MCP servers › io.github.AI-osho › godot-mcp-loop

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

io.github.AI-osho/godot-mcp-loop

Drive a live Godot 4 editor: edit scenes and scripts, run and test the game, record GIFs. — the publisher's description

9 of 9 record checks metRead-only · tools listed 2026-10-23Topic: developer-tools · AI-classifiedversion 0.9.0TypeScriptMITstandard input/output41 tools

Summary

io.github.AI-osho/godot-mcp-loop is a local MCP server listed in the official MCP registry at version 0.9.0. On 2026-10-23 ProtocolProbe started its published package in an isolated sandbox in read-only mode and read its inventory: 41 tools, 0 resources and 0 prompts.

Record checks

9 of 9 record checks met

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met: The version the registry lists can be installed and is not withdrawn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

#5,423 of 15,115 packages by monthly downloads, tied with 5 others
Not ranked by stars: 0 stars (ranked from 10)
#508 of 809 packages meeting all 9 record checks, by downloads, tied with 1 other

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

Key facts

Runs: local package
Transport: standard input/output
Package: npm · listed version behind the latest release
License: MIT
Dependencies: no known high or critical advisories
Repository: public
Tools: 41
Described as changing data: 27 of 41 toolsAI-classified
Mainly works on: files and code on the machine it runs on; a web browser or desktop applicationsAI-classified
Topic: developer-toolsAI-classified
Last tested: 2026-10-23

Add to your client

Worth knowing before you connect it

27 tools are described as changing something (project_connect, editor_launch, editor_quit, …): our AI model's reading of the descriptions, not something we tested. We did not call them.
The registry lists 0.9.0; 0.9.2 is newer (1 release).
Its package is signed and carries a build record naming its source.

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: 0.9.0, 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 2026-10-22
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 0.9.0 (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

41tools

0resources

0prompts

What it mainly works on, as our AI model read its tool descriptions: files and code on the machine it runs on; a web browser or desktop applications.

27 of 41 tools are described as changing something (creating, editing, deleting, sending or running).

