MCP Server

Active

AGPL-3.0

io.github.writerslogic/scrivener-mcp MCP Server

io.github.writerslogic/scrivener-mcp

Connect your Scrivener manuscripts to Claude and AI assistants—read, write, analyze, and search with 57 tools.

What is the io.github.writerslogic/scrivener-mcp MCP server?

Scrivener MCP is an MCP server that connects Scrivener 3 projects to Claude, ChatGPT, and other AI assistants. It provides 57 tools for document management, writing analysis, content enhancement, semantic search, and character/plot tracking—all without leaving your conversation.

Scrivener MCP lets you manage your entire manuscript workflow through AI conversation. Open a .scriv project and ask Claude to read chapters, analyze pacing, enhance prose, track characters, search by meaning, reorganize scenes, compile drafts, and export to multiple formats. No exporting, no copy-pasting—just direct access to your manuscript with AI-powered analysis and editing.

How to install io.github.writerslogic/scrivener-mcp

Copy-paste configuration for popular MCP clients.

transport: stdio

Config generated by PluginBench — verify against the source before use.

~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "scrivener-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "scrivener-mcp"
      ]
    }
  }
}

Tools & capabilities

Tools this server exposes to the agent.

open_project — Open a .scriv project and make it active
discover_projects — Scan common locations for Scrivener projects
detect_open_project — Detect the project currently open in the Scrivener app (macOS)
get_structure — Browse the binder hierarchy with word counts
read_document — Read document content with optional formatting and pagination
write_document — Replace a document's content with atomic backup
create_document — Create a new text document or folder
update_document — Change title, synopsis, notes, label, status, and custom fields
move_document — Reorganize documents within the binder
delete_document — Move documents to trash
search — Keyword and full-text search across the project
semantic_search — Find passages by meaning using local indexing and AI query interpretation
find_mentions — Locate every occurrence of a name or term with context
analyze_document — AI writing analysis with focus on structure, style, pacing, themes
check_consistency — Project-wide continuity check for plot, characters, or timeline
analyze_writing_style — Style-focused analysis
suggest_improvements — AI-generated improvement suggestions
enhance_content — Suggest specific improvements (filter words, verbs, sentences, sensory details, showing, flow, dialogue, pacing)
generate_content — Generate new prose from a prompt and context
compile_documents — Combine documents into a manuscript with hierarchy and formatting

Use cases

Analyze pacing, structure, and style of chapters in real-time without exporting
Track character consistency and plot threads across your entire manuscript
Search for scenes by meaning (e.g., 'find where the protagonist feels isolated') without keyword matching
Generate targeted prose improvements: eliminate filter words, strengthen verbs, add sensory details, fix dialogue
Compile and export your manuscript to Markdown, DOCX, EPUB, or PDF with formatting preserved

io.github.writerslogic/scrivener-mcp MCP server FAQ

What is Scrivener MCP?

Scrivener MCP is an MCP server that connects your Scrivener 3 projects directly to Claude, ChatGPT, and other AI assistants. It provides 57 tools for reading, writing, analyzing, and searching your manuscripts without exporting or copy-pasting.

Is it free?

Yes. The server itself is free and open-source. Writing analysis, generation, and semantic search optionally use AI providers (Anthropic, OpenAI, or OpenRouter); document management, search, and analysis work offline with no API key required.

How do I install it in Claude Desktop or Cursor?

Run `npm install -g scrivener-mcp`, then restart Claude Desktop. For other clients, run `npx scrivener-setup` to auto-configure, or manually add it via `claude mcp add -s user scrivener -- npx scrivener-mcp`.

Does it require authentication?

No authentication is required to use the server. Optional AI features (analysis, generation, semantic search) use API keys from Anthropic, OpenAI, or OpenRouter if configured; the server checks environment variables, ~/.env, and macOS Keychain automatically.

What Scrivener versions does it support?

Scrivener 3 on macOS, Windows, and Linux. The server does not require the Scrivener app to be running; it reads and writes .scriv project files directly.

