This server exposes 77 MCP tools for reading and writing Kanka worldbuilding campaign data via the Kanka API.
List your campaigns (list_campaigns) to find campaign IDs.
Search entities within a campaign (search, requires campaignId and query q).
Manage 15 entity types — Characters, Locations, Families, Organizations, Items, Notes, Events, Calendars, Timelines, Creatures, Races, Quests, Maps, Journals, and Abilities.
For each entity type, five CRUD tools:
list_<entities> — list records in a campaign (paginated via page).
get_<entity> — fetch full details of one record by id.
create_<entity> — create a new record from a data object.
update_<entity> — modify an existing record by id with data.
delete_<entity> — remove a record by id.
Everything is scoped to a campaign — every tool except list_campaigns requires a campaignId.
Note: the README documents extra list_* options (per_page, entries, entry_filter) and mentions list tools for Organizations, but the live schema only exposes page and campaignId, and names the list tool list_organisations while its CRUD siblings use organization.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Kanka MCP Server List my campaigns"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Local MCP tool for the Kanka worldbuilding API. Runs on your machine via stdio — no remote server needed.
Node.js 20+.
A Kanka API token (get one at kanka.io/en/settings/api).
Related MCP server: kanka-mcp
npm installAdd this to your MCP client config:
{
"mcpServers": {
"kanka": {
"command": "node",
"args": ["<ABSOLUTE_PATH_TO_REPO>/index.js"],
"env": {
"KANKA_API_TOKEN": "<YOUR_KANKA_TOKEN>"
}
}
}
}Notes:
Replace <ABSOLUTE_PATH_TO_REPO> with the full path to this repository.
On Windows, prefer forward slashes (C:/Users/...) or escaped backslashes (C:\\Users\\...).
Restart the MCP client after editing the config.
KANKA_API_TOKEN=your_token npm startnpm install -g .
KANKA_API_TOKEN=your_token kanka-mcpThe tool exposes 77 MCP tools for interacting with Kanka:
list_campaigns — List all campaigns
search — Search entities within a campaign
For each entity type (Character, Location, Family, Organization, Item, Note, Event, Calendar, Timeline, Creature, Race, Quest, Map, Journal, Ability):
list_<entities> — List all
get_<entity> — Get details
create_<entity> — Create new
update_<entity> — Update existing
delete_<entity> — Delete existing
Big campaigns return list pages that are too large for some MCP clients to show
in full, which hides the records in the middle of the response. Every
list_<entities> tool takes these options to keep a page small and complete:
Option | Values | Description |
| number | Page number, default |
| 1–100 | Records per page. Enforced by this server, so it holds even when the Kanka API answers with a different page size. Omit it to return the API's own page untouched. |
| boolean | Default |
|
| Default |
When per_page or entry_filter is used, the response carries this server's own
meta instead of the API's:
{
"data": [{ "id": 42, "name": "Thalion", "has_entry": false }],
"meta": {
"page": 1,
"per_page": 100,
"count": 1,
"has_more": false,
"entry_filter": "empty",
"entries_included": false,
"total_unfiltered": 168,
"api_pages_fetched": 12
}
}Notes:
per_page defaults to 25 with entries, 100 without, and pages are stitched
from as many API requests as needed.
total_unfiltered is the size of the whole collection as reported by Kanka —
it is not the number of records left after entry_filter. Walk pages until
has_more is false.
scan_incomplete: true means the budget of 50 API requests per call ran out
before the window was filled, so records past that point were not scanned.
Example — find every character with no entry yet, in as few calls as possible:
{ "campaignId": 235025, "per_page": 100, "entries": false, "entry_filter": "empty" }Community contributions are welcome.
Read CONTRIBUTING.md for workflow, coding standards, and PR checklist.
Review CODE_OF_CONDUCT.md before participating.
npm run lint
npm run format:check
npm testThe .mcpb bundle is built by the MCP bundle (.mcpb) GitHub Actions workflow, not by hand. On every pull request it validates manifest.json, packs the bundle with the official mcpb CLI and starts it to check that it answers an MCP initialize request. Pushes to main keep the bundle as a workflow artifact, and v* tags attach it to the matching GitHub release.
