Scrivener Mcp
io.github.writerslogic由 GitHub 账号 writerslogic 发布v0.12.0更新于 Oct 24, 2026
MCP server for Scrivener: read, write, analyze, and search your manuscripts with AI assistants.
概览
让 AI 助手直接打开、读取、编辑、分析和搜索 Scrivener 3 写作项目，无需导出或来回复制文本。
- 可以做什么
- 将助手连接到 .scriv 项目，可浏览文稿结构、读取和写入文档、创建场景、移动或删除条目，并管理简介、标签、状态等元数据。它提供关键词搜索与本地语义搜索、离线写作报告（可读性、风格、重复、对话标签、连贯性）、AI 写作分析与润色、人物与情节关系追踪、项目持久记忆，以及编译导出为 Markdown、HTML、JSON、DOCX、EPUB 或 PDF。工具按需逐步加载以控制 token 消耗。
- 适用场景
- 适合使用 Scrivener 的小说或剧本作者，希望助手分析节奏、连贯性或风格，提出有针对性的文字修改建议，追踪人物与情节线索，或在保留项目结构和元数据的前提下汇编并导出稿件。
- 运行要求
- 需要 Node.js 18+ 和 Scrivener 3 项目文件，支持 macOS、Windows 或 Linux；以 npm 包 scrivener-mcp 通过 stdio 运行。文档管理、确定性分析、关键词搜索和项目记忆无需 API 密钥。AI 分析、生成、润色和语义搜索需要 Anthropic、OpenAI 或 OpenRouter 密钥，可从 ANTHROPIC_API_KEY、OPENAI_API_KEY、OPENROUTER_API_KEY、env 文件、密钥文件或 macOS 钥匙串读取。Neo4j 为可选项。
安装
在 SourceWeft 中
- 打开 控制台中的 Scrivener Mcp，将其添加到工作区。
- 为需要使用其工具的对话启用该服务。
Desktop only，通过 STDIO。 STDIO 服务会启动本地进程，因此需要 SourceWeft 桌面宿主。
其他 MCP 客户端
参照 仓库 中的启动说明。
README
Scrivener MCP
MCP server for Scrivener: connect your novels, screenplays, and manuscripts to Claude, ChatGPT, and any AI assistant, with document management, writing analysis, content enhancement, offline semantic search, and character/plot tracking.
Start with the safe first session, then use editorial review and workflows, export presets, Content Credentials, or the Windows guide. Compatibility evidence records actual coverage and limits.
[CI] [CodeQL] [OpenSSF Scorecard] [npm] [License]
Install · Mac App · What You Can Do · All Tools · Guides · Contributing
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. Reads Scrivener 3 projects on the
supported platforms. Listed on the
official MCP Registry as
io.github.writerslogic/scrivener-mcp.
Install
Mac app: Draftbridge for Scrivener, $4.99
Not a terminal person? Draftbridge for Scrivener is the ready-made Mac app. It finds your AI apps — Claude Desktop, BoltAI, Cursor, VS Code, LM Studio, Raycast, Claude Code — connects Scrivener MCP to each with one click, shows your projects, and repairs the connection after an app update. No Terminal, no Node.js, no settings files. One-time $4.99, up to 3 Macs, signed and notarized by Apple.
[Draftbridge showing Claude Desktop and BoltAI connected, and the Scrivener projects it found] [The Draftbridge purchase window]
The server, setup tool, and Claude Desktop extension here stay free and open source. The app is
closed source; the fee buys the notarized build and supports development. See the
Mac install guide and FAQ. Report app problems with the
mac-app label.
Free: Claude Desktop extension or command line
Prefer to do it yourself? The .mcpb extension (Claude Desktop only) and the terminal setup below
do the same job for free.
From a terminal:
Restart Claude Desktop and it's ready. Other clients need one more step:
This finds Claude Desktop, Claude Code, Cursor, VS Code, LM Studio, BoltAI, and Raycast and
configures them for you, then confirms the server starts. No Node.js on your Mac? See the
Mac install guide. To set up Claude Code by hand instead:
claude mcp add -s user scrivener -- npx scrivener-mcp, then restart it (or run /mcp).
Other ways to install
npx, no install
or add it to Claude Desktop's config directly:
From GitHub
Homebrew (macOS)
Docker
The container uses Linux x64 with glibc because the pinned Narrative Lens 0.2.0 package has no Linux
ARM64 or musl binary. Linux ARM64 and musl hosts can use this Docker configuration; ARM hosts need
Docker's amd64 emulation. The image runs as the non-root node user;
mounted project directories must permit that user to read and write.