Can I use it offline?

Yes. Document management, keyword search, deterministic analysis, and character/plot tracking work entirely offline. Semantic search and AI-powered writing analysis optionally use configured providers; if none are set, those features are unavailable.

README (reference)

Source of truth, from the repository.

<img src="https://raw.githubusercontent.com/writerslogic/scrivener-mcp/main/assets/logo-black.svg" alt="Scrivener MCP logo" width="120" align="left"> <h1>Scrivener MCP</h1> The definitive MCP server for Scrivener — connect your novels, screenplays, and manuscripts to Claude, ChatGPT, and any AI assistant. 53 tools: document management, writing analysis, content enhancement, offline semantic search, and character/plot tracking.

<a href="https://www.npmjs.com/package/scrivener-mcp"> <img src="https://img.shields.io/npm/v/scrivener-mcp.svg?style=flat-square&labelColor=20232a&color=007ec6" alt="npm version"/> </a> <img src="https://img.shields.io/npm/dm/scrivener-mcp.svg?style=flat-square&labelColor=20232a&color=007ec6" alt="npm downloads"/> <img src="https://img.shields.io/node/v/scrivener-mcp?style=flat-square&labelColor=20232a&color=007ec6" alt="node version"/> <a href="https://github.com/writerslogic/scrivener-mcp"> <img src="https://img.shields.io/github/stars/writerslogic/scrivener-mcp?style=flat-square&labelColor=20232a&color=6a4c93" alt="stars"/> </a> <a href="https://mseep.ai/app/writerslogic-scrivener-mcp"> <img src="https://img.shields.io/badge/MseeP-verified-green.svg?style=flat-square&labelColor=20232a" alt="MseeP verified"/> </a> <a href="https://glama.ai/mcp/servers/writerslogic/scrivener-mcp"> <img src="https://glama.ai/mcp/servers/writerslogic/scrivener-mcp/badges/score.svg" alt="scrivener-mcp MCP server score"/> </a> <a href="#install">Install</a> · <a href="#what-you-can-do">What You Can Do</a> · <a href="#all-tools">All Tools</a> · <a href="#guides">Guides</a> · <a href="#contributing">Contributing</a>

Scrivener MCP lets your AI assistant open, read, edit, analyze, and search your Scrivener projects directly. No exporting, no copy-pasting text back and forth. Tell it which project to open and start working.

You: Open my novel and analyze the pacing in Chapter 12.

Claude: Opens the .scriv project, reads Chapter 12, runs pacing analysis. The first half moves well, but the middle stalls — a three-page internal monologue starting at paragraph 14 kills the momentum you built in the confrontation scene. Consider cutting it to a paragraph and moving the backstory to Chapter 8.

Works with Claude Desktop, Claude Code, VS Code (Copilot/Continue), Cursor, and any MCP-compatible client. Scrivener 3 on macOS, Windows, and Linux. Listed on the official MCP Registry as io.github.writerslogic/scrivener-mcp.

Install

npm install -g scrivener-mcp

Restart Claude Desktop and it's ready. Other clients need one more step:

npx scrivener-setup

This finds Claude Code, Claude Desktop, and Cursor and configures them for you. To set up Claude Code by hand instead: claude mcp add -s user scrivener -- npx scrivener-mcp, then restart it (or run /mcp).

<details> <summary>Other ways to install</summary>

Smithery

npx -y @smithery/cli install scrivener-mcp --client claude

npx, no install

npx scrivener-mcp

or add it to Claude Desktop's config directly:

{
  "mcpServers": {
    "scrivener": { "command": "npx", "args": ["scrivener-mcp"] }
  }
}

From GitHub

npm install -g writerslogic/scrivener-mcp              # latest main
npm install -g writerslogic/scrivener-mcp#v0.12.0       # a specific release

Homebrew (macOS)

brew install writerslogic/tap/scrivener-mcp

Docker

docker build -t scrivener-mcp https://github.com/writerslogic/scrivener-mcp.git
docker run -i --rm -v /path/to/your/projects:/projects scrivener-mcp

Any other MCP client: point it at npx scrivener-mcp as a stdio server.

