Scrivener MCP Server

MCP server for Scrivener - Read, write, analyze, and search manuscripts with semantic search, character/plot tracking, writing analysis, and content

Local serverstdioTypeScript

What is the Scrivener MCP Server?

MCP server for Scrivener - Read, write, analyze, and search manuscripts with semantic search, character/plot tracking, writing analysis, and content enhancement.

What you get

Configuration and credentials

  • Node.js 18+ - Scrivener 3 project files (.scriv) - macOS, Windows, or Linux - Optional: Anthropic or OpenAI API key for AI-powered features (OpenAI required for semantic/embedding features) - Optional: Neo4j for character relationship graphs

More MCP options

Compare MCP servers by category, or browse hosted MCP servers if you prefer an endpoint over a local process.

Maintainer setup documentation.

Recorded tools

Check the linked publisher documentation and your connected client's tool list. Names and availability can vary with the server version and account permissions.

ToolWhat it does
open_projectOpen a .scriv project (accepts .scriv folders or .scrivx files) and make it active
discover_projectsScan common locations for Scrivener projects when you don't know the path
detect_open_projectDetect the project currently open in the Scrivener app (macOS) so you don't need a path
get_structureBrowse the binder hierarchy (folders, documents, word counts)
refresh_projectReload from disk after external edits
close_projectClose the active project and flush pending changes
verify_project_integrityRead-only scan for structural problems (missing/duplicate UUIDs, unreadable content)
get_compile_settingsRead the project's compile formats and taxonomy -- labels/statuses (with colors), collections, section types
get_manuscript_briefingOne "where am I?" snapshot: words vs. target (% to goal), document/status/label counts, longest/shortest documents
list_snapshotsList Scrivener snapshots (title, date) for one document or the whole project
read_snapshotRead a snapshot's text as plain text, with word count
compare_snapshotDiff a snapshot against the current document (or another snapshot): paragraphs added/removed and net word change
create_snapshotTake a Scrivener-native snapshot of a document (restorable from Scrivener's own Snapshots browser) before editing
get_document_infoMetadata for one document (title, type, word count, synopsis, label, status)

How to install the Scrivener MCP Server

{
  "mcpServers": {
    "scrivener": {
      "command": "npx",
      "args": ["-y", "scrivener-setup"],
      "env": {
        "ANTHROPIC_API_KEY": "your-value",
        "OPENAI_API_KEY": "your-value",
        "OPENROUTER_API_KEY": "your-value"
      }
    }
  }
}

Add to claude_desktop_config.json, then restart Claude Desktop.

Configuration

  • Node.js 18+ - Scrivener 3 project files (.scriv) - macOS, Windows, or Linux - Optional: Anthropic or OpenAI API key for AI-powered features (OpenAI required for semantic/embedding features) - Optional: Neo4j for character relationship graphs
VariableDescriptionRequired
ANTHROPIC_API_KEYCredential the server authenticates with.Yes
OPENAI_API_KEYCredential the server authenticates with.Yes
OPENROUTER_API_KEYCredential the server authenticates with.Yes

Example prompts to try

  • “Use Scrivener to open project.”
  • “Use Scrivener to discover projects.”
  • “Use Scrivener to detect open project.”

Frequently asked questions

MCP server for Scrivener - Read, write, analyze, and search manuscripts with semantic search, character/plot tracking, writing analysis, and content enhancement. Confirm the tools offered by your installed version in the connected client. Tool availability and permissions depend on the server and account configuration.