ReforgerForge MCP (wastelandgoats/reforger-forge-mcp) is an MCP server listed on the M8ven Trust Index. It scores 50 out of 100, grade D. It declares 50 tools. No publisher has claimed this listing.

D
Caution
50/100

ReforgerForge MCP

Enables AI-powered modding for Arma Reforger with 50 tools for API search, code generation, project scaffolding, and Workbench control.

Caution. Specific findings reduced this grade. They are listed on the page. Grades reflect the full trust pyramid: code, verification depth, and reputation. New projects cap at C until adoption is earned.

How we verified

⚡ Live Monitored: not connected

Verified is a snapshot. Live keeps it current, and builds your track record.

⚡ Connect GitHub → continuous verification on every pushwhy connect →

Who stands behind it

wastelandgoats

Source: Glama

Is this your MCP?

Claim it to get a verified publisher badge, a free copy of our full audit findings, and direct contact for any high-priority issues we find. Or connect your repo for our deepest verification, Live Monitored: read-only, revoke anytime. What we access →

Install from

The grade above is for the source repository. Registries can serve a different version, so we mark the ones we were not able to read.

// key findings
⚠️
Tool descriptions don’t match what handlers do
1 tool describes read intent but its handler mutates — server_config (line 105: writeFileSync(targetPath, content, "utf-8"))
🚨
Known vulnerabilities in dependencies: 2 critical
Affects packages this MCP installs at runtime. Upgrade or remove the affected dependency.
⚠️
Tests do not pass
Either the test suite is broken or the code regressed. Either way the published behaviour can’t be verified by the publisher’s own tests.
// tools this server exposes50 tools

These names and descriptions are the publisher's own, read from the source code. We print them as written. Our assessment is the findings above, not this list.

animation_graph
api_search

Search the Enfusion / Arma Reforger script API by class name, method name, or keyword. Results automatically include inherited methods from parent classes, detect enum-like constant classes (use type: 'enum'), and show related sibling classes from the same API group. Use format: 'tree' with class se

asset_search
building_setup
component_search

Search for Enfusion ScriptComponent descendants — the building blocks you attach to entities in prefabs. Filter by category (character, vehicle, weapon, damage, inventory, ai, ui, editor, camera, sound, general) and/or by event handler name (e.g., 'OnPlayerConnected', 'EOnFrame', 'OnDamage'). Use th

config_create

Create a config (.conf) file for an Arma Reforger mod. Generates faction definitions, mission headers, entity catalogs, and editor placeables in valid Enfusion text format.

game_browse
game_duplicate
game_read
layout_create

Create a UI layout (.layout) file for an Arma Reforger mod. Generates a properly structured layout with widgets in valid Enfusion text serialization format. Use for HUD elements, menus, dialogs, and custom UI.

mod

Manage Arma Reforger addons: build with the Workbench CLI, scaffold a new addon, or validate an existing addon without building.

prefab
project

Browse, read, or write files in an Arma Reforger Workbench project directory. Use action='browse' to list files, action='read' to read a file, action='write' to write a file.

scenario_create_conflict
script_create

Create a new Enforce Script (.c) file for an Arma Reforger mod. Generates a properly structured script from a template with correct class hierarchy and method stubs. When parentClass is specified and no explicit methods are given, automatically looks up overridable methods from the API index.

server_config

Generate a dedicated server config (server.json) for testing an Arma Reforger mod locally. Configures ports, mod list, scenario, and game properties.

wb_clipboard

Clipboard operations in the World Editor. Copy, cut, paste, paste at cursor, duplicate selected entities, or check if clipboard has content. Paste/cut/duplicate only work in edit mode.

wb_component

Manage components on an entity in the World Editor. Add, remove, or list components attached to an entity. Add/remove only work in edit mode.

wb_connect

Test connection to Arma Reforger Workbench. Returns connection status and current editor mode. Use this to verify Workbench is running with the NET API enabled.

wb_diagnose
wb_play

Switch Workbench to game (play) mode. Compiles scripts and launches the world for testing. Equivalent to pressing Play in the World Editor. Requires edit mode.

