Storywriting-MCP
An MCP server providing 67 tools for AI-assisted storywriting, world-building, character development, screenplay generation in industry formats (Fountain, FDX, PDF), storyboards, and production analytics.
README
Storywriting & Screenplay MCP Server (67 Tools)
A custom Model Context Protocol (MCP) server for AI-assisted storywriting, narrative world-building, character depth development, industry-standard screenplay generation (Fountain, Final Draft .fdx, Courier PDF), visual storyboards, generic outline ingestion, and line production analytics.
Project Structure (Refactored Clean Core Engine)
d:\Studio\MCP -Storywriting\
├── server.py # MCP Server entrypoint (stdio, sse, streamable-http)
├── requirements.txt # Dependencies
├── SETUP_GUIDE.md # Dedicated Claude Connector Setup Guide
├── LLM_COMPATIBILITY.md # ChatGPT, Gemini, Kimi, DeepSeek Guide
└── story_engine/ # Generic Core Engine
├── models.py # Schemas for Story Bible, Screenplay, Storyboards, Pitch Decks
├── storage.py # Storage persistence (.story/ directory)
├── batch_processor.py # Category P: Generic Batch & Pipeline Generator
├── brainstorm.py # Category A: Concept & Brainstorming (4 tools)
├── character.py # Category B: Character Architect & Dynamics (4 tools)
├── world.py # Category C: World-Building & Lore (4 tools)
├── beats.py # Category D: Structural Plotting & Beat Sheets (5 tools)
├── drafting.py # Category E: Interactive Drafting Engine (5 tools)
├── story_doctor.py # Category F: Story Doctor & Continuity (4 tools)
├── screenplay.py # Category G: Screenplay Adaptation & PDF/FDX (4 tools)
├── storyboard.py # Category H: Storyboard & Visual Shotlists (3 tools)
├── dialogue_engine.py # Category I: Character Voice & Dialogue Polish (4 tools)
├── analytics_engine.py # Category J: Screenplay Timing & Analytics (4 tools)
├── directing_engine.py # Category K: Visual Directing, Camera & Audio (5 tools)
├── production_engine.py # Category L: Line Production & Stripboards (4 tools)
├── marketing_engine.py # Category M: Pitch Deck & Marketing Suite (4 tools)
├── writers_room.py # Category N: Writers' Room Mechanics (6 tools)
└── exporters.py # Category O: Multi-Format Exporters & Visual Prompters (5 tools)
🛠️ How to Setup & Install This MCP Server
1. Prerequisite Installation & Python Virtual Environment Setup
- Open PowerShell or Terminal in the project directory:
cd "d:\Studio\MCP -Storywriting" - Create and activate a Python virtual environment:
python -m venv venv .\venv\Scripts\Activate.ps1 - Install required packages:
pip install -r requirements.txt
2. Setting Up in Claude Code / Claude Web (Remote Connector via Ngrok)
To connect Claude Web / Claude Code to your local MCP server:
Step 2A: One-Time Ngrok Authtoken Setup
Authenticate ngrok to resolve remote connection errors:
ngrok config add-authtoken <your-ngrok-authtoken>
Step 2B: Start the MCP Server in Streamable HTTP Mode
Run the server on port 8000:
& "d:\Studio\MCP -Storywriting\venv\Scripts\python.exe" server.py --transport streamable-http --port 8000
(Keep this terminal open!)
Step 2C: Start Ngrok HTTPS Tunnel
In a second terminal window, start ngrok:
ngrok http 8000
Copy the generated https:// forwarding URL (e.g. https://a1b2-34-56-78-90.ngrok-free.app) and append /mcp:
$$\rightarrow \text{\texttt{https://a1b2-34-56-78-90.ngrok-free.app/mcp}}$$
Step 2D: Configure Claude Connector UI
- In Claude Web or Claude Code, open Add custom connector.
- Set:
- Name:
Storywriting & Screenplay Engine - Remote MCP server URL:
https://a1b2-34-56-78-90.ngrok-free.app/mcp
- Name:
- Click Save / Connect. All 67 tools, 4 resources, and 2 prompts will be instantly available in Claude!
3. Setting Up in ChatGPT (GPT-4o)
You can use this MCP server with ChatGPT (GPT-4o / O3-mini) in two easy ways:
Option A: Inside Cursor / Antigravity / Windsurf IDEs (Recommended)
- In your IDE MCP settings, add:
{ "mcpServers": { "storywriting-engine": { "command": "d:\\Studio\\MCP -Storywriting\\venv\\Scripts\\python.exe", "args": ["d:\\Studio\\MCP -Storywriting\\server.py"] } } } - Select GPT-4o or o3-mini in the AI model dropdown.
