Skip to content

MCP servers › io.github.MRRengi › rengi-forge

MCP server · registry snapshot 2026-10-23 · last tested 2026-10-23

io.github.MRRengi/rengi-forge

Gamedev tools for AI agents: level design, renders, sprites, GLB optimizer. Pay per call with x402. — the publisher's description

1 of 2 record checks metRead-only · tools listed 2026-10-23Topic: media-and-design · AI-classifiedversion 0.1.0streamable HTTP36 tools

Summary

io.github.MRRengi/rengi-forge is a remote MCP server listed in the official MCP registry at version 0.1.0. On 2026-10-23 ProtocolProbe connected to it in read-only mode and read its inventory: 36 tools, 0 resources and 0 prompts.

Record checks

1 of 2 record checks met · 7 do not apply

  • met: Registry entry is active and says how to run it
  • not met: Source repository link opens
  • not applicable: Repository is not archived
  • not applicable: Code pushed to the repository in the 90 days before our check
  • not applicable: Repository publishes a security policy (SECURITY.md)
  • not applicable: Package names its licence with a standard (SPDX) identifier
  • not applicable: The version the registry lists can be installed and is not withdrawn
  • not applicable: npm package carries build provenance (attestation)
  • not applicable: No known critical or high advisory in the package or its dependencies
  • Not ranked by downloads: a remote server publishes no download figure
  • Not ranked by stars: no public GitHub repository

From public records, not a safety rating. Each check with its reason · Is it safe to install?

Key facts

Runs
remote (hosted by the publisher)
Transport
streamable HTTP
Sign-in
none needed to open a session
Tools
36
Described as changing data
34 of 36 toolsAI-classified
Mainly works on
accounts and data in outside web servicesAI-classified
Topic
media-and-designAI-classified
Last tested
2026-10-23

Add to your client

Observed fact

This server accepted a session without any credential and lists 4 tools whose name or declaration suggests they change data (sprite_tools_remove_bg, store_assets_steam, store_assets_icons, store_assets_stores). That is our reading of the names; we did not call them. Source: our connection, 2026-10-23.

Worth knowing before you connect it

  • 34 tools are described as changing something (level_design_catalog, level_design_place, level_design_revise, …): our AI model's reading of the descriptions, not something we tested, and the server opened a session without any credential. We did not call them.

Each line comes from a section below, with its source and date.

How fresh this is

Live-tested
yes, a real session (not a text-only review)
Last tested
2026-10-23
Mode
read-only (no tool calls)
Latest version
0.1.0, published 2026-10-20 (registry, as of the 2026-10-23 snapshot)
First listed version
2026-10-20 (earliest version still in the registry; older removed versions would be earlier)
Registry data
snapshot 2026-10-23
Package and repository
checked 2026-10-23
Engine
mcp-runtime-engine@0.1.0 · sdk@1.32.0

Changes since the last refresh

New in the registry: not in the list of 2026-10-04, listed on 2026-10-23 with version 0.1.0 (published 2026-10-20).

Source: the official MCP Registry list on 2026-10-04 and on 2026-10-23.

What it is

What does this server offer?

Observed inventory
36tools
0resources
0prompts

What it mainly works on, as our AI model read its tool descriptions: accounts and data in outside web services.

34 of 36 tools are described as changing something (creating, editing, deleting, sending or running).

  • forge_helpreads or searches

    “What Rengi Forge offers, prices and how payment works.”

    Takes no inputs.

  • level_design_catalogcreates or changes datadescribed as changing data

    “Ingest your prop catalog: footprint, height, pivot and category computed from each GLB.”

    2 inputs, 1 required
    • assetsarrayrequired
    • upAxisstring
  • level_design_placecreates or changes datadescribed as changing data

    “Dress a level: placements for every zone, previews and a 3D viewer link.”

    10 inputs, 1 required
    • catalogIdstring
    • catalogobject
    • layoutobjectrequired
    • heightmapobject
    • briefstring
    • presetstring
    • densitynumber
    • seedinteger or string
    • targetEnginestring
    • planobject“Optional: skip the planner and solve this plan exactly.”
  • level_design_revisecreates or changes datadescribed as changing data

    “Change a placed level by instruction or structured zone edits: denser or sparser, other assets, remove a kind of prop; untouched zones keep their exact transforms.”

