// SCAN REPORT

Narrarium

80 tools. 53 can modify or destroy data without limits.

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

Last updated:

53 can modify or destroy data
27 read-only
80 tools total

Community server · catalogue entry verified 01/07/2026

How to control Narrarium ↓

TOOL MAP

What Narrarium exposes to your agents

Read (27) Write / Execute (51) Destructive / Financial (2)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS
Critical Risk

The most dangerous Narrarium tools

Destructive · Medium wizard_cancel The tool discards in-memory answers from a wizard session, which is irreversible — any data entered into the wizard is permanently lost. Destructive · High revise_paragraph Propose a revision for an existing final paragraph without writing files. Use this for targeted editorial passes like clarity, pacing, tensi Write · Medium wizard_finalize The tool writes files or folders to a local repository, creating or modifying content. Write · Medium start_wizard The tool initiates a guided creation workflow for canon files or chapter structures.

53 of Narrarium's 80 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Narrarium

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

Deny destructive operations
{
  "revise_paragraph": {
    "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
{
  "apply_dialogue_action_beats": {
    "limits": [
      {
        "counter": "apply_dialogue_action_beats_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations
{
  "chapter_wizard": {
    "limits": [
      {
        "counter": "chapter_wizard_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 Narrarium — 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 NARRARIUM →

Instant setup, no code required.

