MCP server for interacting with the Scryfall MTG API
Nothing to run from here
Dungeondraft is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
96/100
trust score
14
downloads a day
local
runs on your machine
308
downloads in 30d
What it does
Read, edit and export Dungeondraft maps; convert Universal VTT (.dd2vtt) into Foundry VTT scenes
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user dungeondraft-mcp '--' npx -y dungeondraft-mcp
# 2 — ask your agent for something these tools do
# list-maps, inspect-map, list-assets and 12 more
Dungeondraft costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
CAAll 1 server
casancam1 server
1 category
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Installation
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. This one runs on your machine: your client starts Dungeondraft as a process under your own user, with your files and your network, so the tool surface below is what it can do to your computer rather than to a server somewhere else. Its scan result is on the Security tab — read the surface before you approve it.
Claude Codedeclared by this listing
This is a public server: you run it yourself and this marketplace is not in the path. You need Node.js — the current LTS (24) is the safe choice; npx comes with it. Claude Code registers it in one command; --scope user makes it available in every project. The '--' is in quotes so that PowerShell passes it on.
claude mcp add --scope user dungeondraft-mcp '--' npx -y dungeondraft-mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
Free on mcprush, and it runs from its publisher’s own package: this marketplace is not in the path, so there is no key of ours to hold and no card to add.
What it asks of you
Nothing is required, but it can take DD_MCP_ROOTS (Folders the server may read and write maps in, separated by ;. Default: your Documents folder), DUNGEONDRAFT_DIR (Dungeondraft install folder (contains Dungeondraft.pck), for built-in asset search. Auto-detected on Windows), DD_ASSET_DIRS (Dungeondraft asset folders with .dungeondraft_pack files, separated by ;) if you want to set them.
What it writes
One config entry your client uses to start the process locally. A local server runs with your file system and your network, which is why it is priced without metering.
What you approve
15 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
Find … files under a folder (default: all configured folders). Returns path, size and last-modified time, newest first.
No parameter schema on file.
Summarise a map: size, levels, element counts, terrain, asset packs and most-used assets. Optionally list elements (node_id, asset, grid position) of given types, filtered by area, to target edits or removals. Never returns raw file data. Coordinates are GRID SQUARES from the map's top-left corner…
No parameter schema on file.
Search installed assets: Dungeondraft built-ins plus asset packs in the configured asset folders. Returns the exact texture path to pass to the add-* tools. Call with no filters for an overview (counts per category, packs, tags). Search matches words in the path and tags, e.g. query "table round"…
No parameter schema on file.
Place objects (props, furniture, trees...) on a level. "at" is the object's CENTRE. Rotation in degrees clockwise. Asset paths come from list-assets (category objects) and are validated; a custom pack is added to the map's manifest automatically. Coordinates are GRID SQUARES from the map's…
No parameter schema on file.
Draw walls as polylines through grid points; set loop=true to close a room. Optional doors are placed on the wall at a grid point (door centre), default 1 square wide. To add doors to an existing wall, pass add_doors_to_wall with its node_id (from inspect-map list ["walls"]). Wall/door textures…
No parameter schema on file.
Add point lights. "range" is the radius in grid squares (default 5), intensity 0-1+ (default 1), colour "#RRGGBB" (default warm ffeccd8b, as Dungeondraft uses). Lights only show in Dungeondraft when the level's lighting is not fully bright. Coordinates are GRID SQUARES from the map's top-left…
No parameter schema on file.
Draw path assets (roads, rivers' edges, fences, cliffs, cave walls...) along grid points. Width in squares (default 1). smooth=false gives sharp corners. Path textures come from list-assets (category paths). Coordinates are GRID SQUARES from the map's top-left corner (x right, y down). (3, 4) is…
No parameter schema on file.
Add floor patterns (wood planks, cobble, tiles...) over a rectangle or polygon. Built-in floors are res://textures/tilesets/simple/... (list-assets category "tilesets", query "simple"); pack floors are category "patterns". Floors are drawn above terrain and below objects. Coordinates are GRID…
No parameter schema on file.
Build complete rooms in one step: a closed wall around a rectangle (or polygon) plus a matching floor and doors. Doors go at grid points on the outline, e.g. the middle of the south wall of area {x:10,y:5,width:6,height:4} is [13, 9]. Coordinates are GRID SQUARES from the map's top-left corner (x…
No parameter schema on file.
Change a level's ambient light, e.g. to make a night variant after duplicate-map. Presets: ${Object.entries(AMBIENT_PRESETS) .map(([k, v]) =>
No parameter schema on file.