godot_statuson 1 other serverreads or searches
“Check the connection to the Godot editor and get basic state: Godot version, project name, currently edited scene and whether the game is running.”
Publisher declares: read-only yes
Takes no inputs.
project_liston 7 other serversreads or searches
“List the Godot projects this server may switch to: folders with project.godot below the --projects-root folders (up to 3 levels down, hidden folders skipped), each with its name, whether the MCP Loop…”
Publisher declares: read-only yes
Takes no inputs.
project_connecton 1 other servercreates or changes datadescribed as changing data
“Point this running server at another Godot project, so the following tool calls work on it — one MCP registration for many games.”
Publisher declares: read-only no · destructive no · open-world no
1 input, 1 required
- pathstringrequired“Project folder (the one with project.godot): absolute, ~/..., or relative to a projects root, e.g.”
editor_launchcontrols a browser or desktopdescribed as changing data
“Open the Godot editor on the current project and wait until the MCP Loop bridge answers, then return the same fields as godot_status.”
Publisher declares: read-only no · destructive no · open-world no
2 inputs
- headlessboolean“Start the editor without a window (default false).”
- timeout_msinteger“How long to wait for the bridge (default 120000; the first open of a project imports every asset).”
editor_quitcontrols a browser or desktopdescribed as changing data
“Close the Godot editor of the current project — only one this server opened with editor_launch (an editor the user opened is refused with EDITOR_NOT_LAUNCHED).”
Publisher declares: read-only no · destructive no · open-world no
2 inputs
- saveboolean“Save all open scenes first (default true).”
- timeout_msinteger“How long to wait for the editor to exit (default 20000).”
project_exporton 4 other serversruns code or commandsdescribed as changing data
“Export the project with one of its export_presets.cfg presets (Godot's `--export-release`, headless, fixed argument list, no shell).”
Publisher declares: read-only no · destructive no · open-world no
4 inputs, 1 required
- presetstringrequired“Preset name from export_presets.cfg (project_info can list them).”
- pathstring“Output under res://build/...”
- timeout_msinteger“Limit for the export process (default 600000).”
- dry_runboolean“Validate the preset and the path, show the command, export nothing.”
project_infoon 3 other serversreads or searches
“Project overview: name, main scene, autoloads, input actions and their events (Godot's built-in ui_* actions are hidden unless include_builtin_actions), and (optionally) a file list filtered by a glo…”
Publisher declares: read-only yes · destructive no · open-world no
3 inputs
- include_builtin_actionsboolean“Also list Godot's built-in ui_* actions (about 90).”
- globstring“If set, list res:// files matching this glob, e.g.”
- max_filesinteger“Cap on listed files (default 200).”
scene_opencontrols a browser or desktopdescribed as changing data
“Open a scene in the editor and make it the edited scene.”
Publisher declares: read-only no · destructive no · open-world no
1 input, 1 required
- pathstringrequired“res:// path of a .tscn/.scn file.”
scene_createcreates or changes datadescribed as changing data
“Create a new scene file with a single root node and open it.”
Publisher declares: read-only no · destructive no · open-world no
4 inputs, 2 required
- pathstringrequired“res:// path ending in .tscn, e.g.”
- root_typestringrequired“Root node class, e.g.”
- root_namestring“Root node name (default: file name in PascalCase).”
- dry_runboolean“Preview only: validate and describe the change without applying it.”
scene_savecreates or changes datadescribed as changing data
“Save the currently edited scene to disk.”
Publisher declares: read-only no · destructive no · open-world no
Takes no inputs.
scene_treeon 1 other serverreads or searches
“Node hierarchy of the edited scene: name, class, relative path, attached script and instanced scene for each node.”
Publisher declares: read-only yes · destructive no · open-world no
2 inputs
- pathstring“Subtree root.”
- depthinteger“Max depth below the subtree root (default 10).”
node_addcreates or changes datadescribed as changing data
“Add a node to the edited scene (undoable).”
Publisher declares: read-only no · destructive no · open-world no
6 inputs
- parentstring“Parent node.”
- typestring“Node class to create.”
- scenestring“res:// path of a scene to instance instead of 'type'.”
- namestring“Node name (made unique among siblings if taken).”
- propertiesobject“Initial property values.”
- dry_runboolean“Preview only: validate and describe the change without applying it.”

