MCP server for interacting with the Scryfall MTG API
Nothing to run from here
Kadal Store 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.
94/100
trust score
14
tools declared
local
or remote
—
downloads a day
What it does
Find assets for what you're making, download what you own, and get a buy link to review.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user kadal-store-mcp '--' npx -y @kadal/store mcp
# 2 — ask your agent for something these tools do
# whoami, list_shelves, search_products and 11 more
Remote: OAuth sign-in · Package: no sign-in.
Kadal Store costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
KAAll 2 servers
kadal2 servers
2 categories
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 can run either way — at an address its publisher runs, or as a process under your own user, with your files and your network — and this marketplace is in the path of neither.
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 kadal-store-mcp '--' npx -y @kadal/store mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
Or connect to its publisher’s address
Its publisher also runs it at https://store.kadal.cc/mcp: nothing to start on your machine, and this marketplace is not in the path.
claude mcp add --scope user --transport http kadal-store-mcp https://store.kadal.cc/mcpFree 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 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
14 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.
Read from its source code. A server that builds its tool list when it starts can list more tools than this.
The person this store sign-in belongs to (id, name, email), its scopes, and whether they run the store. Call it when unsure whether the person is signed in.
No parameter schema on file.
The store's shelves (its categories), each with a slug, name, blurb, how many products it holds, and its licence model. Use a shelf slug to narrow search_products or recommend.
No parameter schema on file.
Search the catalogue. Returns product cards: slug, name, kind (asset or pack), shelf, blurb, url, prices per licence tier in US cents, tags (style, topic, format), and owned (the person's tier if they already own it). Page with nextCursor.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| query | string | no | Words to search for, e.g. 'weekly planner a5' or 'retro ui sound effects'. |
| shelf | string | no | A shelf slug from list_shelves. |
| style | string | no | A style tag, e.g. minimal, pixel-art. |
| topic | string | no | A topic tag. |
| format | string | no | A format tag, e.g. pdf, wav, glb, png. |
| kind | string | no | asset: one product; pack: a bundle of several. |
| maxCents | integer | no | Only products from at most this price, in US cents (2000 = $20). |
| sort | string | no | — |
| limit | integer | no | How many (default 20). |
| cursor | string | no | nextCursor from the previous page. |
Everything about one product: description, prices per tier, its files (name, bytes, minimum tier, edition), editions, what a pack contains and which packs include it, the licence (what each tier allows and does not), and its update history. Check the licence before suggesting a product for…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| slug | string | yes | The product's slug. |
Products that fit what the person is working on. context is a few plain lines about the project and what it needs (project_summary's text is a good start; add what the person asked for). Never put file contents, secrets or personal data in it. Each item has a one-line why and a score;…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| context | string | yes | What the project is and what it needs, at most 6000 characters. |
| shelves | array | no | Shelf slugs to keep to. |
| formats | array | no | Formats to prefer, e.g. ['pdf'] or ['wav', 'ogg']. |
| maxCents | integer | no | Price ceiling in US cents. |
| includeOwned | boolean | no | Also list products the person owns (default false). |
| limit | integer | no | How many (default 8). |
Every product the person owns: the product card, their tier, its files (id, name, bytes, sha256, edition), whether a zip is available, whether it is recolourable (recolor: the colour it is drawn in and the one they last chose), and the latest update. File ids go to download_to_folder or…
No parameter schema on file.