Any other MCP client: point it at npx scrivener-mcp as a stdio server.
Optional: AI-powered features
Document management, deterministic analysis, local passage search, and project memory work with no
API key. Provider-assisted interpretation, generation and enhancement use 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 on legacy MCP connections, no separate key needed. MCP 2026-07-28 connections currently use configured providers for AI features; modern multi-round sampling is not implemented. Passage retrieval runs locally
through Holographic Memory 0.6.4; interpretation and explanations are optional provider features.
Keys are picked up automatically from:
ANTHROPIC_API_KEY/OPENAI_API_KEY/OPENROUTER_API_KEY~/.envor~/.scrivener-mcp/.env~/.anthropic/key,~/.openai/key,~/.openrouter/key- macOS Keychain (
anthropic-api-key/openai-api-key/openrouter-api-key)
What You Can Do
For manuscript operations, 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. Warm 0.6.4 combines native BM25 with local embeddings and optional cross-encoder reranking. Configure local ONNX models for general semantic search; the default encoder covers a disclosed English story-concept vocabulary. Results include exact passages, locations and saved revisions; changed passages update incrementally. No embedding provider is required. See local search configuration.
Track relationships. Record and query how characters, locations, themes, and plot threads connect. Relationships persist in the project's local SQLite state. Discovery proposes unrecorded character/location pairs using saved-text co-occurrence with source revisions.
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.
Sign and validate exports. Activate credentials with use_skill({"name":"credentials"}), then
call c2pa_capabilities to inspect the installed SDK. Export a PDF with export_project, sign it
to a new embedded output with sign_content_credentials, and check that output with
validate_content_credentials. Credential operations run locally without an open project and use
administrator-configured signing material. They do not establish human authorship or formal C2PA
conformance. See Content Credentials for setup, mode coverage and
limits.
All Tools
82 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.
Project -- open, browse, manage
Documents -- read, write, create, organize
Search -- find content, passages, and mentions
Analysis -- quality, consistency, structure
Manuscript comparisons include comparisonBaseline.name and its original envelope, alongside the
current result's envelope, so both saved source revisions remain identifiable after a baseline name
is reused.
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
Compile & Export -- assemble and ship the manuscript
Intelligent compilation returns provider warnings, explicit quality availability, and saved-source
revisions. Rewrites require the complete source to fit 12000 UTF-16 characters; otherwise the
complete original is preserved. Quality opinions cover at most 4000 characters and identify that
coverage. Marketing generation reads the saved Draft by default; use documentIds to select a
smaller scope within the same 12000-character limit. Both reject source changes during generation
and provide read_result references for large output.
Content Credentials -- local asset signing and validation
Activate the credentials skill on demand; these tools do not require an open project.
Format declarations are not proof of native compatibility. Use the Content Credentials guide and per-format native evidence before making coverage claims.
Memory -- persistent project knowledge
Project memory travels within each .scriv project. Explicit series memberships and shared facts use the server's persistent registry; see editorial workflows.
remember validates nested records and acknowledges the saved snapshot with its revision and record
ID. Use that ID for updates; identical creations reuse their ID, and unknown update IDs fail.
Unrecorded profile fields, style preferences and writing statistics stay absent. worldBuilding
stores named records, for example { name: "Moon Harbor", type: "location" }; all merges custom
JSON by key. Requests are capped at 64 KiB and complete project memory at 16 MiB. Large recall
results use read_result. Earlier custom world data remains available under recall with all.
Relationships -- entity connections and story graph
Relationship tools use project-owned SQLite without an external service. Storage admits up to
10000 relationships; names contain at most 128 UTF-16 characters and labels 64. Discovery covers
the characters and locations already recorded in that graph, up to 256 entities, 1000 Draft
documents, 2 Mi UTF-16 source characters and a source-character count multiplied by entity count
of at most 134217728. Its score is the
fraction of documents mentioning both entities among those mentioning either; it is a candidate
association, not a confirmed story fact. Result limits disclose omitted candidates, and large
responses use read_result. Relationship queries page in stable identity order using nextOffset
and graphRevision; edits require restarting the query. Document cross-reference tools use the
character/location registries and saved text, including Research and Draft items excluded from
Compile. Document queries read only the requested document; entity-wide queries and suggestions
inspect all active text within the same source limits. They disclose missing registries, reject
source/registry changes, and preserve every admitted match offset (up to 1000000 positions and