FULL CATALOGUE

All 80 Narrarium tools

DESTRUCTIVE 2 tools
Destructive revise_paragraph Propose a revision for an existing final paragraph without writing files. Use this for targeted editorial pass Destructive wizard_cancel Cancel a wizard session and discard its in-memory answers.
WRITE 51 tools
Write apply_dialogue_action_beats Apply confirmed dialogue action beat selections to a final paragraph after review_dialogue_action_beats. This Write create_asset_prompt Create an asset prompt markdown file in the canonical assets tree for a book, entity, chapter, or paragraph im Write create_chapter Create a chapter folder, chapter metadata file, and paired resume and evaluation files in the local book repos Write create_chapter_draft Create a rough chapter draft inside drafts/ using the same chapter slug structure as the final chapter tree. K Write create_chapter_from_draft Promote a chapter draft into the final chapters/ tree. It copies structural frontmatter from drafts/, accepts Write create_character Create a rich character file using the Narrarium character wizard fields. Use this instead of the generic enti Write create_entity Create a canonical entity markdown file inside the local book repository. Use this for quick stubs, items, loc Write create_faction Create a rich faction file with mission, ideology, methods, alliances, and optional historical research suppor Write create_item Create a rich item file with appearance, purpose, significance, ownership, and optional historical research su Write create_location Create a rich location file with atmosphere, story function, landmarks, risks, and optional historical researc Write create_paragraph Create a numbered paragraph or scene markdown file inside an existing chapter folder. In prose bodies, keep ca Write create_paragraph_draft Create a rough paragraph or scene draft inside drafts/ using the same chapter tree as the final chapter. Write create_paragraph_from_draft Promote a paragraph draft into the final chapters/ tree. It copies structural frontmatter from drafts/, accept Write create_persona Create a reader persona file in personas/ of the book repository. Personas represent fictional reader archetyp Write create_script Create a new scene script in scripts/<chapter>/<paragraph>.md using the Narrarium script meta-language. ${SCR Write create_secret Create a rich secret file with stakes, holders, protection, reveal strategy, and spoiler thresholds. Write create_timeline_event Create a timeline event file with participants, significance, consequences, and optional factual research supp Write evaluate_book Refresh the total book evaluation with chapter scorecards, writing-style-aware editorial checks, canon coheren Write evaluate_chapter Refresh a full chapter evaluation by reading the whole chapter across all paragraph files, combining objective Write evaluate_paragraph Refresh the saved evaluation for a single paragraph while still using the full chapter as context, including o Write export_epub Export the current book repository into an EPUB file from the ordered chapter and paragraph markdown files. Write generate_asset_image Generate an image for a canonical subject, save it into the assets tree, and keep the asset prompt metadata in Write init_book_repo Create the local Narrarium repository structure for a book project, including folders, guidelines, summaries, Write promote_book_item Promote a structured book-level idea or note out of the active queue. You can move it into notes or story desi Write promote_chapter_item Promote a structured chapter-level idea or note out of the active queue. You can move it into chapter notes or Write register_asset Copy an existing image into the canonical assets tree and create its matching prompt metadata file. Write rename_chapter Rename a chapter title or number, move its folder, and move any matching chapter or paragraph asset folders if Write rename_entity Rename an entity in a safe way: update its slug and id, move its markdown file, and move any matching asset fo Write rename_paragraph Rename a paragraph or scene title or number, move its markdown file, and move any matching paragraph asset fol Write review_chapter_with_personas Review a chapter from the perspective of one or more reader personas and write the results to evaluations/chap Write revise_chapter Propose a chapter-level editorial pass without writing files. Use this when you want diagnosis plus scene-by-s Write save_book_item Create or update a structured idea or note entry at book level. Use this for active idea queues and note queue Write save_chapter_item Create or update a structured idea or note entry tied to a chapter draft. Write seed_default_personas Seed the book repository with the five built-in reader personas if they do not already exist. The default pers Write start_wizard Start a multi-step guided wizard session for creating canon files or chapter structures. Use this when the use Write sync_all_resumes Refresh every chapter resume and the total book resume in one pass. Write sync_plot Refresh the root plot.md file so it tracks chapter progression, revealed secrets, and timeline dates from curr Write sync_resume Refresh a chapter resume or the total book resume from the current repository state without calling another mo Write sync_script_ledger Regenerate state/script-ledger.md deterministically from every script file, including secret maps, variable ti Write sync_story_state Refresh state/current.md and per-chapter state snapshots from chapter resume state_changes. This stays manual Write update_book_notes Update the global working notes or story-design document. Use appendBody when the user asks you to keep a note Write update_chapter Update an existing chapter metadata file and optional chapter notes body. Use this for summary, POV, tags, and Write update_chapter_draft Update an existing chapter draft by patching its frontmatter and replacing or appending rough draft body conte Write update_chapter_notes Update or append chapter-specific working notes stored in drafts/<chapter>/notes.md. Use this when the user wa Write update_entity Update an existing entity file by patching frontmatter and optionally replacing or appending markdown body con Write update_paragraph Apply an existing paragraph or scene revision after the user confirmed it. Use this for summary, viewpoint, ta Write update_paragraph_draft Update an existing paragraph draft by patching its frontmatter and replacing or appending rough scene content. Write update_script Update an existing scene script in scripts/<chapter>/<paragraph>.md. Use this to refine beats, add new lines, Write wizard_answer Answer the current prompt in a running wizard session and receive the next guided question. Write wizard_finalize Finalize a wizard session and write the corresponding file or folder into the local book repository. Write write_paragraph_evaluation Write the final paragraph evaluation file using LLM-supplied editorial strengths, concerns, canon notes, next
READ 27 tools
Read chapter_wizard Return the Narrarium chapter checklist so the agent can gather the right details before creating a chapter. Read chapter_writing_context Assemble the point-in-time context that should be read before writing or polishing a chapter: prose defaults, Read character_wizard Return the Narrarium character creation checklist so the agent can gather the right information before creatin Read faction_wizard Return the Narrarium faction creation checklist so the agent can gather the right details before creating a fa Read item_wizard Return the Narrarium item creation checklist so the agent can gather the right details before creating an item Read list_personas List all reader personas defined in the book repository Read list_related_canon List canon files that reference or mention a given id or query, useful before writing scenes or revising conti Read location_wizard Return the Narrarium location creation checklist so the agent can gather the right details before creating a l Read paragraph_to_script Reverse-engineer a scene script skeleton from an existing paragraph body. Use this when: - A paragraph was wr Read paragraph_wizard Return the Narrarium paragraph or scene checklist so the agent can gather the right details before creating a Read paragraph_writing_context Assemble the point-in-time context that should be read before writing or polishing a paragraph: prose defaults Read prepare_paragraph_evaluation Compute objective text metrics and style context for a single paragraph and return them as structured data so Read query_canon Answer a natural-language canon question by combining structured state, summaries, chapters, and repository se Read read_script Read an existing scene script and return its meta-language body plus the legend. Use this to inspect a script Read read_script_ledger Read the generated state/script-ledger.md file, if it exists. Read repository_spec Return the Narrarium repository model and canon rules so clients can understand the book framework structure. Read resume_book_context Assemble restart context for a book project using prose rules, stable context, summaries, and exported convers Read review_dialogue_action_beats Review a final paragraph beat by beat to judge whether dialogue-adjacent actions are purposeful, weak, or bett Read script_to_paragraph Assemble the full writing context needed to turn a scene script into polished prose. Returns: - The script bo Read search_book Search the local book repository across canon, chapters, notes, summaries, and research before drafting or edi Read secret_wizard Return the Narrarium secret creation checklist so the agent can gather the right details before creating a sec Read setup_framework Return the exact npx commands and setup steps to bootstrap a new Narrarium project from scratch, or to upgrade Read timeline_event_wizard Return the Narrarium timeline event checklist so the agent can gather the right details before creating a time Read validate_book Validate Narrarium frontmatter and file placement rules inside the local book repository. Read wikipedia_page Fetch English and the user Read wikipedia_search Search English and the user Read wizard_status Inspect the current state of a wizard session, including collected fields and the next question.
EXPLORE

Related servers

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

Yaver 1060 tools
paymentsadminautomation
Binance MCP Server 734 tools
paymentsadminautomation
GoHighLevel MCP Server 566 tools
paymentsadminautomation
GoCreative Agent API 546 tools
paymentsadminautomation
Claude Flow 454 tools
paymentsadminautomation
ServiceTitan MCP Server 454 tools
paymentsadminautomation
CloudStack MCP Server 442 tools
paymentsadminautomation
Integrations MCP 420 tools
paymentsadminautomation
FAQ

Questions about Narrarium

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

Yes. The Narrarium server exposes 2 destructive tools including revise_paragraph, wizard_cancel. 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 Narrarium? +

The Narrarium server has 51 write tools including apply_dialogue_action_beats, create_asset_prompt, create_chapter. 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 Narrarium.

How many tools does the Narrarium MCP server expose? +

80 tools across 5 categories: Destructive, Execute, Financial, Read, Write. 27 are read-only. 53 can modify, create, or delete data.

How do I enforce a policy on Narrarium? +

Register the Narrarium 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 Narrarium tool call.

Deterministic rules across all 80 Narrarium tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON NARRARIUM →

Instant setup, no code required.

80 Narrarium tools catalogued and risk-classified — across an index of 43,000+ 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.