Skip to main content
Glama

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)

  1. Installieren (aus diesem Repo):

    cd C:\Apps\claude_plugins\storywright-mcp
    uv sync --extra dev
  2. API-Schlüssel festlegen (Benutzer-Umgebung oder MCP env-Block):

    • ANTHROPIC_API_KEY und/oder ANTHROPIC_AUTH_TOKEN — erforderlich für Autor/Lektor/Drittanbieter-Durchläufe (MiniMax verwendet normalerweise Bearer + ANTHROPIC_BASE_URL).

  3. MCP in Cursor registrieren — erstellen oder bearbeiten Sie die mcp.json:

    Bereich

    Pfad (Windows)

    Benutzer (alle Workspaces)

    %USERPROFILE%\.cursor\mcp.json

    Nur dieses Repo

    <repo>\.cursor\mcp.json

    Fügen Sie storywright in 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_TOKEN in 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 Sie STORYWRIGHT_PROJECTS_ROOT, um festzulegen, wo book_projects/ gespeichert werden soll.

    MCP neu laden: Befehlspalette → “Cursor: Reload MCP Servers” (oder Cursor neu starten). uv muss im PATH des Terminals vorhanden sein, in dem Cursor die Server startet.

  4. 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_character nach Bedarf.

    • get_pipeline_status — zeigt das genaue nächste Tool pro Kapitel an.

    • Pro Kapitel: start_chapter → run_writer_agent → run_editor_review → jedes run_third_agent → approve_chapter.

  5. Wichtige Artefakte:

    • briefs/revision_queue.json — Notizen aus request_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 Sie diff_chapter.

    • EXPORT-manuscript.md — optionale Ausgabe von export_manuscript.

Related MCP server: Nyxdoc

Funktionen

  • Strikter Workflow: Drittanbieter-Durchlauf erst nach dem Lektor; die Freigabe erfordert alle konfigurierten Drittanbieter-Agenten, sofern nicht force=true gesetzt ist.

  • Pipeline-Hinweise: get_pipeline_status listet den nächsten Tool-Aufruf pro Kapitel auf.

  • API-Bereitschaft: check_environment validiert Anthropic-Anmeldedaten (ANTHROPIC_API_KEY und/oder ANTHROPIC_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 dev

Umgebung

Variable

Zweck

ANTHROPIC_API_KEY

Optional bei Verwendung von Bearer unten — Aufrufe für Autor/Lektor/Drittanbieter

ANTHROPIC_AUTH_TOKEN

Optional — Bearer-Token (gleiches Muster wie Claude Code; MiniMax verwendet dies oft anstelle von API_KEY)

ANTHROPIC_BASE_URL

Optional — z. B. https://api.minimax.io/anthropic für die Anthropic-kompatible API von MiniMax

STORYWRIGHT_ANTHROPIC_MODEL

Modell-ID (z. B. MiniMax-M2.7 bei Verwendung von MiniMax)

STORYWRIGHT_PROJECTS_ROOT

Übergeordnetes Verzeichnis; Projekte landen in {root}/book_projects/<slug>/

STORYWRIGHT_STATE_DIR

last_project.json für load_last_book_project (Standard ~/.storywright)

STORYWRIGHT_PRIOR_CHAPTERS_MAX_WORDS

Maximale Wörter der zuvor freigegebenen Prosa, die in den Autor-Prompt einfließen (~Standard 12000)

STORYWRIGHT_PRIOR_CHAPTERS_MAX_COUNT

Maximale Anzahl der berücksichtigten vorherigen Kapitel (~Standard 8)

STORYWRIGHT_ANTHROPIC_MAX_RETRIES

Wiederholungsversuche bei vorübergehenden API-Fehlern (~Standard 2)

STORYWRIGHT_ANTHROPIC_RETRY_DELAY_SECONDS

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/anthropic

  • ANTHROPIC_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_mcp

Claude Desktop / OpenCode

Verwenden Sie denselben command / args wie in Cursor, falls Ihre Anwendung MCP-stdio-Server unterstützt.

Typischer Workflow

  1. create_book_project(..., third_agents=[...]) oder load_book_project("C:/absolut/.../book_projects/mein-buch")

  2. plan_book() … (optional)

  3. 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 smoke

Wenn 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 tools
add_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

    C2/5.0

    Scored across 35 tools

    Disambiguation2/5

    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.

    Naming Consistency3/5

    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.

    Tool Count2/5

    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.

    Completeness3/5

    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

    ActivityInactive
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      A
      quality
      D
      maintenance
      A local MCP server for maintaining internal consistency in fiction writing, with constraint-based fact checking, branching, and author-oracle conflict resolution.
      27
      MIT
    • A
      license
      Not graded
      quality
      B
      maintenance
      MCP server for Nyxdoc, a document system where humans and external agents collaborate on documents with version history, agent to-dos, and workspace permissions.
      MIT
    • A
      license
      Not graded
      quality
      B
      maintenance
      An 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 npm
      1
      Apache 2.0