    3 inputs, 1 required
    • jobIdstringrequired
    • instructionstring
    • editsarray
  • level_design_place_2dcreates or changes datadescribed as changing data

    “Fill a 2D tilemap: terrain with proper corner transitions, decorations, obstacles and multi-tile stamps; Tiled .tmj, Unity Tilemap JSON and a preview.”

    8 inputs, 3 required
    • tilesetobjectrequired
    • tileRolesobjectrequired
    • layoutobjectrequired
    • briefstring
    • presetstring
    • densitynumber
    • seedinteger or string
    • planobject
  • level_design_revise_2dcreates or changes datadescribed as changing data

    “Change a 2D map by instruction or zone edits; untouched zones keep their tiles.”

    3 inputs, 1 required
    • jobIdstringrequired
    • instructionstring
    • editsarray
  • asset_render_viewsgenerates contentdescribed as changing data

    “Render a GLB model to four PNG views (three-quarter, front, side, top) for thumbnails and previews, plus mesh stats and size.”

    5 inputs
    • glbstring“Base64 GLB.”
    • glbUrlstring
    • upAxisstring
    • sizenumber
    • backgroundstring
  • asset_render_turntablegenerates contentdescribed as changing data

    “Render a GLB model as a looping turntable GIF, one full revolution, plus mesh stats.”

    5 inputs
    • glbstring“Base64 GLB.”
    • glbUrlstring
    • upAxisstring
    • sizenumber
    • framesinteger
  • asset_render_spritesgenerates contentdescribed as changing data

    “Transparent isometric sprite sheet, 4 or 8 directions in one row (south first, clockwise), with frame JSON.”

    7 inputs
    • glbstring“Base64 GLB.”
    • glbUrlstring
    • upAxisstring
    • directionsnumber
    • cellSizeinteger
    • elevationDegnumber
    • pixelArtboolean
  • sprite_tools_slicecalculates or convertsdescribed as changing data

    “Cut a sprite sheet into frames by grid or by transparent gaps; frame PNGs plus a ZIP.”

    12 inputs
    • imagestring“Base64 PNG, JPEG or WebP.”
    • imageUrlstring
    • modestring
    • colsinteger
    • rowsinteger
    • cellWidthinteger
    • cellHeightinteger
    • margininteger
    • spacinginteger
    • minAreainteger“auto mode: ignore islands smaller than this many pixels”
    • mergeDistanceinteger“auto mode: islands closer than this merge into one sprite”
    • trimboolean
  • sprite_tools_packdescribed as changing data

    “Pack frames into one atlas (MaxRects) with padding and edge extrusion; TexturePacker JSON and Unity JSON.”

    6 inputs, 1 required
    • framesarrayrequired
    • maxSizeinteger
    • paddinginteger
    • extrudeinteger
    • trimboolean
    • powerOfTwoboolean
  • sprite_tools_pixelatecalculates or convertsdescribed as changing data

    “Clean pixel art: find the true pixel grid, downscale to it, snap to a palette, hard alpha.”

    6 inputs
    • imagestring“Base64 PNG, JPEG or WebP.”
    • imageUrlstring
    • scaleinteger“Size of one art pixel in image pixels; detected when omitted.”
    • palettearray“Hex colors to snap to.”
    • colorsinteger
    • alphaThresholdinteger
Show 24 more tools
  • sprite_tools_remove_bgcalculates or convertsdescribed as changing data

    “Cut a sprite, prop or character out of its background: exact keying for one-color backgrounds (text and holes too), AI segmentation for busy ones; clean edges with no halo, trimmed, with a pivot.”

    7 inputs
    • imagestring“Base64 PNG, JPEG or WebP.”
    • imageUrlstring
    • modestring“auto: flat key when the border is one color, AI segmentation otherwise.”
    • keepstring“main: only the main subject and what touches it; all: everything that is not background.”
    • trimboolean
    • paddinginteger
    • pivotstring
  • sprite_tools_video_to_sheetcalculates or convertsdescribed as changing data

    “Turn an animation video or GIF (from Kling, Veo, Sora or a capture) into a sprite sheet: frames at your fps, background removed, every frame aligned to one box and pivot so it does not jitter, the be…”

    10 inputs
    • videostring“Base64 MP4, WebM, MOV or GIF.”
    • videoUrlstring
    • fpsnumber
    • startnumber
    • endnumber
    • maxFramesinteger
    • backgroundstring“auto: keep the video's own transparency, key a one-color background, or use AI (max 24 frames).”
    • frameSizeinteger“Longest side of one frame.”
    • pixelArtboolean“Scale with nearest neighbour.”
    • columnsinteger
  • sprite_tools_normal_mapdescribed as changing data