To cut a release, bump the version in both package.json and manifest.json (CI fails if they differ), merge, then push the tag v<version>. The workflow creates the GitHub release for that tag if it does not exist yet and attaches the .mcpb to it; write the release notes by editing that release afterwards. Files that must stay out of the bundle are listed in .mcpbignore.
To build one locally:
npm ci --omit=dev
npx @anthropic-ai/mcpb@2.1.2 pack . kanka-mcp.mcpb
npm ci # restore the dev dependencies (eslint, prettier) removed aboveCreate a new ability
Inputs: data (required), campaignId (required).
Create a new calendar
Inputs: data (required), campaignId (required).
Create a new character
Inputs: data (required), campaignId (required).
Create a new creature
Inputs: data (required), campaignId (required).
Create a new event
Inputs: data (required), campaignId (required).
Create a new family
Inputs: data (required), campaignId (required).
Create a new item
Inputs: data (required), campaignId (required).
Create a new journal
Inputs: data (required), campaignId (required).
Create a new location
Inputs: data (required), campaignId (required).
Create a new map
Inputs: data (required), campaignId (required).
Create a new note
Inputs: data (required), campaignId (required).
Create a new organization
Inputs: data (required), campaignId (required).
Create a new quest
Inputs: data (required), campaignId (required).
Create a new race
Inputs: data (required), campaignId (required).
Create a new timeline
Inputs: data (required), campaignId (required).
Delete an existing ability
Inputs: id (required), campaignId (required).
Delete an existing calendar
Inputs: id (required), campaignId (required).
Delete an existing character
Inputs: id (required), campaignId (required).
Delete an existing creature
Inputs: id (required), campaignId (required).
Delete an existing event
Inputs: id (required), campaignId (required).
Delete an existing family
Inputs: id (required), campaignId (required).
Delete an existing item
Inputs: id (required), campaignId (required).
Delete an existing journal
Inputs: id (required), campaignId (required).
Delete an existing location
Inputs: id (required), campaignId (required).
Delete an existing map
Inputs: id (required), campaignId (required).
Delete an existing note
Inputs: id (required), campaignId (required).
Delete an existing organization
Inputs: id (required), campaignId (required).
Delete an existing quest
Inputs: id (required), campaignId (required).
Delete an existing race
Inputs: id (required), campaignId (required).
Delete an existing timeline
Inputs: id (required), campaignId (required).
Get details of a ability
Inputs: id (required), campaignId (required).
Get details of a calendar
Inputs: id (required), campaignId (required).
Get details of a character
Inputs: id (required), campaignId (required).
Get details of a creature
Inputs: id (required), campaignId (required).
Get details of a event
Inputs: id (required), campaignId (required).
Get details of a family
Inputs: id (required), campaignId (required).
Get details of a item
Inputs: id (required), campaignId (required).
Get details of a journal
Inputs: id (required), campaignId (required).
Get details of a location
Inputs: id (required), campaignId (required).
Get details of a map
Inputs: id (required), campaignId (required).
Get details of a note
Inputs: id (required), campaignId (required).
Get details of a organization
Inputs: id (required), campaignId (required).
Get details of a quest
Inputs: id (required), campaignId (required).
Get details of a race
Inputs: id (required), campaignId (required).
Get details of a timeline
Inputs: id (required), campaignId (required).
List abilities. Use per_page to keep responses small enough to be returned whole, and entry_filter to return only records whose entry is empty or filled.
Inputs: campaignId (required), page, entries, per_page, +1 more.
List calendars. Use per_page to keep responses small enough to be returned whole, and entry_filter to return only records whose entry is empty or filled.
Inputs: campaignId (required), page, entries, per_page, +1 more.
List all campaigns
Inputs: no named parameters.
List characters. Use per_page to keep responses small enough to be returned whole, and entry_filter to return only records whose entry is empty or filled.
Inputs: campaignId (required), page, entries, per_page, +1 more.
List creatures. Use per_page to keep responses small enough to be returned whole, and entry_filter to return only records whose entry is empty or filled.
Inputs: campaignId (required), page, entries, per_page, +1 more.
List events. Use per_page to keep responses small enough to be returned whole, and entry_filter to return only records whose entry is empty or filled.
Inputs: campaignId (required), page, entries, per_page, +1 more.