16 MiB of serialized mention records).
Background Jobs -- long-running analysis
Queued analysis always runs local prose analysis and includes readability by default. Optional
named entities require a native build with ONNX support and a loaded NER model; unavailable results
are explicit. Optional sentiment uses a local lexicon heuristic. Source revisions hash the supplied
UTF-8 text, and the envelope identifies this raw policy separately from saved RTF analysis and saved
project controls. Project batches preserve input order and run sequentially unless parallel is
selected, with at most five documents in flight. Large completed results return a _ref retrieved
through read_result. Redis/KeyDB cannot remove an active job; embedded cancellation prevents work
that has not started and discards the result of work already running.
suggest_improvements accepts async: true for the same suggestion result through get_job_status.
With useContext: true, documentId is required: generation uses up to the first 16000 UTF-16
characters of that saved document and rejects a changed revision. Its result reports the exact
excerpt range, truncation and source revision. The default useContext: false sends only the prompt.
Suggestions use the configured provider or client sampling, and queued generation is not automatically
retried. Large synchronous and queued results use read_result references.
analyze_writing_style accepts 1–64 nonempty text samples, each up to 64000 UTF-16 characters.
Its provider prompt includes at most 8000 characters including separators; coverage reports the
range used from every sample, including any omitted samples. Missing or malformed profile fields
are explicitly unavailable, partial finding lists preserve valid entries, and sample revisions
hash the original supplied UTF-8 text. Large profiles also use read_result references.
Discovery -- explore capabilities
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
- Content Credentials -- Local C2PA signing and validation, administrator setup, tested modes and conformance limits
- Scrivener File Format -- The reverse-engineered
.scrivformat, 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
- Stable Node.js
^22.23.4 || ^24.22.1 || >=26.12.1(24.22.1 or newer on Node 24 recommended) - Scrivener 3 project files (.scriv)
- Native npm/npx installs: macOS x64/ARM64, Windows x64, or Linux x64 with glibc. Architecture refers to the Node.js runtime.
- 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
The patched floors protect Node TLS paths used by the pinned CAI native SDK; SQLite 13 also requires Node-API 10. Node 23 and 25 are excluded. See the runtime compatibility policy.
Development
See the compatibility and upgrade policy for runtime checks, protocol contracts, dependency upgrades and the stable release gate.
Why This One?
A few Scrivener MCP servers exist. Our column describes the current server; other feature claims come from each project's own docs, published package, and advertised tools, last re-read on 2026-10-22; stars, forks, activity, and published version were refreshed
2026-11-02. "No" means undocumented — notnecessarily impossible through the connected AI client.
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
AGPL-3.0 © WritersLogic, Inc.
Scrivener is a trademark of Literature & Latte Ltd. This project is independent and is not affiliated with, endorsed by, or sponsored by Literature & Latte.
Free for personal use and open-source projects. Commercial license available for proprietary integration. See COMMERCIAL_LICENSE.md for details.
Also from WritersLogic: WritersProof witnesses your keystrokes, pauses, and revisions as you write, then seals that process into tamper-evident, independently verifiable proof you wrote it yourself — AI accusations, settled with evidence instead of your word.
GitHub · npm · Issues · Changelog
MCP 2026-07-28 uses server/discover and a stable full tool catalog. Each request supplies the protocol version and client capabilities in MCP _meta. open_project returns a com.writerslogic/project token in result _meta; include that token in subsequent project tool requests. Opening another project invalidates the previous token. Calls are serialized per stdio connection. Legacy MCP initialization and progressive skill discovery remain available.
来源：README.md，提交 cc4fd49
工具
0版本历史
1- v0.12.0最新Sep 16, 2026
评分
已满足适用检查项的 50%
该评分衡量此收录条目的完整程度，依据注册中心条目、端点与公开来源计算得出。它不是对服务器本身的评价，也不表示服务器安全或当前可用：可连通性是带日期的检查结果，评分也不包含安装量或用户评价。
- 近 30 天内可连通25 分
请保持端点能够响应 MCP 握手；SourceWeft 每 30 天探测一次。
- 已声明认证方式10 分
请在注册中心条目中声明凭据请求头，或保持端点能够响应探测，以便判定其认证方式。
- 已列出工具15 分
请让服务器在无凭据时响应 tools/list，或发布可在沙箱中无凭据启动的软件包。
- 描述必需15 分
- 图标10 分
- 文档15 分
- 许可证10 分