Scrivener MCP server

Read from the package source without running it. The installed server may list more.

• add_relationship

  Record a typed, directed relationship between two story entities (e.g. a character

• advanced

  Async job queue and batch operations

• analysis

  Analyze writing quality, enhance prose, check consistency, track goals, tune writing preferences

• analyze_document

  Analyze the writing quality of a single document and return a summary of readability, pacing,

• analyze_writing_style

  Analyze the prose style of one or more text samples — sentence variety, tone, voice,

• build_vector_store

  Build search index

• cancel_jobwrite action

  Cancel a queued or running background job by its type and id. Returns whether the

• character_network

  THE default tool for "map my characters" / "how do my characters connect": returns the full

• check_consistency

  Scan the whole project for continuity problems and return the issues found: character

• check_plot_consistency

  Scan a set of documents for plot-level inconsistencies — timeline conflicts, contradicted

• close_project

  Close the currently open project, flush any pending memory/auto-save state, and clear the

• collect_feedback

  Record feedback on an AI operation (e.g. "enhance_content") so it feeds the insights returned

• compare_snapshot

  Compare a document snapshot against the current document text, or against another snapshot

• compilation

  Compile manuscripts, export, statistics

• compile_documents

  Compile the project's documents into a single continuous manuscript in the requested format

• create_documentwrite action

  Create a new text document or folder in the binder and return its new id. Optionally set the

• create_snapshotwrite action

  Take a Scrivener-native snapshot of a document's current content, restorable from Scrivener's

• delete_documentwrite action

  Move a document to the project trash. This is reversible: the document can be listed with

• detect_open_project

  Detect which Scrivener project the user currently has open in the desktop Scrivener app, so

• discover_connections

  Surface previously unrecorded relationships across the project by analyzing entity

• discover_projects

  Scan common locations (Documents, Desktop, and iCloud Mobile Documents) for Scrivener

• documents

  Read, write, create, delete, move, and rename documents

• enhance_content

  Produce an AI-improved version of a document's text for a chosen goal (fix grammar, refine

• export_project

  Export the whole project to a publishing/interchange format. Markdown, HTML, and JSON

• find_analogies

  Find analogies (A:B :: C:?)

• find_mentions

  Find every occurrence of a specific name or term (a character, place, or keyword) across all

• find_orphaned_entities

  List registered characters and locations that no document actually mentions — entities added

• find_relationships

  Query the story graph for entities related to a given entity, returning the connected

• generate_content

  Generate new prose from a natural-language prompt and return the generated text, optionally

• generate_marketing_materials

  Generate a publishing/marketing artifact from the manuscript — a synopsis, query letter,

• get_compile_settings

  Return the project's compile-format definitions (from Settings/compile.xml) and its

• get_document_info

  Return metadata for a single document without its body text: title, type, word count,

• get_entity_references

  Trace the reference graph between documents and registered characters/locations, in either

• get_job_status

  Look up the status and progress of a background job previously started by

• get_manuscript_briefing

  One "where am I?" snapshot of the whole manuscript: total word count against the project draft

• get_queue_stats

  Get job queue statistics

• get_statistics

  Return project-wide statistics: total word and document counts, plus title and author. Use

• get_structure

  Return the binder hierarchy of the open project: its folders and documents in tree order,

• get_writing_goals

  List writing goals with computed progress: percent complete, words remaining, and whether each

• get_writing_preferences

  Return the current author writing preferences plus feedback insights: how much feedback has

• hhm_dream

  Creative concept recombination

• list_skills

  List the available skills (tool groups) — project, documents, search, analysis,

• list_snapshots

  List the snapshots Scrivener has saved of a project's documents (from the .scriv

• list_trash

  List all documents currently in the project trash, with their ids and titles. Use this to

• memory

  Store and recall persistent project facts (characters, world, plot, style)

• move_document

  Move a document or folder to a different parent folder in the binder, optionally at a specific

• multi_agent_analysis

  Multi-agent analysis

• open_project

  Open a Scrivener project and make it the active project for this session. Every document,

• project

  Open, browse, save, close, and verify Scrivener projects

• queue_document_analysis

  Enqueue a background NLP analysis of one document (readability, entities, sentiment) and

• queue_project_analysis

  Enqueue a background batch analysis across many documents at once and return a job id

• read_annotations

  Return the inline comments and footnotes attached to a document, grouped by type. Use this

• read_document

  Read the text of a single document. By default returns plain text; set format to "formatted"

• read_snapshot

  Return the text of a single document snapshot. Pass the documentId and the snapshotId from

• recall

  Read back the project's persistent memory: stored characters, world-building, plot threads,

• refresh_project

  Reload the open project from disk, discarding the in-memory cache. Use this when the project

• relationships

  Entity relationships, character networks, story graph

• remember

  Store or update a fact in the project's persistent memory so later tools and sessions stay

• restore_document

  Restore a trashed document back into the binder, optionally into a specific target folder

• search

  Search the open project and return matching documents with relevance-ranked snippets. By

• semantic_search

  Find passages by meaning rather than exact words, using embeddings over the project, and

• set_writing_goalwrite action

  Create or replace the active word-count goal for a cadence (daily, weekly, or whole project),

• set_writing_preferences

  Set the author writing preferences that shape AI writing output (enhance_content and other

• store_chapter_orderwrite action

  Store chapter sequence

• suggest_connections

  Suggest characters or locations a document might be missing: entities it does not mention

• suggest_improvements

  Generate AI writing suggestions for a prompt or a specific document — ideas for revision,

• sync_to_neo4j

  Sync relationships to Neo4j

• update_documentwrite action

  Update a document's title and/or its metadata (synopsis, notes, label, status, and custom

• use_skill

  Activate a skill so its tools become available to call. Returns the activated skill's tool

• verify_project_integrity

  Scan the open project for structural problems and return a read-only report: binder entries

• write_documentwrite action

  Replace a document's text with new content, preserving the surrounding Scrivener formatting

• Code scan289 source files scanned15/25
• –Live reliabilityno gateway calls yet and no remote to proben/a
• –Tool poisoningtools not inspected (local package is not executed); not countedn/a
• Auth qualitylocal package, no credentials required12/15
• Maintenancelast push 3 days ago15/15
• Maintainer identityregistry namespace matches repository owner7/10

Scrivener: common questions

Is Scrivener MCP server safe?

Mostly: it is graded B (75/100). Read the Scrivener safety report

How do I install Scrivener?

It runs on your machine. Copy the Claude Code, Claude Desktop or Cursor config from the install section.

Does Scrivener need an API key?

Not as far as the registry entry and our scan can tell: no credentials are declared or required.

Is Scrivener maintained?

The last commit was 3 days ago (2026-09-21). The latest release is v0.12.0.

What can I use instead of Scrivener?

Servers from other publishers that do the same job: Gdelt MCP server, OpenAgenda MCP server and Dimensions Analytics MCP server. Compare all Scrivener alternatives.