    “Normal map for a sprite or sprite sheet, for 2D lights in Unity URP 2D and Godot: a rounded bevel from the silhouette plus surface detail, alpha kept, OpenGL or DirectX; a height map and a preview li…”

    6 inputs
    • imagestring“Base64 PNG sprite or sheet with transparency.”
    • imageUrlstring
    • bevelnumber“Rim width in pixels; from the sprite size when omitted.”
    • strengthnumber
    • detailnumber“How much surface detail from the colors goes into the bumps.”
    • conventionstring“opengl (green up) for Unity and Godot.”
  • sprite_tools_autotiledescribed as changing data

    “Two terrain textures (grass over dirt, sand over water) to a full 47-tile autotile set with natural, seamless edges, outer and inner corners, plus ready rules: Tiled wang set, Godot 4 TileSet terrain…”

    10 inputs
    • basestring“Base terrain texture (what is underneath: dirt, water), base64 PNG/JPEG/WebP.”
    • baseUrlstring
    • topstring“Top terrain texture (what you paint: grass, sand), base64.”
    • topUrlstring
    • tileSizeinteger
    • edgestring“soft for painted styles, crisp for pixel art.”
    • rimboolean“crisp only: a dark 1 px outline on the top terrain's edge.”
    • edgeWidthnumber“How deep the transition sits into a tile, as a fraction of the tile.”
    • roughnessnumber“0 = straight edges, 1 = very irregular.”
    • seedinteger
  • glb_optimizer_optimizecalculates or convertsdescribed as changing data

    “Shrink a GLB (up to 10 MB) for web or mobile: dedup, join draw calls, gentle simplify, textures to WebP at a max size, meshopt or Draco compression; before/after renders, size report and loader notes…”

    7 inputs
    • glbstring“Base64 GLB.”
    • glbUrlstring
    • presetstring
    • maxTextureSizeinteger
    • simplifyRationumber“Target share of triangles to keep (0 = only the error bound decides).”
    • compressionstring
    • textureFormatstring
  • glb_optimizer_optimize_largecalculates or convertsdescribed as changing data

    “Shrink a large GLB (up to 50 MB) for web or mobile, same pipeline as optimize: dedup, join, simplify, WebP textures, meshopt or Draco.”

    7 inputs
    • glbstring“Base64 GLB.”
    • glbUrlstring
    • presetstring
    • maxTextureSizeinteger
    • simplifyRationumber“Target share of triangles to keep (0 = only the error bound decides).”
    • compressionstring
    • textureFormatstring
  • glb_optimizer_inspectreads or searches

    “Inspect a GLB without changing it: triangles, draw calls, materials, texture memory, animations, glTF validator errors, and concrete suggestions to make it lighter.”

    2 inputs
    • glbstring
    • glbUrlstring
  • glb_optimizer_convertcalculates or convertsdescribed as changing data

    “Convert FBX, OBJ (zip with .mtl and textures), glTF (zip), STL, PLY, DAE or 3DS to one GLB: Y-up, in meters, materials and FBX animations kept.”

    5 inputs
    • filestring“Model file as base64: FBX, GLB, STL, PLY, DAE, 3DS, or a ZIP holding an OBJ/glTF with its .mtl/.bin and textures.”
    • fileUrlstring
    • fileNamestring“Original file name, helps tell the format apart.”
    • upAxisstring“auto trusts FBX/glTF/DAE metadata, assumes Y-up for OBJ and Z-up for STL/PLY/3DS.”
    • unitScalestring or number“Multiply sizes by this to get meters; auto reads FBX units and treats large STLs as millimeters.”
  • glb_optimizer_lodcalculates or convertsdescribed as changing data

    “Generate a LOD chain from a GLB (default 100/50/25/10% of triangles) with locked borders so UV seams and silhouettes hold; one GLB per level, a side-by-side render and Unity LODGroup transition heigh…”

    4 inputs
    • glbstring
    • glbUrlstring
    • ratiosarray
    • lockBorderboolean“Keep open edges and UV seams in place (recommended).”
  • glb_optimizer_colliderscalculates or convertsdescribed as changing data

