manuscript.md— optionale Ausgabe vonexport_manuscript.
Related MCP server: Nyxdoc
Funktionen
Strikter Workflow: Drittanbieter-Durchlauf erst nach dem Lektor; die Freigabe erfordert alle konfigurierten Drittanbieter-Agenten, sofern nicht
force=truegesetzt ist.Pipeline-Hinweise:
get_pipeline_statuslistet den nächsten Tool-Aufruf pro Kapitel auf.API-Bereitschaft:
check_environmentvalidiert Anthropic-Anmeldedaten (ANTHROPIC_API_KEYund/oderANTHROPIC_AUTH_TOKEN), bevor Sie eine Sitzung starten.Budget für vorherige Prosa: Der Autor bezieht den Text der letzten freigegebenen Kapitel bis zu konfigurierbaren Wort-/Kapitel-Limits ein (spart Kontext im Vergleich zum Laden des gesamten Buches).
Wiederholungsversuche: Vorübergehende Anthropic-Fehler (429/5xx, Timeouts) werden mit Backoff wiederholt (
STORYWRIGHT_ANTHROPIC_MAX_RETRIES).Strukturierte Lektor-Meta: Lektor-Berichte sollten mit
---STORYWRIGHT_META_START---…END---enden; geparstes JSON neben dem Markdown-Bericht.Export / Diff:
export_manuscript,diff_chapter(Entwurf vs.prev.md).Ressourcen:
storywright://project/*,storywright://meta/version.
Installation
cd storywright-mcp
uv sync --extra devUmgebung
Variable | Zweck |
| Optional bei Verwendung von Bearer unten — Aufrufe für Autor/Lektor/Drittanbieter |
| Optional — Bearer-Token (gleiches Muster wie Claude Code; MiniMax verwendet dies oft anstelle von |
| Optional — z. B. |
| Modell-ID (z. B. |
| Übergeordnetes Verzeichnis; Projekte landen in |
|
|
| Maximale Wörter der zuvor freigegebenen Prosa, die in den Autor-Prompt einfließen (~Standard 12000) |
| Maximale Anzahl der berücksichtigten vorherigen Kapitel (~Standard 8) |
| Wiederholungsversuche bei vorübergehenden API-Fehlern (~Standard 2) |
| Basis-Verzögerung zwischen Wiederholungsversuchen (~Standard 2.0) |
MiniMax (Anthropic-kompatibles Gateway)
Storywright verwendet das offizielle anthropic Python SDK, das ANTHROPIC_BASE_URL und ANTHROPIC_AUTH_TOKEN genauso liest wie Claude Code. Spiegeln Sie Ihre env-Einstellungen aus ~/.claude/settings.json in den Storywright MCP env-Block in Cursor (oder der Shell), zum Beispiel:
ANTHROPIC_BASE_URL=https://api.minimax.io/anthropicANTHROPIC_AUTH_TOKEN= Ihr MiniMax-Token (Bearer)STORYWRIGHT_ANTHROPIC_MODEL=MiniMax-M2.7(oder die Modell-ID, die Ihr Anbieter erwartet)
Committen Sie keine API-Schlüssel; bevorzugen Sie OS-Umgebungsvariablen oder Cursor-Geheimnisse.
Ausführen (stdio)
uv run storywright-mcp
uv run python -m storywright_mcpClaude Desktop / OpenCode
Verwenden Sie denselben command / args wie in Cursor, falls Ihre Anwendung MCP-stdio-Server unterstützt.
Typischer Workflow
create_book_project(..., third_agents=[...])oderload_book_project("C:/absolut/.../book_projects/mein-buch")plan_book()… (optional)start_chapter(1)→run_writer_agent(1)→run_editor_review(1)→run_third_agent(1, …)→approve_chapter(1)
Verwenden Sie get_pipeline_status, wann immer Sie den Überblick verlieren.