Show 29 more tools

node_deleteon 1 other serverdeletesdescribed as changing data
“Delete a node and its children from the edited scene (undoable with edit_undo).”
Publisher declares: read-only no · destructive yes · open-world no
2 inputs, 1 required
- pathstringrequired“Node path relative to the edited scene's root; '.' is the root itself (e.g.”
- dry_runboolean“Preview only: validate and describe the change without applying it.”
node_geton 1 other serverreads or searches
“Read properties of a node in the edited scene.”
Publisher declares: read-only yes · destructive no · open-world no
3 inputs, 1 required
- pathstringrequired“Node path relative to the edited scene's root; '.' is the root itself (e.g.”
- propertiesarray“Only these properties (supports 'position:x').”
- changed_onlyboolean“When no list is given: only non-default values (default true).”
node_setcreates or changes datadescribed as changing data
“Set one or more properties on a node as a single undoable action.”
Publisher declares: read-only no · destructive no · open-world no
3 inputs, 2 required
- pathstringrequired“Node path relative to the edited scene's root; '.' is the root itself (e.g.”
- propertiesobjectrequired“Property name -> new value.”
- dry_runboolean“Preview only: validate and describe the change without applying it.”
script_readon 1 other serverreads or searches
“Read a text resource inside the project (GDScript, shader, .tscn, .cfg ...).”
Publisher declares: read-only yes · destructive no · open-world no
1 input, 1 required
- pathstringrequired“res:// path.”
script_writecreates or changes datadescribed as changing data
“Create or overwrite a GDScript (.gd) file.”
Publisher declares: read-only no · destructive no · open-world no
3 inputs, 2 required
- pathstringrequired“res:// path ending in .gd.”
- contentstringrequired“Full new file content.”
- dry_runboolean“Preview only: validate and describe the change without applying it.”
script_editon 1 other servercreates or changes datadescribed as changing data
“Change part of an existing GDScript file by exact text replacement, without resending the whole file.”
Publisher declares: read-only no · destructive no · open-world no
3 inputs, 2 required
- pathstringrequired“res:// path of an existing .gd file.”
- editsarrayrequired
- dry_runboolean“Preview only: validate and describe the change without applying it.”
script_attachcreates or changes datadescribed as changing data
“Attach an existing script to a node in the edited scene (undoable).”
Publisher declares: read-only no · destructive no · open-world no
3 inputs, 2 required
- nodestringrequired“Node path relative to the edited scene's root; '.' is the root itself (e.g.”
- scriptstring or nullrequired“res:// path of the script, or null to detach.”
- dry_runboolean“Preview only: validate and describe the change without applying it.”
edit_undodescribed as changing data
“Undo the most recent edits made through this MCP server (node, property, script changes), newest first.”
Publisher declares: read-only no · destructive yes · open-world no
1 input
- stepsinteger“How many actions to undo (default 1).”
file_writeon 2 other serverscreates or changes datadescribed as changing data
“Create, overwrite or partially edit a text file in the project: .yaml/.yml (e.g.”
Publisher declares: read-only no · destructive no · open-world no
4 inputs, 1 required
- pathstringrequired“res:// path, e.g.”
- contentstring“Full file content (creates or overwrites).”
- editsarray“Exact text replacements applied in order to the existing file.”
- dry_runboolean“Preview only: validate and return the diff without writing.”
image_writecreates or changes datadescribed as changing data
“Create a PNG sprite from text, NES-style: 'palette' maps single characters to colors and each string in 'rows' is one row of pixels ('.' and ' ' are transparent).”
Publisher declares: read-only no · destructive no · open-world no
8 inputs, 2 required
- pathstringrequired“res:// path ending in .png.”
- paletteobjectrequired“Character -> color ('#rrggbb', '#rrggbbaa', a name, or [r, g, b, a] in 0..1), e.g.”
- rowsarray“One image: rows of palette characters, all the same length (max 256x256).”
- framesarray“Several same-sized frames, laid out left to right.”
- scaleinteger“Integer upscale factor (default 1).”
- mirrorstring“Symmetric sprites: give only the left half ('x'), top half ('y') or top-left quarter ('xy'); the rest is mirrored.”
- mirror_overlapboolean“Share the middle column/row instead of repeating it (odd widths/heights).”
- dry_runboolean“Validate and report the size without writing.”