wb_stop

Stop game mode and return to the World Editor. Equivalent to pressing Stop in the World Editor. Requires play mode.

wb_save

Save the current world in the World Editor. Optionally save to a new path (Save As). Only works in edit mode.

wb_undo_redo

Undo or redo the last action in the World Editor.

wb_open_resource

Open a resource file in the appropriate Workbench editor (e.g., a .et prefab in the Prefab Editor, a .c script in the Script Editor).

wb_entity_create

Create a new entity in the World Editor from a prefab. Optionally set position, rotation, name, and target layer. Only works in edit mode (not play mode).

wb_entity_delete

Delete an entity from the World Editor by name. Only works in edit mode.

wb_entity_list

List entities in the current world. Supports pagination and optional name filtering.

wb_entity_inspect

Get detailed information about a specific entity, including its components, properties, position, and children. Identify by name or index.

wb_entity_modify

Modify an entity in the World Editor. Supports moving, rotating, renaming, reparenting, and setting or clearing component properties. Only works in edit mode.

wb_entity_select

Manage entity selection in the World Editor. Select, deselect, clear selection, or get the current selection.

wb_entity_duplicate
wb_execute_action
wb_knowledge
wb_launch
wb_cleanup
wb_layers

Manage layers in the World Editor. List layers, create/delete layers, rename, set active layer, query visibility, get layer info, or toggle lock. Create/delete/rename/toggleLock only work in edit mode.

wb_localization

Manage localization entries in the Workbench Localization Editor. Insert, delete, or modify string table entries, or get the full localization table.

wb_prefabs

Prefab operations in the Workbench. Create entity templates, save prefab changes, look up prefab GUIDs, or locate prefabs by path. createTemplate/save only work in edit mode.

wb_projects

Query project information from the Workbench. List all loaded addon projects, locate a specific project by name, or open a .gproj to load it into Workbench.

wb_reload

Reload scripts or plugins in the Workbench. Use after editing .c script files or Workbench plugins to pick up changes without restarting.

wb_resources

Manage Workbench resources. Register new resources, rebuild resource databases, get resource info, or open a resource in its editor.

scenario_create
wb_script_editor

Interact with the Workbench Script Editor. Get the current file, read/write individual lines, insert new lines, remove lines, or get the total line count.

wb_state

Get a full snapshot of the current Workbench state. Returns mode (edit/play), entity count, selected entity count and names, terrain bounds, sub-scene, and prefab edit status.

wb_terrain

Query terrain information. Get the terrain height at a world coordinate or get the world bounds (min/max extents).

wb_validate

Validate a material or texture resource using the Workbench's built-in validators. Returns validation errors and warnings.

wiki_read
wiki_search
workshop_info
// known CVEs in dependencies2 critical

Disclosed vulnerabilities in this server's declared npm dependencies (via OSV). Whether each is reachable depends on the installed versions.

criticalvitest@3.0.0GHSA-5xrq-8626-4rwp

When Vitest UI server is listening, arbitrary file can be read and executed

criticalvitest@3.0.0GHSA-9crc-q9x8-hgqq

Vitest allows Remote Code Execution when accessing a malicious website while Vitest API server is listening

Depend on this server? Get alerted when its CVEs change.Watch this server free →
// environment variables
To run this server yourself, you supply these values. They go in your own MCP client configuration and stay on your machine. The secret label means the value is sensitive, not that the server mishandles it.
configENFUSION_DEFAULT_MOD
configENFUSION_EXTRACTED_PATH
configENFUSION_GAME_PATH"": "C:\\Program Files (x86)\\Steam\\steamapps\\common\\Arma Reforger",
configENFUSION_MCP_DATA_DIR
configENFUSION_MCP_DEBUG
configENFUSION_PROJECT_PATH"": "C:\\Users\\YOU\\Documents\\My Games\\ArmaReforgerWorkbench\\addons"
configENFUSION_WORKBENCH_HOSTNET API host 127.0.0.1
configENFUSION_WORKBENCH_PATH"": "C:\\Program Files (x86)\\Steam\\steamapps\\common\\Arma Reforger Tools",
configENFUSION_WORKBENCH_PORTNET API port 5775
configREFORGER_FORGE_DEBUGEnable debug logging off
// quality suggestions

Dependencies

10 dependencies, 1 flagged: playwright

Tool annotations

No tools have read-only/destructive annotations

Add readOnlyHint or destructiveHint annotations to every tool so hosts can warn users before invoking.