    “Collision for a model: a set of convex hulls that hug the shape (V-HACD), ready for Godot (-convcolonly nodes), Unreal (UCX_ names) and Unity (convex MeshColliders via an editor script), plus hulls.j…”

    6 inputs
    • glbstring
    • glbUrlstring
    • enginestring
    • maxHullsinteger“Upper limit; the fewest hulls that fit the shape (within 3% of the volume the limit gives) are used.”
    • resolutioninteger“Voxels used to read the shape; higher follows small details.”
    • maxVerticesPerHullinteger“64 keeps every hull valid for Unity convex MeshColliders (255 polygons).”
  • texture_tools_seamlesscalculates or convertsdescribed as changing data

    “Make a texture tile without visible seams: removes baked lighting, hides the seam along the path where the image already matches.”

    4 inputs
    • imagestring“Texture as base64 (PNG, JPEG or WebP).”
    • imageUrlstring“Texture as a URL.”
    • delightboolean“Remove baked light/dark gradients first so the tile does not show bands.”
    • blendWidthnumber“Overlap used to hide the seam, as a fraction of the size.”
  • texture_tools_pbrdescribed as changing data

    “PBR maps from one albedo image: normal (OpenGL for Unity/three.js and DirectX for Unreal), 16-bit height, roughness and ambient occlusion, plus a lit preview.”

    7 inputs
    • imagestring“Albedo (base color) texture as base64 (PNG, JPEG or WebP).”
    • imageUrlstring“Albedo (base color) texture as a URL.”
    • heightobject“Optional height map you already have.”
    • delightboolean
    • normalStrengthnumber
    • invertHeightboolean“Set when dark areas are raised (e.g.”
    • roughnessstring or number
  • texture_tools_packdescribed as changing data

    “Pack grayscale maps into one texture for an engine preset: Unreal ORM, Unity URP metallic/smoothness, Unity HDRP mask map.”

    7 inputs, 1 required
    • presetstringrequired
    • aoobject
    • roughnessobject
    • smoothnessobject“Give roughness or smoothness; the other is derived (smoothness = 1 - roughness).”
    • metallicobject
    • detailobject
    • sizeinteger“Output side; default is the largest input.”
  • texture_tools_atlasdescribed as changing data

    “Pack textures into one atlas with edge-filled gutters so mipmaps do not bleed; UV rects for bottom-left (Unity, OpenGL) and top-left (DirectX, Unreal) origins.”

    4 inputs, 1 required
    • texturesarrayrequired
    • paddinginteger“Gutter around each texture, filled with its edge pixels so mipmaps do not bleed.”
    • powerOfTwoboolean
    • maxSizeinteger
  • audio_tools_cleancalculates or convertsdescribed as changing data

    “Trim silence, normalize loudness to a LUFS target with a -1 dBTP ceiling, add anti-click fades and convert (ogg, wav, mp3; mono for SFX).”

    9 inputs
    • audiostring“Audio file as base64 (wav, mp3, ogg, flac, m4a).”
    • audioUrlstring“Audio file URL.”
    • formatstring
    • kindstring“Sets the loudness target and channel default: sfx -16 LUFS mono, music -18 stereo, ambience -20 stereo, voice -16 mono.”
    • targetLufsnumber
    • trimSilenceboolean
    • silenceThresholdDbnumber
    • monoboolean
    • sampleRatenumber
  • audio_tools_loopcalculates or convertsdescribed as changing data

    “Turn music or ambience into a seamless loop: cuts at zero crossings and crossfades the end into the start with an equal-power curve.”

    7 inputs
    • audiostring“Audio file as base64 (wav, mp3, ogg, flac, m4a).”
    • audioUrlstring“Audio file URL.”
    • formatstring
    • startSecnumber
    • endSecnumber
    • crossfadeMsnumber
    • monoboolean
  • audio_tools_variationsdescribed as changing data

    “Make 2-12 variations of one sound effect with small pitch and volume changes, so repeated footsteps or hits do not sound copy-pasted.”