input_action_setcreates or changes datadescribed as changing data
“Add or replace an input action in the project's input map (project.godot), or remove it with remove: true.”
Publisher declares: read-only no · destructive no · open-world no
7 inputs, 1 required
- namestringrequired“Action name, e.g.”
- keysarray
- mouse_buttonsarray
- joypad_buttonsarray
- deadzonenumber“Default 0.2.”
- removeboolean“Remove the action instead.”
- dry_runboolean
project_setting_setcreates or changes datadescribed as changing data
“Change one project setting from a fixed list: the main scene, the viewport size, the window size override, the stretch mode/aspect, the project name and max_fps.”
Publisher declares: read-only no · destructive no · open-world no
3 inputs, 2 required
- keystringrequired“Setting key.”
- valuenumber or boolean or string or null or array or objectrequired“New value; converted to the setting's type.”
- dry_runboolean“Return before/after without writing.”
game_runcontrols a browser or desktopdescribed as changing data
“Launch the game from the editor and wait until the MCP runtime inside it is connected.”
Publisher declares: read-only no · destructive no · open-world no
4 inputs
- scenestring“'main' (default), 'current' (the edited scene), or a res:// scene path.”
- restartboolean“Stop a running game first instead of failing.”
- pause_on_errorboolean“Leave the game paused in the debugger on script errors (default false).”
- timeout_msinteger“How long to wait for the game to connect (default 20000).”
game_stopcontrols a browser or desktopdescribed as changing data
“Stop the running game.”
Publisher declares: read-only no · destructive no · open-world no
Takes no inputs.
game_queryreads or searches
“Read live state from the running game.”
Publisher declares: read-only yes · destructive no · open-world no
2 inputs
- nodestring“Node in the running game: relative to the running scene (e.g.”
- propertiesarray
game_inputcontrols a browser or desktopdescribed as changing data
“Play a sequence of input steps in the running game (actions, keys, mouse), in order and with real timing; hold_frames/wait_frames count physics frames for deterministic timing.”
Publisher declares: read-only no · destructive no · open-world no
3 inputs, 1 required
- stepsarrayrequired
- recordobject“Sample node properties during the sequence.”
- pause_at_endboolean“Pause the game when the sequence finishes (default false).”
game_ui_auditreads or searches
“Walk the Control nodes of the running game and report layout problems: Controls with no size, Controls outside the viewport or beyond their parent panel, text that needs more room than its rect (clip…”
Publisher declares: read-only yes · destructive no · open-world no
2 inputs
- nodestring“Node in the running game: relative to the running scene (e.g.”
- include_hiddenboolean“Also list hidden Controls (default false).”
game_in_viewreads or searches
“Check whether a Node3D is inside the camera's view (not behind it, projected inside the viewport) and where it lands on screen — the 3D judgement that otherwise needs a screenshot.”
Publisher declares: read-only yes · destructive no · open-world no
2 inputs
- nodestring“Node in the running game: relative to the running scene (e.g.”
- camerastring“Camera3D to use; default the active 3D camera.”
game_rayreads or searches
“Cast a ray between two world-space points and return the hit position, normal, distance and collider (or hit: false).”
Publisher declares: read-only yes · destructive no · open-world no
6 inputs, 2 required
- fromnumber or boolean or string or null or array or objectrequired“World start point [x, y, z].”
- tonumber or boolean or string or null or array or objectrequired“World end point [x, y, z].”
- excludestring“CollisionObject3D to ignore (e.g.”
- collision_maskinteger“Physics layers to hit (default all).”
- collide_with_areasboolean“Include Area3D (default false).”
- collide_with_bodiesboolean“Include bodies (default true).”
game_contactsreads or searches
“List a RigidBody3D's contact points, normals and the bodies they touch (contact_monitor must be on), so grounding can be read instead of inferred from a picture.”
Publisher declares: read-only yes · destructive no · open-world no
1 input, 1 required
- nodestringrequired“Node in the running game: relative to the running scene (e.g.”
game_setcreates or changes datadescribed as changing data
“Change state in the running game, e.g.”
Publisher declares: read-only no · destructive no · open-world no
2 inputs, 1 required
- nodestring“Node in the running game: relative to the running scene (e.g.”