CLI
uv run storywright-mcp agents # list third-pass agents
uv run storywright-mcp smoke # ping Anthropic/MiniMax (tiny token use)
uv run storywright-mcp smoke --with-book # temp folder + new project + chapter 1 writer (full pipeline chunk)Namen wie run_editor_review(1) sind MCP-Tools (verwendet aus Cursor/Chat), keine Shell-Befehle. Von PowerShell aus können Sie dieselbe Logik nach load_book_project aufrufen:
uv run python -c "from storywright_mcp import workflow; workflow.load_book_project(r'C:/path/to/book_projects/your-book'); print(workflow.run_editor_review(1))"MiniMax testen (oder einen beliebigen Anthropic-kompatiblen Proxy)
Legen Sie in PowerShell dieselben Variablen wie in ~/.claude/settings.json fest und führen Sie dann smoke aus dem Repo aus (Anmeldedaten bleiben nur in Ihrer Shell):
$env:ANTHROPIC_BASE_URL = "https://api.minimax.io/anthropic"
$env:ANTHROPIC_AUTH_TOKEN = "<your-token>"
$env:STORYWRIGHT_ANTHROPIC_MODEL = "MiniMax-M2.7"
cd C:\Apps\claude_plugins\storywright-mcp
uv run storywright-mcp smokeWenn Sie STORYWRIGHT_SMOKE_OK in der Ausgabe sehen, funktionieren Routing und Authentifizierung. Verwenden Sie smoke --with-book, um create_book_project → run_writer_agent mit Live-Inferenz zu bestätigen (kostet mehr Token; Dateien landen in einem temporären storywright-smoke-* Verzeichnis).
CI
GitHub Actions führt ruff + pytest bei Push/PR aus (.github/workflows/ci.yml).
Lizenz
MIT
Available Tools
35 toolsadd_chapterC
Register a chapter outline.
Inputs: chapter_num (required), title (required), target_words. Returns: result
add_characterC
Add a character and continuity entry.
Inputs: name (required), role (required), description, voice_notes, +1 more. Returns: result
add_deathC
Schedule a canonical death.
Inputs: character (required), chapter (required), circumstances (required), death_style. Returns: result
add_established_factD
Inputs: fact (required), chapter (required), source. Returns: result
add_inventory_itemD
Track an inventory item.
Inputs: name (required), initial_holder (required), description, acquired_chapter. Returns: result
add_locationD
Inputs: chapter (required), location (required), description. Returns: result
add_running_gagD
Register a running gag.
Inputs: name (required), owner (required), setup_chapter (required), description, +1 more. Returns: result
approve_chapterA
Approve chapter; updates continuity. Requires all configured third passes unless force=true.
Inputs: chapter_num (required), force. Returns: result
check_environmentA
Verify ANTHROPIC_API_KEY and show model / prior-chapter budget / Storywright version.
Inputs: no named parameters. Returns: result
create_book_projectC
Create a new book project under book_projects/ (or STORYWRIGHT_PROJECTS_ROOT). Loads the new project.
Inputs: project_name (required), book_title (required), genre, authors, +2 more. Returns: result
diff_chapterC
Diff current draft vs .prev.md snapshot from last writer overwrite.
Inputs: chapter_num (required), max_lines. Returns: result
export_manuscriptC
Concatenate approved chapters into one markdown file at project root.
Inputs: output_filename. Returns: result
fire_gagD
Inputs: gag_name (required), chapter (required). Returns: result
get_book_bibleD
Readable bible markdown.
Inputs: no named parameters. Returns: result
get_chapter_statusC
Inspect one chapter.
Inputs: chapter_num (required). Returns: result
get_continuity_logC
JSON continuity log.
Inputs: no named parameters. Returns: result
get_inventoryD
Inputs: no named parameters. Returns: result
get_living_charactersD
Inputs: no named parameters. Returns: result
get_pipeline_statusB
Next MCP tool to call per chapter (guarded pipeline hints).
Inputs: no named parameters. Returns: result
get_project_statusB
Markdown table of chapters, statuses, editor verdicts, third-pass completion.