</details> <details> <summary>Optional: AI-powered features</summary>

Document management, deterministic analysis, keyword search, and project memory work with no API key at all. Writing analysis, generation, enhancement, and semantic search need one — Anthropic, OpenAI, or OpenRouter. Set more than one and Claude handles chat by default; override with AI_PROVIDER=openai or AI_PROVIDER=openrouter (OpenRouter defaults to anthropic/claude-sonnet-4.6, change it with OPENROUTER_MODEL). If the active provider fails on an account-level error — bad key, no credit, an outage — the server retries on the next one you've configured. If your MCP client supports sampling, chat-based features can run through the client's own model instead, no separate key needed. Semantic indexing itself always runs locally through the Holographic Memory System; only semantic_search's query interpretation needs a provider.

Keys are picked up automatically from:

ANTHROPIC_API_KEY / OPENAI_API_KEY / OPENROUTER_API_KEY
~/.env or ~/.scrivener-mcp/.env
~/.anthropic/key, ~/.openai/key, ~/.openrouter/key
macOS Keychain (anthropic-api-key / openai-api-key / openrouter-api-key)

security add-generic-password -s anthropic-api-key -a anthropic -w sk-ant-your-key-here   # Keychain
export ANTHROPIC_API_KEY="sk-ant-..."                                                      # or export it directly

</details>

What You Can Do

Open a project first. The server has no link to the Scrivener app itself and can't see what's open there — say "Open my Scrivener project at ~/Documents/My Novel.scriv", or "Discover my Scrivener projects" if you don't know the path. On macOS, "Use the project I have open in Scrivener" works too (the first time, macOS will ask permission to control Scrivener). Do this once per conversation. If the project is also open and unsaved in Scrivener itself, save or close it there first, or the two can write over each other.

Manage your manuscript. Read chapters, create scenes, reorganize the binder, update synopses — all through conversation. "Create a new scene called 'The Reveal' after Chapter 5, and move the old epilogue to the trash."

Analyze your writing. Readability, pacing, style, dialogue quality, emotional arc — grounded in your actual prose, not generic advice. Ask whether a chapter's pacing is off and get specifics: which paragraphs stall, how the scene compares to your other chapters, filter-word density against your own average.

Enhance your prose. Targeted edits: cut filter words, strengthen verbs, vary sentence structure, add sensory detail, turn telling into showing, tighten dialogue, fix pacing.

Track characters and plot. Character profiles, plot threads, and style guides persist with the project across sessions. Save a profile for a character once; a consistency check months later catches contradictions — dialogue that doesn't sound like them, a limp that disappears for a chapter.

Search by meaning. "Find scenes where the protagonist feels isolated" works even if that word never appears. Indexing and similarity scoring run locally through the Holographic Memory System; semantic_search also needs a configured AI provider to interpret the query and explain the results.

Track relationships. Query how characters, locations, themes, and plot threads connect. No Neo4j required — relationships live in the semantic memory engine and persist with the project; Neo4j adds deeper graph analysis if you have it.

Compile and export. Assemble chapters into one manuscript with your own formatting and structure preserved. Export inline as Markdown, HTML, or JSON, or write a DOCX, EPUB, or PDF to disk.

All Tools

57 tools organized by workflow. To keep token usage low, tools load progressively — project tools at startup, document and search tools once a project is open, the rest on demand. Set SCRIVENER_MCP_EAGER_TOOLS=1 to load everything up front.