- propertiesobjectrequired“Property path -> new value.”
game_pauseon 1 other servercontrols a browser or desktopdescribed as changing data
“Pause (paused: true) or resume the running game.”
Publisher declares: read-only no · destructive no · open-world no
1 input, 1 required
- pausedbooleanrequired
game_stepcontrols a browser or desktopdescribed as changing data
“Run exactly N physics frames, then leave the game paused (pauses it first if needed).”
Publisher declares: read-only no · destructive no · open-world no
4 inputs, 1 required
- framesintegerrequired“Physics frames to run (60 per second by default).”
- pressarray“Actions to press before the first frame and keep held.”
- releasearray“Held actions to release before the first frame.”
- taparray“Actions to press for exactly the first frame.”
game_callruns code or commandsdescribed as changing data
“Call a method on a node in the running game (e.g.”
Publisher declares: read-only no · destructive no · open-world no
4 inputs, 1 required
- nodestring“Node in the running game: relative to the running scene (e.g.”
- methodstringrequired“Method name.”
- argsarray“Positional arguments.”
- timeout_msinteger“How long to wait for the result.”
game_wait_forreads or searches
“Wait until a property of a node in the running game (or the return value of one of its methods, e.g.”
Publisher declares: read-only yes · destructive no · open-world no
9 inputs, 2 required
- nodestringrequired“Node in the running game, relative to the running scene (e.g.”
- propertystring“Property path, e.g.”
- methodstring“Check this method's return value instead of a property, e.g.”
- argsarray“Arguments for 'method'.”
- opstringrequired“Comparison; changed/increased/decreased compare with the value when waiting starts.”
- valuenumber or boolean or string or null or array or object“Expected value: a number, boolean, string, null or array (vectors as [x, y]).”
- timeout_msinteger“Default 5000.”
- tolerancenumber“Allowed difference for numbers with ==, !=, >=, <= (default 0.0001).”
- messagestring“Explains a failure in the test's words; prefixed to the error.”
logs_readreads or searches
“Read captured output: prints, errors and warnings (with file/line and stack when available).”
Publisher declares: read-only yes · destructive no · open-world no
4 inputs
- sourcestring
- sinceinteger“Cursor from a previous call's 'next'.”
- min_levelstring“Default 'info'.”
- limitinteger“Default 200.”
screenshoton 82 other serversreads or searches
“Capture an image of the running game (target='game', default) or of the editor's 2D/3D viewport (target='editor').”
Publisher declares: read-only yes · open-world no
3 inputs
- targetstring
- max_widthinteger“Downscale to at most this width (default 1280).”
- normalizestring“Game only: scale to the project's viewport size (default) or keep the window size (editor captures are unchanged).”
scenario_runon 1 other serverruns code or commandsdescribed as changing data
“Run a scripted play-test: (re)start the game, then execute steps in order — wait_for, assert, input, query, screenshot, wait_ms, assert_no_errors, set, call, repeat — stopping at the first failure.”
Publisher declares: read-only no · destructive no · open-world no
8 inputs
- pathstring“Scenario file, e.g.”
- pathsarray“Several scenario files, run in the given order.”
- stop_on_failureboolean“With a folder or paths: stop after the first scenario that does not pass.”
- scenariostring or object“Inline scenario as YAML text or an object: {name, scene?, steps: [...]}.”
- include_screenshotsboolean“Attach screenshots as images (default true; for a folder or paths, default is failure screenshots only).”
- reportstring“'summary' (default) or 'full' to also return the JSON report.”
- save_tostring“Folder in the project for evidence, e.g.”
- movieobject“Record the run with Movie Maker (one scenario; needs save_to and a game window — not with --headless in Main Run Args).”
test_runruns code or commandsdescribed as changing data
“Run the project's unit tests with GUT or GdUnit4 (whichever is installed in addons/) in a separate headless Godot process started by the editor, and return pass/fail counts, every failing test with i…”
Publisher declares: read-only no · destructive no · open-world no
5 inputs
- frameworkstring“Default 'auto': the one installed.”
- pathstring“Test folder or one test script, e.g.”
- teststring“GUT only: run the tests whose name contains this, e.g.”
- timeout_msinteger“Stop the run after this long (default 120000).”
- reportstring“'full' adds the JSON result with every test's status.”