    8 inputs
    • audiostring“Audio file as base64 (wav, mp3, ogg, flac, m4a).”
    • audioUrlstring“Audio file URL.”
    • formatstring
    • countinteger
    • pitchSemitonesnumber“Max pitch change either way.”
    • volumeDbnumber“Max volume change either way.”
    • seedinteger
    • monoboolean
  • audio_tools_voicecalculates or convertsdescribed as changing data

    “Make a voice recording or TTS take game-ready: rumble high-passed, noise reduced against the measured floor, sibilance tamed, dialogue loudness (-18 LUFS) with a -1 dBTP ceiling, and a long take spli…”

    7 inputs
    • audiostring“Audio file as base64 (wav, mp3, ogg, flac, m4a).”
    • audioUrlstring“Audio file URL.”
    • formatstring
    • targetLufsnumber“Dialogue loudness; -18 LUFS is a common game VO target.”
    • denoisenumber“0 gentle, 1 strong.”
    • splitboolean“One file per phrase.”
    • minSilenceMsinteger“A pause at least this long separates two phrases.”
  • store_assets_steamdescribed as changing data

    “Every Steam store and library capsule from one key art at the exact required sizes: logo composited per Steam rules, Library Hero without logo, separate transparent Library Logo, page background, a c…”

    4 inputs, 1 required
    • keyArtobjectrequired“Your main artwork, ideally without text, at least 1920 px wide.”
    • logoobject“Game logo with a transparent background.”
    • heroArtobject“Artwork for the Library Hero with no logo or text; key art is used when omitted.”
    • dimBackgroundnumber“How much to darken the page background so text stays readable.”
  • store_assets_iconsdescribed as changing data

    “App icons from one square art: iOS 1024 with Contents.json, Android adaptive icon layers at every density plus legacy and Play Store 512, and web favicons with a manifest snippet.”

    4 inputs, 1 required
    • artobjectrequired“Square artwork, at least 1024x1024.”
    • foregroundobject“Android adaptive icon foreground with transparency; the art is used when omitted.”
    • backgroundstring“Android adaptive background colour; sampled from the art's edge when omitted.”
    • namestring
  • store_assets_storesdescribed as changing data

    “One key art and logo to the store images beyond Steam: itch.io cover 630x500, Google Play feature graphic 1024x500, Epic landscape 2560x1440 and portrait 1200x1600; gameplay screenshots fitted to Goo…”

    4 inputs, 1 required
    • keyArtobjectrequired“Main artwork without text, at least 1920 px wide.”
    • logoobject“Game logo with a transparent background.”
    • screenshotsarray“Gameplay screenshots to fit to Google Play and App Store sizes.”
    • storesarray
  • font_tools_bitmapdescribed as changing data

    “Bitmap font from a TTF/OTF: atlas PNG, BMFont .fnt with kerning, JSON and a preview of a sample line.”

    11 inputs
    • fontstring“TTF or OTF file as base64.”
    • fontUrlstring
    • sizeinteger“Pixel size (em).”
    • modestring“pixel: crisp, no antialiasing, for pixel art games; smooth: antialiased.”
    • charsetstring
    • charsstring“charset=custom: exactly these characters.”
    • colorstring“Glyph colour baked into the atlas (white lets the engine tint it).”
    • outlineinteger
    • outlineColorstring
    • paddinginteger
    • samplestring
  • leaderboard_boardscreates or changes datadescribed as changing data

    “Create a board with 100,000 submissions and 365 days; returns keys and a ready JS snippet.”

    6 inputs, 1 required
    • namestringrequired
    • sortstring“desc: higher is better; asc: lower is better (times)”
    • minScorenumber
    • maxScorenumber
    • periodsarray
    • signedboolean“Require HMAC-signed submissions (for games with a server).”
  • leaderboard_topupcreates or changes datadescribed as changing data

    “Add 100,000 submissions and 365 days to a board.”

    2 inputs, 2 required
    • boardIdstringrequired
    • adminKeystringrequired

Each quoted sentence is the first sentence of the publisher’s own description. The kind of tool and the “changes data” mark are our AI model’s reading of that description, not something we tested: two differently worded runs had to agree, otherwise no label is shown, and nobody has checked them by hand. A tool without the “changes data” mark is described as only reading, searching or calculating, or the two runs did not agree. No tool was called. Read the publisher’s full description before relying on it. Inputs are the parameters in the tool's own input schema: name, declared type, whether it is required, and the first sentence of its description. Read 2026-10-23.

How well are its tools described?

Features #4 and #5

How clearly this server's own tool descriptions say what a tool does, and how consistent its tool list is. The first part is an AI model's yes/no reading of each description; the second part is counted. We do not turn it into a grade.