All four hints declared on every tool

50/50 tools missing one or more hints — animation_graph (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); api_search (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); asset_search (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +47 more. OpenAI's directory rejects tools where any of the four hints are missing or non-boolean.

For every tool, set all four hints (readOnlyHint, destructiveHint, idempotentHint, openWorldHint) to explicit true/false values that match the handler’s actual behaviour.

Destructive tools are labelled

1 tool perform destructive updates without destructiveHint — scenario_create_conflict deletes at line 212 (unlinkSync(p))

Add destructiveHint:true to any tool whose handler calls .delete(), .upsert(), .update(), unlink, rm, DELETE, DROP, REPLACE INTO, or any operation that overwrites existing data.

Descriptions match behaviour

1 tool describes read intent but its handler mutates — server_config (line 105: writeFileSync(targetPath, content, "utf-8"))

Rename the tool, rewrite the description, or move the side-effect into a separate clearly-named tool.

Tool inputs are validated

46/50 tool handlers declare input schemas (92%)

Declare an inputSchema with zod/joi/yup on every tool definition.

Tool handlers catch errors

43/50 tool handlers wrap calls in try/catch (86%)

Wrap each tool handler body in try/catch and return a structured error response.

Tool test coverage

Only 2/50 tools referenced in tests (4%)

Write tests that reference each tool by name so every tool has at least one test.

Tests pass

npm test failed — tests do not pass

Make sure npm test runs cleanly. Common cause: missing build step or missing env vars.

Shell command execution

14 child_process calls — runs shell commands

Prefer library functions over shell-outs. If you must shell out, ensure all inputs are properly escaped.

Dev dependencies

2 critical/high in dev-only deps (does not ship to users)

Upgrade dev dependencies when convenient.

Tool description accuracy

server_config: description implies read-only but handler writes/deletes/executes

Update tool descriptions to accurately reflect all capabilities — especially write, delete, or execute operations.

Claim the listing to review these findings one by one and send us a correction where you disagree, straight to the team. Claiming also means we tell you when the grade moves, and reach you first if we find anything urgent.

// full audit trail
The findings above are the summary. The full trail, every check we ran, each deduction, the network hosts observed and the dependency advisories, goes to verified publishers, along with an alert whenever a new one lands. Verified publishers can also review each finding and dispute it in one click. Publisher corrections have sharpened several of our checks this month, because the maintainer knows the codebase better than any scanner.
// improvement guidance — verified publishers only
We have 11 concrete improvements we can share with the publisher of this MCP. Each comes with specific guidance to raise the trust score.
// embed badge in your README
[![M8ven Verified](https://m8ven.ai/badge/mcp/wastelandgoats/reforger-forge-mcp?variant=verified)](https://m8ven.ai/mcp/wastelandgoats/reforger-forge-mcp)
Shows verification status without the grade. Want the grade badge instead? Remove ?variant=verified from the URL.
commit: 5e5237663fd50aa40a2b4ef9e1f8e14df191ac52
code hash: a16628cbdd610015bf15e0422da7e6c7e7765c0f9a6e85f015f45a82d12a33f2
view raw JSON →
Check MCPs from inside your assistant
Tool Check · MCP

Vetting this one by hand? Tool Check is an MCP that scores other MCPs. Add it once and ask Claude, ChatGPT, or any MCP client to grade a server, surface CVEs, check the publisher, and suggest safer alternatives — before you install.

https://m8ven.ai/api/mcp/tool-check
check_toolsearch_toolscompare_toolsrecommend_alternativescheck_publisherreport_concern
How to add it →Free · no account needed · works in any MCP client