List families. Use per_page to keep responses small enough to be returned whole, and entry_filter to return only records whose entry is empty or filled.
Inputs: campaignId (required), page, entries, per_page, +1 more.
List items. Use per_page to keep responses small enough to be returned whole, and entry_filter to return only records whose entry is empty or filled.
Inputs: campaignId (required), page, entries, per_page, +1 more.
List journals. Use per_page to keep responses small enough to be returned whole, and entry_filter to return only records whose entry is empty or filled.
Inputs: campaignId (required), page, entries, per_page, +1 more.
List locations. Use per_page to keep responses small enough to be returned whole, and entry_filter to return only records whose entry is empty or filled.
Inputs: campaignId (required), page, entries, per_page, +1 more.
List maps. Use per_page to keep responses small enough to be returned whole, and entry_filter to return only records whose entry is empty or filled.
Inputs: campaignId (required), page, entries, per_page, +1 more.
List notes. Use per_page to keep responses small enough to be returned whole, and entry_filter to return only records whose entry is empty or filled.
Inputs: campaignId (required), page, entries, per_page, +1 more.
List organisations. Use per_page to keep responses small enough to be returned whole, and entry_filter to return only records whose entry is empty or filled.
Inputs: campaignId (required), page, entries, per_page, +1 more.
List quests. Use per_page to keep responses small enough to be returned whole, and entry_filter to return only records whose entry is empty or filled.
Inputs: campaignId (required), page, entries, per_page, +1 more.
List races. Use per_page to keep responses small enough to be returned whole, and entry_filter to return only records whose entry is empty or filled.
Inputs: campaignId (required), page, entries, per_page, +1 more.
List timelines. Use per_page to keep responses small enough to be returned whole, and entry_filter to return only records whose entry is empty or filled.
Inputs: campaignId (required), page, entries, per_page, +1 more.
Search entities
Inputs: q (required), campaignId (required).
Update an existing ability
Inputs: id (required), data (required), campaignId (required).
Update an existing calendar
Inputs: id (required), data (required), campaignId (required).
Update an existing character
Inputs: id (required), data (required), campaignId (required).
Update an existing creature
Inputs: id (required), data (required), campaignId (required).
Update an existing event
Inputs: id (required), data (required), campaignId (required).
Update an existing family
Inputs: id (required), data (required), campaignId (required).
Update an existing item
Inputs: id (required), data (required), campaignId (required).
Update an existing journal
Inputs: id (required), data (required), campaignId (required).
Update an existing location
Inputs: id (required), data (required), campaignId (required).
Update an existing map
Inputs: id (required), data (required), campaignId (required).
Update an existing note
Inputs: id (required), data (required), campaignId (required).
Update an existing organization
Inputs: id (required), data (required), campaignId (required).
Update an existing quest
Inputs: id (required), data (required), campaignId (required).
Update an existing race
Inputs: id (required), data (required), campaignId (required).
Update an existing timeline
Inputs: id (required), data (required), campaignId (required).
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Scored across 77 tools
Each entity type has a clear list/get/create/update/delete split, so tool selection is mostly determined by the entity being managed. The generic `search` tool and the broad `list_*`/`get_*` surface add slight overlap, but no two tools appear to do the same job.
Nearly all tools follow a snake_case verb_noun pattern, such as `create_event` and `delete_calendar`. Minor deviations exist: `search` is a bare verb, and the spelling inconsistency between `list_organisations` and the CRUD tools using `organization` breaks the otherwise predictable naming.
77 tools for CRUD across 16 entity types is extremely heavy and well past the 50+ threshold for an oversized surface. The same coverage could be exposed with fewer generic or grouped tools, and this count is likely to overwhelm tool selection.
Core lifecycle coverage is strong: every major entity type has list/get/create/update/delete operations, avoiding obvious CRUD dead ends. However, campaign-level operations, relations, tags, posts, members, and other Kanka features are absent, so non-CRUD workflows may hit gaps.
Access your Kazkar TTRPG world — campaigns, chronicles, transcripts, lore — in any MCP client.
Manage your tabletop RPG campaign from any MCP client: worlds, sessions, quests, lore, recaps.
MCP server for Argo RPG Platform — connects AI assistants to campaign data via OAuth2
Rick and Morty MCP — wraps the Rick and Morty API (free, no auth)
