Storywright MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| ANTHROPIC_API_KEY | No | Anthropic API key (optional if using ANTHROPIC_AUTH_TOKEN) | |
| ANTHROPIC_BASE_URL | No | Base URL for Anthropic-compatible API (e.g. MiniMax) | |
| ANTHROPIC_AUTH_TOKEN | No | Anthropic Bearer token for MiniMax (optional if using ANTHROPIC_API_KEY) | |
| STORYWRIGHT_STATE_DIR | No | Directory for last_project.json (default ~/.storywright) | |
| STORYWRIGHT_PROJECTS_ROOT | No | Parent directory for book projects | |
| STORYWRIGHT_ANTHROPIC_MODEL | No | Model ID to use (e.g. MiniMax-M2.7) | |
| STORYWRIGHT_ANTHROPIC_MAX_RETRIES | No | Retries for transient API failures (default 2) | |
| STORYWRIGHT_PRIOR_CHAPTERS_MAX_COUNT | No | Max number of prior chapters (default 8) | |
| STORYWRIGHT_PRIOR_CHAPTERS_MAX_WORDS | No | Max words of prior approved prose (default 12000) | |
| STORYWRIGHT_ANTHROPIC_RETRY_DELAY_SECONDS | No | Base delay between retries (default 2.0) |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| create_book_projectC | Create a new book project under book_projects/ (or STORYWRIGHT_PROJECTS_ROOT). Loads the new project. |
| load_book_projectB | Load an existing project from disk (prefer absolute paths). |
| load_last_book_projectA | Load the last successfully opened project from ~/.storywright/last_project.json if valid. |
| get_project_statusB | Markdown table of chapters, statuses, editor verdicts, third-pass completion. |
| check_environmentA | Verify ANTHROPIC_API_KEY and show model / prior-chapter budget / Storywright version. |
| get_pipeline_statusB | Next MCP tool to call per chapter (guarded pipeline hints). |
| get_continuity_logC | JSON continuity log. |
| add_chapterC | Register a chapter outline. |
| add_characterC | Add a character and continuity entry. |
| add_deathC | Schedule a canonical death. |
| add_running_gagD | Register a running gag. |
| add_inventory_itemD | Track an inventory item. |
| plan_bookC | Phased book bible planning (identity→…→tone); completes with sync to project config. |
| update_planC | Patch book_bible.json; may sync characters/deaths/gags into project. |
| get_book_bibleD | Readable bible markdown. |
| start_chapterB | Open drafting for a chapter (NOT_STARTED → DRAFT). |
| run_writer_agentA | Draft chapter via Claude (DRAW → AWAITING_EDITOR). Requires ANTHROPIC_API_KEY. |
| run_editor_reviewC | Editor pass after writer. |
| run_third_agentB | Third-pass reviewer (comedy, pacing, …). Repeat until all project.third_agents covered. |
| list_third_agentsA | List built-in third-pass agents. |
| approve_chapterA | Approve chapter; updates continuity. Requires all configured third passes unless force=true. |
| request_revisionC | Send chapter back to writer with notes. |
| get_chapter_statusC | Inspect one chapter. |
| get_living_charactersD | – |
| get_inventoryD | – |
| get_running_gagsD | – |
| mark_character_deadD | – |
| transfer_itemD | – |
| fire_gagD | – |
| add_locationD | – |
| add_established_factD | – |
| export_manuscriptC | Concatenate approved chapters into one markdown file at project root. |
| diff_chapterC | Diff current draft vs |
| search_manuscriptC | Substring search across manuscript/*.md. |
| scan_manuscript_markersA | Find TODO/FIXME/DRAFT/TBD/XXX markers in manuscript markdown. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| guarded_chapter_pipeline | Recommended tool order for one chapter. |
| planning_wizard | Book bible phases. |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| resource_book_config | |
| resource_continuity | |
| resource_bible | |
| resource_project_path | |
| resource_version | Server package version (for debugging configs). |
TDQS
Scored across 35 tools
Many tool descriptions are blank or minimal (e.g., add_location, fire_gag, get_inventory), and several tools have overlapping purposes (e.g., add_death vs mark_character_dead, add_running_gag vs fire_gag). This makes it difficult for an agent to distinguish between tools.
Tool names follow a verb_noun pattern but use a wide variety of verbs (add, approve, check, create, diff, export, fire, get, list, load, mark, plan, request, run, scan, search, start, transfer, update). This variety, while not chaotic, lacks a strong consistent theme.
35 tools is far above the recommended range of 3-15 for a well-scoped set, and significantly exceeds the 25+ threshold. The high count suggests over-specialization or redundant functionality.
The tool set covers many aspects of story writing (chapters, characters, inventory, gags, planning, etc.) but lacks basic CRUD operations such as delete or update for most resources, and has redundant tools (e.g., add_death and mark_character_dead). Some obvious gaps in lifecycle management are present.