Control the Unity and Godot editors from AI clients: scenes, scripts, physics, materials.
The Glade MCP server enables AI clients to control Unity and Godot editors, handling scenes, scripts, physics, and materials. It exposes a Model Context Protocol workflow to synchronize model context with editor state, facilitating automated scene management and tool integration.
🛠️ Key Features
Support for Unity and Godot editors
Manage scenes, scripts, physics, and materials
Model Context Protocol (MCP) integration for AI-driven context synchronization
Lightweight, modular server with extensible toolCount and readmeExcerpt
🚀 Use Cases
AI-assisted scene construction and manipulation
Automated script and asset updates from AI clients
Editor state synchronization for model-context-driven workflows
Integration with IDEs and development tools (VS Code, etc.)
⚡ Developer Benefits
Clear MCP-based interface for editor control
Easily discoverable via topics like mcp, model-context-protocol, and ai-tools
Grounded data model aligning with Unity and Godot workflows
⚠️ Limitations
Data fields are limited to provided name, description, topics, toolCount, and readmeExcerpt
Behavior details depend on actual editor integrations and MCP implementation specifics
The Unity bridge starts automatically on localhost:8765.
Godot (4.3+)
Download com.gladekit.mcp-bridge.zip from the latest Godot bridge release. (Grab the zip asset under Assets - not "Source code".)
Extract it and you get a single com.gladekit.mcp-bridge/ folder. Move it into your project's addons/ directory, so the final path is <your-godot-project>/addons/com.gladekit.mcp-bridge/plugin.cfg.
The Godot bridge starts automatically on localhost:8766. You should see a confirmation line in the editor Output panel:
code
[GladeKit MCP Bridge] listening on ws://127.0.0.1:8766 (v0.7.6, 105 tools registered, thread-polled at 200Hz)
Supported: Godot 4.3+ GDScript projects, Forward+ and Compatibility renderers, 2D and 3D. Not yet supported: Godot Mono / C# projects, web export targets, headless server builds. The bridge is editor-only; it never runs in exported games.
Engine auto-detection: the MCP server probes both ports on startup and exposes the matching tool set. Running both editors at once? Set GLADEKIT_MCP_FORCE_ENGINE=unity or =godot to pin a specific engine.
In Windsurf, open Windsurf Settings → MCP Servers → Open MCP Registry, then click the settings (gear) icon to open mcp_config.json. Add the snippet below (or edit ~/.codeium/windsurf/mcp_config.json directly):
Unity's built-in AI Assistant can connect to GladeKit via MCP. This gives you GladeKit's 260+ tools directly inside the Unity Editor - no external AI client needed.
Requires: Unity 6000.3+ with AI Gateway package (com.unity.ai.assistant@2.x)
In Unity, go to Edit > Project Settings > AI > MCP Servers
Under Path Configuration, paste your terminal's PATH into User Path so Unity can find uvx. To get your PATH:
Mac/Linux:echo $PATH
Windows:echo %PATH%
Click Refresh Config File and Reload Servers
Verify the server shows StartedSuccessfully in the Servers section
Tip: If uvx isn't found, add the directory containing it to the path field in the config (e.g., "/opt/homebrew/bin" on Mac or "C:\\Users\\<you>\\.local\\bin" on Windows). Alternatively, use pip install gladekit-mcp and set "command": "python" with "args": ["-m", "gladekit_mcp"].
Troubleshooting: If the server shows FailedToStart, click Inspect for error details. The most common cause is PATH - Unity's PATH differs from your terminal's PATH. See the Troubleshooting section below.
Paid tier (GLADEKIT_API_KEY): To enable RAG knowledge base and cross-session memory on any client, add the key to the env field of your config. See Cloud intelligence below.
All 260+ tools are dispatchable. Claude Code sees ~80 curated core tools by default (Claude Code has a practical 128-tool limit; Unity AI Gateway has a cloud token budget). Use get_relevant_tools to discover extended tools for specialized work (blend trees, NavMesh, IK, Cinemachine, etc.).
7 MCP resources: Bridge health, project context, scene hierarchy, project scripts, current selection, GLADE.md, and session memory.