Change a level's terrain: assign textures to slots 1-8 (list-assets category terrain), fill the whole level with one slot, and/or paint strokes. Each stroke is an area (rectangle), circle or line (polyline with a width, for trails/roads) painted with a slot; "feather" (squares) softens the edge…
No parameter schema on file.
Remove elements of the given types that lie entirely inside an area, and/or by node_id (from inspect-map). Walls take their doors with them. Requires an area or node_ids. Use dry_run first to see what would go. Coordinates are GRID SQUARES from the map's top-left corner (x right, y down). (3, 4)…
No parameter schema on file.
Copy a map to a new file in the same folder (or a given path) to start a variant, e.g. a night version. Never overwrites an existing file.
No parameter schema on file.
Dungeondraft is needed to render map images, so this cannot export on its own. It builds a .dd2vtt from the map's walls, doors and lights plus an image you exported from Dungeondraft (File > Export > PNG/WEBP of the whole map, no grid if you want Foundry's). Useful when you changed…
No parameter schema on file.
Convert a .dd2vtt/.uvtt into Foundry VTT v13 scene data: grid, walls, doors and lights, plus the map image extracted to a file. Writes <name>.<png|webp> and <name>.foundry-scene.json. Upload the image to Foundry (e.g. The Forge Assets Library), then in Foundry create a scene and use "Import Data"…
No parameter schema on file.
Free
$0 forever
- Every tool, no call limit
- No card, and mcprush charges nothing for it
- Source published under MIT
- Runs on your machine — nothing of it reaches our gateway
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install Dungeondraft or to call it, at any volume.
Call allowance · this installenforced at the gateway
Monthly allowance, in calls
—
—
Alert at 80% · then the tool returns a normal MCP error
Used this month: —
ATrust score 96 / 100
Release 0.1.0 · scanned 14 Oct 2026
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
Threat score100
Client score96
Findings0 threat · 0 capability
Capabilitymoderate
Coveragesource
Verificationrepo
Surface digestcb7633d85eef022fe66ef42ef80bb7d4f45dcbef883cefd5f5873227b2ecb025
Score vectorthreat 100 → client 96
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | moderate | capability blast radius (moderate) — client exposure if the model is manipulated | −3 |
| verification-discount | repo | publisher verification (public source) — no provenance, but the source is public and inspectable | −1 |
| coverage-honesty | source | inspection depth (source) — how much of the target the scan could see | −0 |
score = clamp(round(threatScore − E_cap − E_ver − E_cov), 0, 100). No model, no opinion, no network call at scoring time: the same methodology version against the same bytes always produces this number, and every line above is a field of the report rather than a summary of it.
What the scan could actually read
A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.
Tool surfaceread
Implementation sourceread
Package metadataread
Live transportnot available
Tools were statically extracted from the published source (15 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command "npx -y <package>".
Capability — what it could do if the model were manipulated
Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. moderate is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| list-maps | no tags | |
| inspect-map | no tags | |
| list-assets | no tags | |
| add-objects | state-write | state-write: declares readOnlyHint: false |
| add-walls | state-write | state-write: declares readOnlyHint: false |
| add-lights | state-write | state-write: declares readOnlyHint: false |
| add-paths | state-write | state-write: declares readOnlyHint: false |
| add-floors | state-write | state-write: declares readOnlyHint: false |
| build-room | state-write | state-write: declares readOnlyHint: false |
| set-environment | state-write | state-write: declares readOnlyHint: false |
| set-terrain | state-write | state-write: declares readOnlyHint: false, destructiveHint: true |
| remove-elements | state-write | state-write: declares readOnlyHint: false, destructiveHint: true |
| duplicate-map | state-write | state-write: declares readOnlyHint: false |
| export-dd2vtt | state-write | state-write: declares readOnlyHint: false |
| dd2vtt-to-foundry-scene | state-write | state-write: declares readOnlyHint: false |
Toxic-flow graph
The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.
The public result for this release does not print the flow graph, so there is nothing to show here. That is not the same as "no paths were found": what the scan did read is above, under coverage.
Supply chain and provenance
Integrityfirst-seen
Surface digestcb7633d85eef022f
Scanned2026-10-14
This is the first scan of this surface here, so there is nothing yet to compare it against.
Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.
Release history
Always latest — the install command names no version, so it installs the newest release when it runs; the current release on file is 0.1.0. Pin a release below and the command asks for exactly that one.
0.1.0
undated
latestNo release note was published with this version.
—
no reviews yet
Who can review
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Sign in to write one
Any signed-in account that does not publish Dungeondraft can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
No reviews yet
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.