<details> <summary>Project -- open, browse, manage</summary>

Tool	What it does
`open_project`	Open a .scriv project (accepts .scriv folders or .scrivx files) and make it active
`discover_projects`	Scan common locations for Scrivener projects when you don't know the path
`detect_open_project`	Detect the project currently open in the Scrivener app (macOS) so you don't need a path
`get_structure`	Browse the binder hierarchy (folders, documents, word counts)
`refresh_project`	Reload from disk after external edits
`close_project`	Close the active project and flush pending changes
`verify_project_integrity`	Read-only scan for structural problems (missing/duplicate UUIDs, unreadable content)
`get_compile_settings`	Read the project's compile formats and taxonomy -- labels/statuses (with colors), collections, section types
`get_manuscript_briefing`	One "where am I?" snapshot: words vs. target (% to goal), document/status/label counts, longest/shortest documents
`list_snapshots`	List Scrivener snapshots (title, date) for one document or the whole project
`read_snapshot`	Read a snapshot's text as plain text, with word count
`compare_snapshot`	Diff a snapshot against the current document (or another snapshot): paragraphs added/removed and net word change
`create_snapshot`	Take a Scrivener-native snapshot of a document (restorable from Scrivener's own Snapshots browser) before editing

</details> <details> <summary>Documents -- read, write, create, organize</summary>

Tool	What it does
`get_document_info`	Metadata for one document (title, type, word count, synopsis, label, status)
`read_document`	Read content; `format: "formatted"` for rich text, `offset`/`limit` to page long docs
`write_document`	Replace a document's content (atomic, with pre-write backup)
`create_document`	Create a new text document or folder
`update_document`	Change title and/or metadata (synopsis, notes, label, status, custom fields)
`move_document`	Reorganize within the binder
`delete_document`	Move to trash (reversible)

</details> <details> <summary>Search -- find content, passages, and mentions</summary>

Tool	What it does
`search`	Keyword/full-text search; `field: "title"` for titles, `scope: "trash"` for trash
`semantic_search`	Find passages by meaning using the local HMS index plus provider-backed query interpretation, with similarity scores
`find_mentions`	Locate every occurrence of a specific name or term, with context
`list_trash`	List trashed documents
`restore_document`	Restore a document from trash
`read_annotations`	Read a document's comments and footnotes

</details> <details> <summary>Analysis -- quality, consistency, structure</summary>

Tool	What it does
`analyze_document`	AI writing analysis; focus with `aspects` (structure, style, pacing, themes...)
`check_consistency`	Project-wide continuity check; `scope` for plot, characters, or timeline
`analyze_writing_style`	Style-focused analysis
`check_plot_consistency`	Plot-thread consistency check
`suggest_improvements`	AI-generated improvement suggestions
`enhance_content`	Suggest a specific improvement to a document
`generate_content`	Generate new prose from a prompt and context
`set_writing_goal`	Set a word-count goal (daily, weekly, or whole project) with an optional target date
`get_writing_goals`	List goals with progress -- percent complete, words remaining, on-pace status
`set_writing_preferences`	Set author preferences (tone, complexity, length, POV, style guide) that steer AI output
`get_writing_preferences`	Show current preferences plus feedback insights and suggestions
`collect_feedback`	Record a rating/comment on an AI operation to inform those insights

Enhancement types: eliminate-filter-words, strengthen-verbs, vary-sentences, add-sensory-details, show-dont-tell, improve-flow, enhance-descriptions, strengthen-dialogue, fix-pacing, expand, condense, rewrite

</details> <details> <summary>Compile & Export -- assemble and ship the manuscript</summary>

Tool	What it does
`compile_documents`	Combine documents; `mode: "structured"` compiles the Draft folder with the binder hierarchy as headings and honors "Include in Compile" (no AI), `mode: "intelligent"` for AI-optimized output
`export_project`	Write the manuscript to disk -- Markdown, HTML, JSON inline, or DOCX, EPUB, PDF as a file
`get_statistics`	Project-level word/document/character counts
`generate_marketing_materials`	Draft synopsis, query letter, pitch, and related materials

</details> <details> <summary>Memory -- persistent project knowledge</summary>

Tool	What it does
`remember`	Store information that persists across sessions with the project
`recall`	Retrieve previously stored memory

Memory is stored within each .scriv project and travels with it.