Download URLs for files the person owns, each with its name, size and sha256, valid for 10 minutes; no cookie needed (curl -L works). Narrow with fileIds or an edition; zip: true adds one link for the whole product; color recolours a recolourable product's SVGs (their names become…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| slug | string | yes | — |
| fileIds | array | no | Only these files (ids from list_library). |
| edition | object | no | — |
| zip | boolean | no | Also a link to the whole product as one zip. |
| color | string | no | — |
A link to a review page on the store where the person sees each item (picture, licence, price), anything they already own, and the total, and pays in the checkout themselves. Only when the person asked to buy or agreed to it; building the link charges nothing and buys nothing. Give them the URL,…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| items | array | yes | — |
| ref | string | no | Where the link came from, for the store's counts (default agent). |
Tell Kadal about a product the person has: a mistake (a typo, a wrong date, a missing page, a broken file), a question, or an idea. Say where with fileName and page (PDFs, from 1) or timeSeconds (audio and video). The note is private to the person and Kadal, and its replies show in list_my_notes.…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| slug | string | yes | — |
| fileName | string | no | The file the problem is in, as list_library names it. |
| page | integer | no | The PDF page, counting from 1. |
| timeSeconds | number | no | Seconds into the audio or video. |
| kind | string | yes | — |
| body | string | yes | What is wrong and where, in plain words. |
The person's notes (reports) on products, with each one's status (open, accepted, declined, duplicate, fixed), a plain status line, and the thread with Kadal's replies.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| status | string | no | — |
A short summary of a project folder, without its contents: name and description from package.json / pyproject.toml / Cargo.toml, dependency names, tools it uses (Godot, Blender, Next.js, Obsidian…), the README's headings, file-type counts and the top-level names. It is what `kadal-store recommend…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| dir | string | no | A folder, relative to the project (default: the project itself). |
Download files the person owns into the project, each checked against its sha256; files already there with the same checksum are skipped. dir is relative to the project (default kadal-store/<slug>). Narrow with fileNames or fileIds (from list_library) or an edition, or zip: true for the whole…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| slug | string | yes | — |
| dir | string | no | — |
| fileNames | array | no | Only these files, by name. |
| fileIds | array | no | Only these files, by id. |
| edition | object | no | — |
| zip | boolean | no | The whole product as one zip instead of its files. |
| color | string | no | — |
| overwrite | boolean | no | Download again even when the same file is already there. |
Operator only: every person's notes, filtered by status, kind, shelf or planned wave, with counts per status.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| status | string | no | — |
| kind | string | no | — |
| shelf | string | no | — |
| wave | string | no | A planned wave, e.g. wave-4. |
| limit | integer | no | — |
Operator only: accept (with the wave it is planned for), decline, mark duplicate (of another note), reopen, or mark fixed, with an optional reply the author is emailed. Each call writes to the note's thread; do it once per decision, and only as the operator asked.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | string | yes | — |
| decision | string | yes | — |
| reply | string | no | — |
| wave | string | no | — |
| duplicateOf | string | no | — |
Free
$0 forever
- Every tool, no call limit
- No card, and mcprush charges nothing for it
- Source published under AGPL-3.0
- 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 Kadal Store 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 94 / 100
Release 0.1.2 · scanned 6 Nov 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 score94
Findings1 threat · 1 capability
Capabilityhigh
Coveragesource
Verificationsource
Surface digest54c291e3d0eeae9ecfba199ce8a4e6ffba49c776f13aae6e9c4baa9e8a887f29
Score vectorthreat 100 → client 94
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | high | capability blast radius (high) — client exposure if the model is manipulated | −6 |
| verification-discount | source | publisher verification (provenance) — cryptographic build provenance ties the artifact to its source | −0 |
| 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 (14 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. high is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| whoami | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| list_shelves | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| search_products | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| get_product | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| recommend | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| list_library | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| get_download_links | untrusted-input | untrusted-input: keyword "download", declares openWorldHint: true (interacts with entities outside the server) |
| create_buy_link | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| report_problem | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| list_my_notes | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| project_summary | no tags | |
| download_to_folder | untrusted-inputexternal-sink | untrusted-input: keyword "download"; external-sink: declares readOnlyHint: false, openWorldHint: true |
| feedback_queue | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| triage_note | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
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.
flow-1
Untrusted input can drive an external action even though no sensitive source is exposed.
Supply chain and provenance
Integrityfirst-seen
Surface digest54c291e3d0eeae9e
Scanned2026-11-06
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 0.1.2. Pin a release below and the command asks for exactly that one.
0.1.2
5 Nov 2026
latestNo release note was published with this version.
0.1.1
undated
- The version this listing was on when mcprush began following its releases. The registry was not asked when it shipped, so this row carries no date.
—
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 Kadal Store 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.