Descriptions

AI reading of each description

Says what the tool does
100% of 36 tools
Says what it returns
100% of 33 tools
Says when to use it
100% of 36 tools
Items covered per tool
4.0 of 4 on average

Counted from the listing

Parameters with a description
38% of 215
Tools with a description
100% of 36
Typical description length
456 characters

The tool set

Counted from the listing

Tools
36
Size of the list
about 16,488 tokens for an agent to load (characters ÷ 4)
Naming
36 of 36 names use snake_case

AI reading: easy to mix up

No pair found.

The AI items cover 36 of 36 tools: for a tool where two differently worded runs disagreed, that item is left out. They were not checked by hand, and no tool was called. “Easy to mix up” means two tools whose names or descriptions overlap without saying how they differ; the AI found none. We do not rate whether the tool set is complete or whether side effects are spelled out, because our AI reading of those was not reliable enough.

How do I add it to my client?

Config from the registry entry

From the remote endpoint (Streamable HTTP)

We connected to this URL on 2026-10-23 (a read-only session: no tool was called).

Add to CursorAn install link in the format Cursor documents, holding the Cursor config below.

Claude Desktop or claude.ai
Settings → Connectors → Add custom connector, then paste:
https://rengi.dev/mcp
Cursor · .cursor/mcp.json in a project, or ~/.cursor/mcp.json
{
  "mcpServers": {
    "rengi-forge": {
      "url": "https://rengi.dev/mcp"
    }
  }
}
VS Code · .vscode/mcp.json
{
  "servers": {
    "rengi-forge": {
      "type": "http",
      "url": "https://rengi.dev/mcp"
    }
  }
}
VS Code (command line) · Bash or zsh terminal (macOS, Linux)
code --add-mcp '{"name":"rengi-forge","type":"http","url":"https://rengi.dev/mcp"}'
Claude Code
claude mcp add --transport http rengi-forge https://rengi.dev/mcp
Try it in the MCP Inspector · runs on your machine, opens in your browser · Node 22.19+
npx @modelcontextprotocol/inspector@2.11.0 --server-url https://rengi.dev/mcp --transport http
  • The server runs on the operator's infrastructure; it may ask you to sign in when you first connect.
  • The MCP Inspector lists the server's tools, resources and prompts; a tool you call there runs for real.

Built from the server's registry entry with each client's documented format (checked 2026-10-14; the Cursor link and the VS Code command 2026-10-19; the MCP Inspector command 2026-10-21). Values in < > are yours to fill in; this page never contains a key. Where the server needs a setting the entry does not declare, it can still fail to start.

Does the registry listing match what we found?

Feature #6

The registry verifies a package once, when it is published, and does not re-check it. A difference below is about the listing, not a judgement of the publisher.

Registry saysWe foundResultSource · date
Remote endpoint rengi.dev/mcpSession openedmatchesour test · 2026-10-23
No credential declared as requiredOpened a session without any credentialmatchesour test · 2026-10-23

Choosing

Record checks

Public records · not a safety rating

1 of 2 record checks met · 7 do not apply

  • Not ranked by downloads: a remote server publishes no download figure
  • Not ranked by stars: no public GitHub repository
  • MetRegistry entry is active and says how to run itActive, with a package or a remote address.
  • Not metSource repository link opensThe registry entry gives no repository link.
  • Does not applyRepository is not archivedNo public GitHub repository to read.
  • Does not applyCode pushed to the repository in the 90 days before our checkNo public GitHub repository to read.
  • Does not applyRepository publishes a security policy (SECURITY.md)No public GitHub repository to read.
  • Does not applyPackage names its licence with a standard (SPDX) identifierRemote server: it ships no package.
  • Does not applyThe version the registry lists can be installed and is not withdrawnRemote server: it ships no package.
  • Does not applynpm package carries build provenance (attestation)Remote server: it ships no package.
  • Does not applyNo known critical or high advisory in the package or its dependenciesRemote server: it ships no package.

Read from public records only: the registry entry, npm/PyPI, GitHub and advisory databases, checked 2026-10-23. No tool was called. Only “met” and “not met” are counted, so the total differs between servers; a check that does not apply or that we could not run is listed, never counted against it. It is not a safety rating. How each check works · Leaderboards

Common questions about io.github.MRRengi/rengi-forge

Answered from the data above

Is io.github.MRRengi/rengi-forge safe to install?

