MCP server for interacting with the Scryfall MTG API
Nothing to run from here
X4CodeSense 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.
92/100
trust score
15
downloads a day
local
runs on your machine
915
downloads in 30d
What it does
X4: Foundations scripts: checks, schema elements, expression types, scripts, cues and texts.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user x4codesense-mcp '--' npx -y x4-script-mcp
# 2 — ask your agent for something these tools do
# check, describe_element, expression_type and 6 more
X4CodeSense costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
PublisherVerified · since 2026
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 X4CodeSense 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 x4codesense-mcp '--' npx -y x4-script-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 X4_GAME (The installed game, the folder of X4.exe; its files are read from the catalogs.), X4_UNPACKED (The extracted game files, the folder holding libraries, md and aiscripts; used instead of X4_GAME.) 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
9 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.
Checks X4 scripts and patches as the X4CodeSense editor and x4-script-check do: well-formedness, the game schemas, expressions, variables, names, cues, scripts and texts referred to. Returns the findings with their quick fixes (edits to apply), and counts. Run it after every change to an md or…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| paths | array | yes | Files and folders. A folder is checked as x4-script-check checks it: the md, aiscripts and libraries folders in it and one level deeper, so an extension or a folder of extensions. Relative paths are t |
| text | string | no | The text to check instead of what is on disk, for one file in paths: what you are about to write there. |
| severity | string | no | The least severe finding to report: error, warning, info or hint (the default, all). |
An element of the Mission Director or AI script schema, from the game’s md.xsd or aiscripts.xsd: its documentation, its attributes (type, required, default, allowed values, whether the value is an expression) and the child elements it allows. Use it before writing an element or attribute you are…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| name | string | yes | The element name: set_value, find_ship, create_order, cue. |
| script | string | yes | md for Mission Director scripts, aiscripts for AI scripts. |
| parent | string | no | The parent element, for an element declared differently in different places, such as param or actions. |
| attribute | string | no | One attribute in full: every allowed value with its documentation. Without it, every attribute with the first values by name. |
What a keyword or a property chain of the expression language yields, step by step, from the game’s scriptproperties.xml: player.ship, player.ship.sector, event.param; and the properties of the result with their types. Or a datatype’s properties. A variable has no type here, its type comes from…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| expression | string | no | A keyword and its properties: player.ship.sector. |
| datatype | string | no | Instead of an expression, a datatype: ship, sector, list, faction. |
| script | string | no | The script kind, for the keywords of one kind only: md (the default) or aiscripts. |
| filter | string | no | Only the properties of the result whose names contain this text, with their descriptions, also those of the types derived from it. Without it, its own and inherited properties as name → type. |
Mission Director scripts, AI scripts, cues, libraries and interrupt library items (actions, handlers, conditions) of the game, its DLCs and the extensions, by name: whole names first, then those starting with the query, then those containing it; the extensions’ before the game’s among equals. A…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| query | string | yes | A name or part of one. |
| limit | integer | no | The most names to return; 50 by default. |
Where what is named at a place of a script is defined, as the editor’s go to definition finds it: a cue, script, library, label, variable, order, text, element or attribute of the schema, property of scriptproperties.xml. Each place with its line of text.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| file | string | yes | The script or patch. |
| line | integer | yes | The line, from 1. |
| column | integer | yes | The column, from 1. |
Every place that names what is named at a place of a script, in the game, its DLCs and the extensions, as the editor finds them: who signals a cue, includes a library, runs a script. Each place with its line of text. Use it instead of searching the files for a name.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| file | string | yes | The script or patch. |
| line | integer | yes | The line, from 1. |
| column | integer | yes | The column, from 1. |
What the editor’s hover shows for a place of a script or patch: an element or attribute with its documentation from the schema, a step of a property chain with its type and description from scriptproperties.xml, a variable with its type and where the type comes from, a cue or script with where it…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| file | string | yes | The script or patch. |
| line | integer | yes | The line, from 1. |
| column | integer | yes | The column, from 1. |
Texts of the game and the extensions, as the game shows them, references resolved: {page, id} in a language; the texts of a page; or the texts that contain some words. Use it instead of searching the t folders: for what a {page, id} says, or to find an existing text to reuse.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| page | integer | no | The page id. |
| id | integer | no | The text id on the page; without it, the texts of the page. |
| search | string | no | Instead of page and id: words that must all be in the text, without regard to case. |
| language | string | no | The language number, 44 for English; by default the one the server was started with. |
| limit | integer | no | The most texts to return for a page or a search; 20 by default. |
What the server read: the game folder, the extension folders, how many scripts and texts, and the problems met reading them.
No parameter schema on file.
Free
$0 forever
- Every tool, no call limit
- No card, and mcprush charges nothing for it
- Source published under Apache-2.0
- 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 X4CodeSense 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 92 / 100
Release 0.4.0 · scanned 15 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 score98
Client score92
Findings2 threat · 6 capability
Capabilityhigh
Coveragesource
Verificationsource
Surface digest3ccef7137597af98a75f06b3b84ddd7f3ef73ce104eb5720fe720c4571d019e1
Score vectorthreat 98 → client 92
| 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 (9 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 |
|---|---|---|
| check | no tags | |
| describe_element | code-exec | code-exec: parameter "script" |
| expression_type | code-exec | code-exec: parameter "script" |
| find | no tags | |
| definition | no tags | |
| references | no tags | |
| hover | no tags | |
| text | no tags | |
| status | no tags |
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 digest3ccef7137597af98
Scanned2026-10-15
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 0.4.0. Pin a release below and the command asks for exactly that one.
0.4.0
6 Oct 2026
latestNo release note was published with this version.
0.3.0
4 Oct 2026
No release note was published with this version.
0.2.0
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 X4CodeSense 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.