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. “Publisher declares” lists the hints the server itself sends with the tool (MCP annotations: read-only, destructive, idempotent, open-world); they are the publisher's claims, not checked by us. 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 41 tools
Says what it returns: 63% of 41 tools
States limits, defaults or errors: 38% of 40 tools
Says when to use it: 13% of 40 tools
Items covered per tool: 2.2 of 4 on average

Counted from the listing

Parameters with a description: 92% of 126
Tools with a description: 100% of 41
Typical description length: 302 characters

The tool set

Counted from the listing

Tools: 41
Size of the list: about 13,333 tokens for an agent to load (characters ÷ 4)
Naming: 40 of 41 names use snake_case

AI reading: easy to mix up

No pair found.

The AI items cover 41 of 41 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, comparing tools within groups of 40. 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 npm package godot-mcp-loop

Our sandbox started this package 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. The command runs the publisher’s code on your machine.

Claude Desktop · claude_desktop_config.json (Settings → Developer → Edit Config)

{
  "mcpServers": {
    "godot-mcp-loop": {
      "command": "npx",
      "args": [
        "-y",
        "godot-mcp-loop@0.9.0"
      ]
    }
  }
}

Cursor · .cursor/mcp.json in a project, or ~/.cursor/mcp.json

{
  "mcpServers": {
    "godot-mcp-loop": {
      "command": "npx",
      "args": [
        "-y",
        "godot-mcp-loop@0.9.0"
      ]
    }
  }
}

VS Code · .vscode/mcp.json

{
  "servers": {
    "godot-mcp-loop": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "godot-mcp-loop@0.9.0"
      ]
    }
  }
}

VS Code (command line) · Bash or zsh terminal (macOS, Linux)

code --add-mcp '{"name":"godot-mcp-loop","type":"stdio","command":"npx","args":["-y","godot-mcp-loop@0.9.0"]}'

Claude Code

claude mcp add --transport stdio godot-mcp-loop -- npx -y godot-mcp-loop@0.9.0

Try it in the MCP Inspector · runs on your machine, opens in your browser · Node 22.19+

npx @modelcontextprotocol/inspector@2.11.0 -- npx -y godot-mcp-loop@0.9.0

This runs the publisher's code on your machine (npx). Read its README first.
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.

Can it be installed, and is it up to date?

Version pin · advisories

Listed version

Registry lists: 0.9.0
Latest stable: 0.9.2
Status: behind the latest release (1 releases, 0 days)
Withdrawn: no

Source: registry.npmjs.org · 2026-10-23. About the version the registry lists; a manual install may resolve to a different one.

Dependency advisories

Counted in the full dependency tree as resolved on 2026-10-24 (npm audit; each bar counts packages with an advisory, not advisories). Bars share one scale. The package itself has no known vulnerability (OSV.dev).

Integrity, provenance, license

Integrity: sha512-AgzF9ziaVrxP1mHPg…
Signature: signed and attested
License: MIT

Source: the package registry · 2026-10-22.

Usage

Downloads: 466 in the last month

Source: api.npmjs.org · 2026-10-22.

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 says	We found	Result	Source · date
Published package can be started	Started and answered	matches	our test · 2026-10-23
Version 0.9.0 on npm	Exists and can be installed	matches	npm · 2026-10-23
Repository github.com/AI-osho/godot-mcp-loop	Opens publicly	matches	api.github.com · 2026-10-22

Who made it?

Feature #7 · lineage

Facts about the publisher. We do not turn them into a trust score.

Namespace: io.github.AI-osho
GitHub owner: a personal account (AI-osho)
Build record: signed and attested

Repository: github.com/AI-osho/godot-mcp-loop
Stars: 0
Repository age: 0–30 days
Last push: 0–30 days ago
Archived: no
Security policy: SECURITY.md

Source: the registry entry and api.github.com · 2026-10-22; security policy read from GitHub · 2026-10-23.

Publish this server? Run these checks against it yourself before release, from your own machine: a server the command starts, or your own server at its URL after a one-time proof that you control it: npx protocolprobe-selftest.

Choosing

Record checks

Public records · not a safety rating

9 of 9 record checks met

#5,423 of 15,115 packages by monthly downloads, tied with 5 others
Not ranked by stars: 0 stars (ranked from 10)
#508 of 809 packages meeting all 9 record checks, by downloads, tied with 1 other

MetRegistry entry is active and says how to run itActive, with a package or a remote address.
MetSource repository link opensThe linked GitHub repository is public.
MetRepository is not archivedNot archived.
MetCode pushed to the repository in the 90 days before our checkLast push 0-30 days before our check.
MetRepository publishes a security policy (SECURITY.md)SECURITY.md found.
MetPackage names its licence with a standard (SPDX) identifierMIT
MetThe version the registry lists can be installed and is not withdrawnThe listed version exists; a newer one is out.
Metnpm package carries build provenance (attestation)Signed, with a build attestation naming the source and workflow.
MetNo known critical or high advisory in the package or its dependenciesNone known in the package or its dependency tree.