Inputs: no named parameters. Returns: result
get_running_gagsD
Inputs: no named parameters. Returns: result
list_third_agentsA
List built-in third-pass agents.
Inputs: no named parameters. Returns: result
load_book_projectB
Load an existing project from disk (prefer absolute paths).
Inputs: project_path (required). Returns: result
load_last_book_projectA
Load the last successfully opened project from ~/.storywright/last_project.json if valid.
Inputs: no named parameters. Returns: result
mark_character_deadD
Inputs: character_name (required), chapter (required), cause (required). Returns: result
plan_bookC
Phased book bible planning (identity→…→tone); completes with sync to project config.
Inputs: phase, data, reset, status. Returns: result
request_revisionC
Send chapter back to writer with notes.
Inputs: chapter_num (required), notes (required). Returns: result
run_editor_reviewC
Editor pass after writer.
Inputs: chapter_num (required). Returns: result
run_third_agentB
Third-pass reviewer (comedy, pacing, …). Repeat until all project.third_agents covered.
Inputs: chapter_num (required), agent_type. Returns: result
run_writer_agentA
Draft chapter via Claude (DRAW → AWAITING_EDITOR). Requires ANTHROPIC_API_KEY.
Inputs: chapter_num (required), chapter_brief. Returns: result
scan_manuscript_markersA
Find TODO/FIXME/DRAFT/TBD/XXX markers in manuscript markdown.
Inputs: no named parameters. Returns: result
search_manuscriptC
Substring search across manuscript/*.md.
Inputs: query (required), file_glob. Returns: result
start_chapterB
Open drafting for a chapter (NOT_STARTED → DRAFT).
Inputs: chapter_num (required). Returns: result
transfer_itemD
Inputs: item_name (required), new_holder (required), chapter (required). Returns: result
update_planC
Patch book_bible.json; may sync characters/deaths/gags into project.
Inputs: section, changes. Returns: result
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 35 tools
Many tool descriptions are blank or minimal (e.g., add_location, fire_gag, get_inventory), and several tools have overlapping purposes (e.g., add_death vs mark_character_dead, add_running_gag vs fire_gag). This makes it difficult for an agent to distinguish between tools.
Tool names follow a verb_noun pattern but use a wide variety of verbs (add, approve, check, create, diff, export, fire, get, list, load, mark, plan, request, run, scan, search, start, transfer, update). This variety, while not chaotic, lacks a strong consistent theme.
35 tools is far above the recommended range of 3-15 for a well-scoped set, and significantly exceeds the 25+ threshold. The high count suggests over-specialization or redundant functionality.
The tool set covers many aspects of story writing (chapters, characters, inventory, gags, planning, etc.) but lacks basic CRUD operations such as delete or update for most resources, and has redundant tools (e.g., add_death and mark_character_dead). Some obvious gaps in lifecycle management are present.
Maintenance
Related MCP Connectors
Agentic AI book creator: plan, write, illustrate, narrate, and publish books from any MCP client.
Project management shared by people and AI agents, with persistent project state through MCP.
Publish Git-backed multilingual novels with agents, safe layouts, reviews, and author approval.
MCP Server for Slima - AI Writing IDE for Novel Authors with AI Beta Reader.
Related MCP Servers
- AlicenseAqualityDmaintenanceA local MCP server for maintaining internal consistency in fiction writing, with constraint-based fact checking, branching, and author-oracle conflict resolution.27MIT
- AlicenseNot gradedqualityBmaintenanceMCP server for Nyxdoc, a document system where humans and external agents collaborate on documents with version history, agent to-dos, and workspace permissions.MIT
- FlicenseNot gradedqualityDmaintenanceMCP server enabling AI agents to collaborate in shared rooms with a document edited via compare-and-swap optimistic concurrency, plus a chat channel and change deltas.-
- AlicenseNot gradedqualityBmaintenanceAn MCP server that lets multiple AI coding agents share state, preserve context across sessions, and coordinate via a knowledge graph, messaging, and branch-preserving checkpoint/resume with conflict handling.76 npm1Apache 2.0