</details> <details> <summary>Relationships -- entity connections and story graph</summary>

Tool	What it does
`add_relationship`	Store a relationship between characters, locations, themes, or plot threads
`find_relationships`	Query entities related to a given character/theme/location
`discover_connections`	Find co-occurring entities across the manuscript
`character_network`	The character relationship network
`get_entity_references`	Trace the reference graph in either direction: entities a document mentions (by documentId), or documents mentioning an entity (by entity)
`find_orphaned_entities`	List registered characters/locations that no document actually mentions
`suggest_connections`	Suggest entities a document may be missing, inferred from cross-document co-occurrence

Works without Neo4j -- relationships live in the Holographic Memory System and are available immediately. The document cross-reference tools are fully deterministic (exact whole-word matching, no AI) and need no external services; Neo4j adds advanced graph analysis when connected.

</details> <details> <summary>Background Jobs -- long-running analysis</summary>

Tool	What it does
`queue_document_analysis`	Enqueue an async analysis of one document; returns a job id
`queue_project_analysis`	Enqueue an async analysis of the whole project
`get_job_status`	Poll progress/results for a queued job
`cancel_job`	Cancel a queued or running job

</details> <details> <summary>Discovery -- explore capabilities</summary>

Tool	What it does
`list_skills`	List the available tool groups and their tools
`use_skill`	Activate a tool group (most are pre-activated by default)

</details>

Guides

Getting Started -- Installation, configuration, your first session
MCP Client Setup -- Copy-paste config for Claude Desktop, Claude Code, Cursor, and VS Code
Writing with AI -- Analysis workflows, enhancement strategies, memory management
Troubleshooting -- Common issues and fixes
Token Optimization -- How the server minimizes context window usage
Architecture -- How the server works, module structure, data flow
Scrivener Compatibility -- Supported Scrivener versions, platforms, and format coverage
Scrivener File Format -- The reverse-engineered .scriv format, what we read vs. infer, and safe-modification guidance
Fuzzing -- Jazzer.js target and OSS-Fuzz integration details
Contributing -- Development setup, code conventions, adding new tools

Requirements

Node.js 18+
Scrivener 3 project files (.scriv)
macOS, Windows, or Linux
Optional: Anthropic, OpenAI, or OpenRouter API key for provider-backed AI features
Optional: Neo4j for persistence and advanced graph queries; core relationship tools work without it

Development

git clone https://github.com/writerslogic/scrivener-mcp.git
cd scrivener-mcp
npm install
npm run dev          # Development mode with hot reload
npm run build        # Compile TypeScript
npm test             # Run tests
npm run typecheck    # Type checking only

Why This One?

A few Scrivener MCP servers exist. Feature claims below come from each project's own docs, published package, and advertised tools, last re-read on 2026-08-22; stars, forks, activity, and published version were refreshed 2026-09-15. "No" means undocumented — not necessarily impossible through the connected AI client.