Read from public records only: the registry entry, npm/PyPI, GitHub and advisory databases, checked 2026-10-22. 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.AI-osho/godot-mcp-loop

Answered from the data above

Is io.github.AI-osho/godot-mcp-loop safe to install?

We do not rate servers as safe or unsafe. 9 of its 9 applicable record checks are met (facts from public records, each listed on this page). What the records show: Its npm package carries a build-provenance attestation that names its source repository and build workflow. Its source repository opens publicly. Its repository had a push in the last 90 days. A newer stable release exists than the one listed. The package itself has no known vulnerability (OSV.dev). Its full dependency tree has no known advisory. 27 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.

Has io.github.AI-osho/godot-mcp-loop been security tested?

Partly. 2 of the 12 checks that apply to it were exercised. We started the package in an isolated sandbox and read what it declares, but this test round was read-only, so its tools were not called. No security verdict is published before verification.

What can io.github.AI-osho/godot-mcp-loop do?

It lists 41 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, delete, run code or commands and control a browser or desktop. We did not call any tool, so this describes the text, not the behaviour.

Can io.github.AI-osho/godot-mcp-loop change or delete data?

27 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.

Does io.github.AI-osho/godot-mcp-loop publish a security policy?

Yes: its repository has a public security policy (github.com/ai-osho/godot-mcp-loop/blob/HEAD/SECURITY.md). That is the publisher's statement, not permission for us to test the server, and we call none of its tools.

Is the listed version current?

No. The registry lists 0.9.0; the latest stable release on npm is 0.9.2.

Where is the source code of io.github.AI-osho/godot-mcp-loop?

In github.com/AI-osho/godot-mcp-loop, which opens publicly.

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

io.github.callstack/agent-deviceagent-devicealso has tools that controls a browser or desktop, creates or changes data, deletes, runs code or commands, reads or searchescompare with this one
io.github.A9T9/uivision-mcpUi.Vision MCPalso has tools that controls a browser or desktop, creates or changes data, deletes, runs code or commands, reads or searchescompare with this one
io.github.Buoy-gg/mcpalso has tools that controls a browser or desktop, creates or changes data, deletes, runs code or commands, reads or searchescompare with this one
io.github.tugcantopaloglu/godot-mcpGodot MCPalso has tools that controls a browser or desktop, creates or changes data, deletes, runs code or commands, reads or searchescompare with this one
io.github.jumodada/drissionpage-mcpDrissionPage MCPalso has tools that controls a browser or desktop, creates or changes data, deletes, runs code or commands, reads or searchescompare with this one
io.github.tomyud1/godot-mcpalso has tools that controls a browser or desktop, creates or changes data, deletes, runs code or commands, reads or searchescompare with this one

Active servers whose topic is also “developer-tools” 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

Not probed (read-only run)

We started the package in an isolated sandbox and read what it declares, but this test round was read-only, so its tools were not called. 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

Inventory: exercised
Hidden instructions: exercised
Real execution: not run · our policy
Secret leak: not run · nothing to check it against
Internal addresses: not run · our policy
Unconfirmed changes: not run · our policy
Bad input: not run · our policy
Model requests: not run · nothing to check it against
Sensitive questions: not run · nothing to check it against
Folder boundary: not run · our policy
Log leaks: not run · nothing to check it against
Hidden content: not run · nothing to check it against
Fake assistant turns: not applicable
Token passthrough: not applicable
Token audience: not applicable
Sign-in redirect: not applicable
Consent handling: not applicable
Sign-in metadata: not applicable

2 exercised10 not run (reason given)6 not applicable

Each check ends in exactly one state: exercised, not run (with the reason), or not applicable (with the reason). 2 of the 12 checks that apply to it were exercised. We do not publish security-check outcomes for named servers.