We do not rate servers as safe or unsafe. 1 of its 2 applicable record checks are met (facts from public records, each listed on this page). What the records show: 34 of its tools describe changing data (our AI model's reading of the descriptions). These are facts with their sources on this page, not a safety guarantee, and we did not run its tools.

Does io.github.MRRengi/rengi-forge need an API key or sign-in?

It opened a session without any credential on 2026-10-23. The registry entry declares no required credential; no declaration is not a guarantee.

Has io.github.MRRengi/rengi-forge been security tested?

Partly. 3 of the 15 checks that apply to it were exercised. It accepted a session without any credential and lists tools whose names suggest they change data. We did not call them. No security verdict is published before verification.

What can io.github.MRRengi/rengi-forge do?

It lists 36 tools. In our AI model's reading of their descriptions (two runs had to agree, nobody checked it by hand), they include tools that read or search, create or change data, generate content and calculate or convert. We did not call any tool, so this describes the text, not the behaviour.

Can io.github.MRRengi/rengi-forge change or delete data?

34 of its tools say in their description that they create, edit, delete, send or run something (our AI model's reading). We did not call any tool, so we cannot say what actually happens.

Found this page useful?

Anonymous · no sign-in

A quick, anonymous reaction — no account, no email. One per kind from your browser. The tally updates when the page is next refreshed, and it is only a rough count, never a safety rating or a measured number of people.

Similar servers

Same topic · AI-read

Active servers whose topic is also “media-and-design” and that have at least one tool of the same kind; most kinds in common first, then most GitHub stars. The topic and the tool kinds are an AI model's reading of the publishers' descriptions, not checked by hand. Similar is not a recommendation.

Compare with another server

Side by side: registry entry, our read-only session, the tools and the 18 classification fields. Same values as each page; no score.

Security testing

What did we test, and what did we leave out?

18 checks · features #1, #2

Open without sign-in

It accepted a session without any credential and lists tools whose names suggest they change data. We did not call them. No security score is given; a check we did not run is never counted as passed.

The 18 checks at a glanceour test · 2026-10-23
  1. Inventory: exercised
  2. Hidden instructions: exercised
  3. Real execution: not run · our policy
  4. Secret leak: not run · nothing to check it against
  5. Internal addresses: not run · our policy
  6. Unconfirmed changes: not run · our policy
  7. Bad input: not run · our policy
  8. Model requests: not run · nothing to check it against
  9. Sensitive questions: not run · nothing to check it against
  10. Folder boundary: not run · our policy
  11. Log leaks: not run · nothing to check it against
  12. Hidden content: not run · nothing to check it against
  13. Fake assistant turns: not applicable
  14. Token passthrough: not applicable
  15. Token audience: not applicable
  16. Sign-in redirect: not run · our policy
  17. Consent handling: not testable from outside
  18. Sign-in metadata: exercised

3 exercised12 not run (reason given)3 not applicable

Each check ends in exactly one state: exercised, not run (with the reason), or not applicable (with the reason). 3 of the 15 checks that apply to it were exercised. We do not publish security-check outcomes for named servers.

Exercised · 3
  • 1Inventory
    tool-list
    Reads the declared tools, resources and prompts.exercised
  • 2Hidden instructions
    description-poisoning
    Looks for hidden instructions in tool descriptions.exercised
  • 18Sign-in metadata
    oauth-url-scheme
    Checks the published sign-in metadata for unsafe URLs.exercised
Not run, with the reason · 12
  • 3Real execution
    real-execution
    Calls a tool and checks what really happens.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes; an operator can run this check on their own server with our self-test command.not run · our policy
  • 4Secret leak
    canary-leak
    Plants a fake secret and checks whether it leaks.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against
  • 5Internal addresses
    ssrf
    Checks whether a tool can be steered to internal addresses.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes; an operator can run this check on their own server with our self-test command.not run · our policy
  • 6Unconfirmed changes
    write-without-confirmation
    Checks whether tools that change data act without asking.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes; an operator can run this check on their own server with our self-test command.not run · our policy
  • 7Bad input
    error-handling
    Sends bad input and watches how the server answers.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes; an operator can run this check on their own server with our self-test command.not run · our policy
  • 8Model requests
    sampling
    Checks whether the server asks the client's model to act for it.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against
  • 9Sensitive questions
    elicitation-sensitive-data
    Checks whether the server asks users for sensitive data.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against
  • 10Folder boundary
    root-boundary
    Checks whether the server reaches outside the folders it was given.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes; an operator can run this check on their own server with our self-test command.not run · our policy
  • 11Log leaks
    logging-side-channel
    Checks whether log messages carry data they should not.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against
  • 12Hidden content
    audience-hiding
    Checks resources that hide content from the user.This check needs content the server returns, and nothing was read or called.not run · nothing to check it against
  • 16Sign-in redirect
    open-redirect
    Checks the sign-in redirect for abuse.Testing the sign-in redirect means sending probes to the operator's sign-in service, which we do not do.not run · our policy
  • 17Consent handling
    confused-deputy
    Checks consent handling when one service acts for another.Depends on the operator's own consent screen, which differs per server and cannot be tested from outside.not testable from outside
Does not apply to this server · 3
  • 13Fake assistant turns
    fake-assistant-turn
    Checks prompts that pose as the assistant's own words.The server exposes no prompts.not applicable
  • 14Token passthrough
    token-passthrough
    Checks whether the server forwards a user's token to other services.The server opened a session without sign-in, so there is no token flow to check.not applicable
  • 15Token audience
    token-audience-validation
    Checks whether tokens meant for another service are accepted.The server opened a session without sign-in, so there is no token flow to check.not applicable

