Scrivener MCP Server

62 tools. 18 can modify or destroy data without limits.

2 destructive tools with no built-in limits. Policy required.

Last updated:

18 can modify or destroy data
44 read-only
62 tools total

Community server · catalogue entry verified 11/06/2026

How to control Scrivener MCP Server ↓

Read (44) Write / Execute (16) Destructive / Financial (2)
Critical Risk

18 of Scrivener MCP Server's 62 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

PolicyLayer is an MCP gateway — it sits between your AI agents and Scrivener MCP Server, and nothing reaches the server without passing your rules. These are the rules we recommend:

Deny destructive operations
{
  "cancel_job": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Blocked by default. Requires approval."
      }
    ]
  }
}

Destructive tools should never be available to autonomous agents without human approval.

Rate limit write operations
{
  "close_project": {
    "limits": [
      {
        "counter": "close_project_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations
{
  "analyze_document": {
    "limits": [
      {
        "counter": "analyze_document_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

  1. Create a free account and register Scrivener MCP Server — nothing to install.
  2. Add these rules — paste them, or build them visually. Tune the limits to your setup.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
ENFORCE POLICY ON SCRIVENER →

Free to start. No card required.

READ 44 tools
Read analyze_document Analyze writing quality Read analyze_narrative Analyze narrative structure Read analyze_writing_style Analyze writing style Read check_character_continuity Check character continuity Read check_consistency Check project consistency Read check_plot_consistency Check plot consistency Read collect_feedback Submit feedback Read cross_reference_analysis Cross-reference related content Read enhance_content AI content enhancement Read find_analogies Find analogies (A:B :: C:?) Read find_cooccurrences Find co-occurrences Read find_document Find documents by title Read find_mentions Find entity mentions Read fractal_search Fractal retrieval search Read get_all_documents Paginated flat list of all documents Read get_document_annotations Get annotations and footnotes Read get_document_info Get document metadata Read get_job_status Get queued job status Read get_memory Retrieve AI memory Read get_memory_analytics Get memory performance metrics Read get_memory_stats Get memory usage stats Read get_queue_stats Get job queue statistics Read get_statistics Get project statistics Read get_structure Get project hierarchy Read get_word_count Get word count Read hhm_dream Creative concept recombination Read ingest_document_fractal Ingest into fractal memory Read ingest_project_fractal Ingest project into fractal memory Read intelligent_compilation AI-optimized compilation Read list_skills List available tool groups and their contents Read list_trash List trashed documents Read multi_agent_analysis Multi-agent analysis Read queue_document_analysis Queue async NLP analysis Read queue_project_analysis Queue batch project analysis Read read_document Read document content Read read_document_formatted Read document with formatting Read recover_document Restore from trash Read refresh_project Reload project from disk Read search_content Search across all documents Read search_trash Search trashed documents Read semantic_search Semantic search Read track_motifs Track recurring motifs Read use_skill Activate a skill to register its tools Read vector_search Semantic vector search

Other MCP servers with similar tools — same risk classification, starter policies for each.

Can an AI agent delete data through the Scrivener MCP Server MCP server? +

Yes. The Scrivener MCP Server server exposes 2 destructive tools including cancel_job, delete_document. These permanently remove resources with no undo. PolicyLayer blocks destructive tools by default so they never reach the upstream server.

How do I prevent bulk modifications through Scrivener MCP Server? +

The Scrivener MCP Server server has 13 write tools including close_project, create_document, export_project. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach Scrivener MCP Server.

How many tools does the Scrivener MCP Server MCP server expose? +

62 tools across 4 categories: Destructive, Execute, Read, Write. 44 are read-only. 18 can modify, create, or delete data.

How do I enforce a policy on Scrivener MCP Server? +

Register the Scrivener MCP Server MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every Scrivener MCP Server tool call.

Deterministic rules across all 62 Scrivener MCP Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

Free to start. No card required.

62 Scrivener MCP Server tools catalogued and risk-classified — across an index of 42,500+ MCP servers.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.