- ChatGPT will natively execute all 67 screenplay tools, draft prose, and render storyboards!
Option B: Via Open-WebUI / LibreChat / Custom GPT Actions
- Launch the server in HTTP mode (
server.py --transport streamable-http --port 8000). - Open Open-WebUI Settings $\rightarrow$ Tools $\rightarrow$ Add MCP Server URL:
http://localhost:8000/mcp. - Select GPT-4o as your active LLM.
4. Live Integration with VS Code "Better Fountain" Extension
This server natively generates industry-standard Fountain 1.1 screenplay files (.story/screenplay.fountain).
- Install the Better Fountain extension in VS Code.
- Open
d:\Studio\MCP -Storywriting\.story\screenplay.fountain. - Whenever Claude or the MCP engine commits screenplay scenes, Better Fountain instantly updates:
- Live side-by-side formatted screenplay preview
- Real-time page count and scene duration estimates
- Interactive scene outline sidebar
16 Production Tool Categories (67 MCP Tools)
- Category A: Concept & Brainstorming (4 tools):
initialize_story_project,brainstorm_high_concept,develop_thematic_core,generate_title_bank. - Category B: Character Architect & Dynamics (4 tools):
create_character_profile,map_character_relationships,generate_character_backstory,generate_name_bank. - Category C: World-Building & Lore Engine (4 tools):
build_setting_location,define_world_rules,create_faction_or_culture,generate_world_timeline. - Category D: Structural Plotting & Beat Sheets (5 tools):
generate_beat_sheet,weave_subplots,outline_scene,calculate_pacing_and_stakes,import_one_line_orders_file. - Category E: Interactive Drafting Engine (5 tools):
draft_scene_prose,write_dialogue_pass,expand_sensory_details,propose_branching_options,generate_cliffhanger_or_twist. - Category F: Story Doctor & Continuity (4 tools):
check_narrative_continuity,scene_doctor_diagnostic,rebalance_show_vs_tell,analyze_pacing_and_rhythm. - Category G: Screenplay Adaptation & Export (4 tools):
narrative_to_scene_breakdown,generate_fountain_scene,export_screenplay,approve_and_commit_screenplay_scene. - Category H: Storyboard Engine (3 tools):
generate_storyboard_shotlist,update_frame_approval,render_storyboard_html. - Category I: Character Voice & Dialogue Polish (4 tools):
dialect_and_subtext_tuner,dialogue_rhythm_and_meter_analyzer,character_arc_tracker,generate_character_voice_bible. - Category J: Screenplay Timing & Analytics (4 tools):
estimate_screenplay_runtime,character_screen_time_matrix,scene_tension_and_pacing_heat_map,screenplay_table_read_simulator. - Category K: Visual Directing, Camera & Audio (5 tools):
soundtrack_and_audio_cues_designer,color_palette_and_lighting_guide,aspect_ratio_and_lens_advisor,scene_transitional_hook_generator,motif_and_symbolism_tracker. - Category L: Line Production & Stripboards (4 tools):
stripboard_element_breakdown,day_night_location_grouping,vfx_and_stunt_manifest,fountain_syntax_linter. - Category M: Pitch Deck & Marketing Suite (4 tools):
generate_pitch_deck_outline,generate_synopsis_suite,comparable_titles_analyzer,audience_emotional_engagement_predictor. - Category N: Writers' Room Mechanics (6 tools):
pitch_alternative_endings,generate_character_interview,red_herring_and_twist_architect,character_archetype_chemistry_analyzer,magic_or_tech_limitation_auditor,act_climax_escalator. - Category O: Multi-Format Exporters (5 tools):
comic_book_page_script_converter,fountain_to_epub_markdown,subtext_and_unspoken_desire_doctor,world_sensory_palette_builder,storyboard_frame_prompter. - Category P: Generic Batch Execution Engine (2 tools):
ingest_any_outline_file,generate_batch_screenplay.
⚡ Quick Start: Running Local CLI Modes
# Local stdio mode (Claude Desktop, Antigravity, Cursor)
& "d:\Studio\MCP -Storywriting\venv\Scripts\python.exe" server.py --transport stdio
# Streamable HTTP mode (Claude Connectors / Web UI / ChatGPT)
& "d:\Studio\MCP -Storywriting\venv\Scripts\python.exe" server.py --transport streamable-http --port 8000
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
Neon Database
MCP server for interacting with Neon Management API and databases
E2B
Using MCP to run code via e2b.
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.