Source: our own test, 2026-10-23, mcp-runtime-engine@0.1.0. Which checks count and why follows our published scoring model.

What happened during the test?

Feature #8

The steps in order, as the test record holds them.

  1. 0 msStarted a read-only session with the server's remote endpoint
  2. 1,360 msConnected after 0 redirects. No credential was sent or needed.
  3. Read the inventory: 36 tools, 0 resources, 0 prompts.
  4. 3,978 msFinished: 3 checks exercised.

Reference

How is it classified?

18 fields

One value per field, each with its source. Fields written by AI models are marked. A field with no value says why.

TopicAI-classified
AI-classified · 2026-10-23
Pricing modelAI-classified
not checked
no website in the registry entry
Programming language
does not apply
no existing GitHub repository (server declares no repository link, so there is nothing to fetch)
Hosting type
registry · 2026-10-23
MCP capability
tools
our test · 2026-10-23
Transport
streamable HTTP
registry · 2026-10-23
Required credentials
none declared
registry · no declaration is not a guarantee
Package registry
does not apply
remote-only server: no package is shipped, so there is no package registry
Freshness
0–30 days
registry updatedAt · 2026-10-23
Lifecycle status
registry · 2026-10-23
License class
does not apply
remote-only server: ships no package, so there is nothing to look up in a package registry
Integrity hash
does not apply
remote-only server: ships no package, so there is nothing to look up in a package registry
Signature / provenance
does not apply
remote-only server: ships no package, so there is nothing to look up in a package registry
Dependency advisories
does not apply
ships no package, so there are no dependencies to audit
Popularity
does not apply
remote-only server: ships no package, so there is nothing to look up in a package registry
Publisher signals
not stated
no readable GitHub owner to describe
Maintenance
does not apply
server declares no repository link, so there is nothing to fetch
Environment
the publisher's infrastructure
where it runs, from the hosting type

“Not stated” means the source did not state it; “does not apply” means it does not apply to this kind of server; “our limit” means our own lookup failed. A linked value opens the directory filtered to the same value.

Cite or correct this page

Sources and corrections

Suggested citation

ProtocolProbe. “io.github.MRRengi/rengi-forge: MCP server record.” Data checked 2026-10-23. https://protocolprobe.com/mcp/servers/io.github.MRRengi/rengi-forge

Figures are valid for the date shown. Our facts on this page are CC BY 4.0: reuse them with a link and the check date. Quoted text (the publisher’s descriptions, website quotes, tool names) is not ours to license.

As JSON: this record in the API · API documentation.

Badge for your README

ProtocolProbe: 1 of 2 record checks met

[![ProtocolProbe](https://protocolprobe.com/api/v1/badge/io.github.MRRengi/rengi-forge)](https://protocolprobe.com/mcp/servers/io.github.MRRengi/rengi-forge)

It shows this server's record-check count: facts from public records, no tool called. It is not a security rating or a pass. It links here and updates after each data reload.

Something wrong, or is this yours?

If a fact here is wrong, tell us and we will re-check it. If you operate this server, you can run our checks on it yourself with the free self-test command; we call no server’s tools ourselves for anything shown here.

Write to hello@protocolprobe.com · corrections log · methodology