Exercised · 2

1Inventory
tool-listReads the declared tools, resources and prompts.exercised
2Hidden instructions
description-poisoningLooks for hidden instructions in tool descriptions.exercised

Not run, with the reason · 10

3Real execution
real-executionCalls a tool and checks what really happens.This check calls the package's tools. This test round was read-only, so no tool was called; tools can act on outside services with the publisher's or a user's account.not run · our policy
4Secret leak
canary-leakPlants 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
ssrfChecks whether a tool can be steered to internal addresses.This check calls the package's tools. This test round was read-only, so no tool was called; tools can act on outside services with the publisher's or a user's account.not run · our policy
6Unconfirmed changes
write-without-confirmationChecks whether tools that change data act without asking.This check calls the package's tools. This test round was read-only, so no tool was called; tools can act on outside services with the publisher's or a user's account.not run · our policy
7Bad input
error-handlingSends bad input and watches how the server answers.This check calls the package's tools. This test round was read-only, so no tool was called; tools can act on outside services with the publisher's or a user's account.not run · our policy
8Model requests
samplingChecks 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-dataChecks 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-boundaryChecks whether the server reaches outside the folders it was given.This check calls the package's tools. This test round was read-only, so no tool was called; tools can act on outside services with the publisher's or a user's account.not run · our policy
11Log leaks
logging-side-channelChecks 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-hidingChecks 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

Does not apply to this server · 6

13Fake assistant turns
fake-assistant-turnChecks prompts that pose as the assistant's own words.The server exposes no prompts.not applicable
14Token passthrough
token-passthroughChecks whether the server forwards a user's token to other services.The server runs locally over standard input/output, so there is no sign-in flow to check.not applicable
15Token audience
token-audience-validationChecks whether tokens meant for another service are accepted.The server runs locally over standard input/output, so there is no sign-in flow to check.not applicable
16Sign-in redirect
open-redirectChecks the sign-in redirect for abuse.The server runs locally over standard input/output, so there is no sign-in flow to check.not applicable
17Consent handling
confused-deputyChecks consent handling when one service acts for another.The server runs locally over standard input/output, so there is no sign-in flow to check.not applicable
18Sign-in metadata
oauth-url-schemeChecks the published sign-in metadata for unsafe URLs.The server runs locally over standard input/output, so there is no sign-in flow to check.not applicable

Source: our own test in an isolated sandbox, 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.

0 msStarted the published package in an isolated sandbox (read-only mode)
6,041 msConnected after 0 redirects.
Read the inventory: 41 tools, 0 resources, 0 prompts.
6,996 msFinished: 2 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

developer-tools

AI-classified · 2026-10-23

Pricing modelAI-classified

no value

The website listed in the registry is a code-hosting, package or marketplace page, not the product's own site.

Programming language

TypeScript

api.github.com · 2026-10-23

Hosting type

local package

registry · 2026-10-23

MCP capability

tools

our test · 2026-10-23

Transport

standard input/output

registry · 2026-10-23

Required credentials

none declared

registry · no declaration is not a guarantee

Package registry

npm

registry · 2026-10-23

Freshness

0–30 days

registry updatedAt · 2026-10-23

Lifecycle status

active

registry · 2026-10-23

License class

permissive

package registry · 2026-10-22

Integrity hash

declared (sri)

package registry · 2026-10-22

Signature / provenance

signed and attested

package registry · 2026-10-22

Dependency advisories

none known

npm audit · 2026-10-24

Popularity

466 downloads a month

package registry · 2026-10-22

Publisher signals

owner: a personal account · repository age: 0–30 days · stars: 0–9 · build record: signed and attested

api.github.com · 2026-10-22

Maintenance

active

api.github.com · 2026-10-22

Environment

your machine

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.AI-osho/godot-mcp-loop: MCP server record.” Data checked 2026-10-23. https://protocolprobe.com/mcp/servers/io.github.AI-osho/godot-mcp-loop

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](https://protocolprobe.com/api/v1/badge/io.github.AI-osho/godot-mcp-loop)](https://protocolprobe.com/mcp/servers/io.github.AI-osho/godot-mcp-loop)

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