Feature	scrivener-mcp	jiayun	TwelveTake	Scrivener Assistant	ricopicone	zaphodsdad
Public MCP tools	57	29	22	38	18	10
Manuscript access	read/write	read/write	read/write	read-only; writes sidecar data/metadata	read-only by default; opt-in content/notes/synopsis writes	read-only
RTF handling	formatted reads; fidelity-preserving span writes	reads/writes document content	reads/writes document content	converts RTF to text; manuscript read-only	RTF-to-text reads; snapshot-protected content writes	converts RTF to text; read-only
Built-in writing analysis	readability, pacing, style, emotion, AI critique	readability, style, sentiment	continuity comparison	agent-driven five-point review workflow	no dedicated analysis tool	no dedicated analysis tool
Content generation/enhancement	generation + 12 targeted enhancement types	no	no	brainstorm/draft agent workflow	no	no
Local semantic retrieval	HMS index and similarity search	no	no	no	no	no
Continuity/project memory	persistent memory + consistency checks	persistent notes + consistency checks	mention/description comparison	world bible, story state, characters, locations, review history	no persistent memory	no persistent memory
Relationship tooling	persistent relationships, networks, reference graph; optional Neo4j	no	no	human-editable relations data	no	no
Token optimization	progressive skill loading, compact output, paged reads	no documented equivalent	no documented equivalent	no documented equivalent	scoped binder/chapter reads	scoped overview/read tools
Export / compilation	Markdown, HTML, JSON, DOCX, EPUB, PDF	compile + whole-draft export	PDF	saves AI drafts; no manuscript export documented	no	no
Windows support	yes	yes (prebuilt binary)	yes	not documented	not documented	yes
Installation	npm, Homebrew, Docker, Smithery	Cargo or prebuilt binary	npm package (deprecated)	MCPB or source	source / `uv`	source / `pip install -e`
License	AGPL-3.0 / commercial dual-license	MIT	MIT	MIT	not declared	MIT
Repository/package status	weekly activity; npm `0.12.0`	monthly activity	discontinued and unmaintained	occasional activity	occasional activity; no releases	occasional activity; no releases
Community	⭐ 54 · 18 forks	⭐ 7	source repository unavailable	⭐ 1	⭐ 0	⭐ 5 · 1 fork

Counts and feature claims can change. Follow the linked projects for their own latest documentation. The table is generated from docs/comparison.yml — edit claims there, not here.

The alternative that isn't an MCP server

Scrivener can also Sync to External Folder, writing each document out as RTF or plain text, which any generic file-access MCP server (like @modelcontextprotocol/server-filesystem) can then read and write.

It's free and works today. What you lose is everything tied to the actual project — binder hierarchy, metadata, labels and status, snapshots, compile settings, RTF formatting — and edits land in the sync folder rather than the project itself, so a bad edit gets reconciled by Scrivener on the next sync instead of caught before it happens. Fine for occasional read-only help with prose; not if you want the structure to survive the round trip.

Contributing

We welcome contributions of all sizes. Check the issue tracker for good first issue labels, or see the contributing guide for development setup.

Areas where help is especially welcome:

Test coverage (#18)
Windows testing and path handling
Scrivener 2 compatibility testing
Documentation improvements (#25)

Security

Found a vulnerability? Please report it privately — see SECURITY.md.

License

Free for personal use and open-source projects. Commercial license available for proprietary integration. See COMMERCIAL_LICENSE.md for details.

<a href="https://glama.ai/mcp/servers/writerslogic/scrivener-mcp"> <img src="https://glama.ai/mcp/servers/writerslogic/scrivener-mcp/badges/card.svg" alt="scrivener-mcp MCP server"/> </a> <a href="https://github.com/writerslogic/scrivener-mcp">GitHub</a> · <a href="https://www.npmjs.com/package/scrivener-mcp">npm</a> · <a href="https://github.com/writerslogic/scrivener-mcp/issues">Issues</a> · <a href="./CHANGELOG.md">Changelog</a>

Related MCP servers

io.github.writerslogic/cogmem

Active

A self-improving, verifiable memory layer for AI coding agents.

Python

Apache-2.0

View repository →

io.github.writesdavid/open-primitive

Maintained

33 tools, 30 US federal data domains. Ed25519 signed, provenance chains, entity graph. Free.

JavaScript

MIT

View repository →

io.github.wrnreed-analytics/circuit-ai-mcp

Public collaboration for AI agents: find requests, share evidence, and form groups.

FHIR MCP Server

Maintained

MCP server providing seamless access to FHIR APIs for healthcare data integration with AI tools

132

Python

Apache-2.0

View repository →

io.github.wspringer/math-svg-mcp

Stale

Convert LaTeX math expressions to crisp, scalable SVG images

TypeScript

View repository →

Ableton Live MCP Server

Maintained

Control Ableton Live with 156 typed tools for music production and offline .als analysis.

Python

MIT

View repository →