GLADE.md
Create a GLADE.md file in your Unity project root. The MCP server reads it and injects it into every request. Works as a permanent context layer: your game's design intent, conventions, and constraints are always in scope.
markdown
# My Game
Genre: 3D platformer
Player: CharacterController, double jump enabled
Art style: pixel art, 16x16 sprites
Naming: PascalCase for scripts, snake_case for folders
Script semantic search
Set OPENAI_API_KEY in your MCP config's env field and the server ranks project scripts by semantic similarity to your query. Ask "how does the enemy spawn?" and the right script surfaces, even if it's not named EnemySpawner.
Everything needed ships with the package; no install flags or extras required. Get a key at platform.openai.com/api-keys (pay-as-you-go, pennies per search via text-embedding-3-small).
Without the key, search_project_scripts still returns scripts - just unranked. Keys are never sent anywhere except OpenAI's embedding endpoint.
Skill calibration
The server tracks vocabulary across your messages and detects whether you're a Unity beginner or expert. Beginners get plain-language explanations and encouraging framing. Experts get terse, technical responses. Calibration persists to .gladekit/skill_level.json in your project.
Asset pipeline (free CC0 imports)
Three tools for finding and importing free, commercially-usable assets directly from your AI client. All assets are CC0 (public domain, no attribution required). v1 ships Kenney.nl packs; additional providers (Freesound, Quaternius, AI generation) are on the roadmap.
Tool
Purpose
find_asset
Search ranked candidates by description, asset type, style, and license. Read-only, no Unity dispatch.
import_asset
Download, extract, place under Assets/, configure import settings for the asset type, and write a .gladekit-asset.json sidecar with license metadata. Requires explicit licenseAcknowledged: true.
list_imported_assets
Walk the project's sidecars and surface a license audit (license counts, attribution-required count). Useful before a commercial release.
Example workflow (Cursor, Claude Code, Windsurf use the same pattern):
You: I'm prototyping a 2D platformer and need placeholder character + tile art. Find me something free.
The AI calls find_asset:
json
{"description":"platformer character and tiles","asset_type":"sprite_2d","max_results":5}
Result (truncated):
json
{"success":true,"candidates":[{"id":"kenney/platformer-pack-redux","name":"Platformer Pack Redux","description":"360+ side-scrolling platformer sprites: characters, enemies, tiles, items, hazards.","license":"CC0-1.0","license_summary":"Public domain. No attribution required for any use, including commercial.","official_page":"https://kenney.nl/assets/platformer-pack-redux","approx_assets":360,"score":0.92},{"id":"kenney/pixel-platformer","score":0.71, ... },{"id":"kenney/tiny-town","score":0.45, ... }],"count":3}
You: Let's go with Platformer Pack Redux. Import it to Assets/Sprites/Platformer/. I accept the CC0 license.
The MCP server resolves the download URL locally (catalog is bundled with the server, no cloud dependency), passes it to the Unity bridge, which downloads, extracts, configures TextureImporter for each sprite (Texture Type = Sprite, Filter Mode = Point, Uncompressed) and writes the license sidecar. Result:
json
{"success":true,"message":"Imported 360 file(s) from kenney/platformer-pack-redux to Assets/Sprites/Platformer/","downloadedBytes":1842340,"importedFileCount":360,"configuredImportSettings":354,"license":"CC0-1.0","sidecarPath":"Assets/Sprites/Platformer/.gladekit-asset.json"}
The sprites appear in the Unity Project window, ready to drop into a scene.
You: Before I ship, audit my imported assets. Anything that needs attribution?
CC0 needs no attribution; the audit report is empty for required attributions. If you imported a CC-BY asset later, it would surface here so you remember to credit it.
Security and license discipline:
The LLM never sees download URLs. URL resolution happens cloud/MCP-side; the bridge tool refuses if the resolved fields are missing or LLM-injected.
licenseAcknowledged: true is required on every import_asset call. The bridge refuses without it. Do not set it without explicit user confirmation.
The bridge validates _resolvedUrl's host against a per-provider allowlist (AssetPipelineGuard.IsResolvedUrlHostAllowed) before downloading. Even a client bypassing both the cloud and MCP preprocessors cannot smuggle in an arbitrary download URL; unknown hosts fail closed. HTTPS only.
Every imported asset bundle gets a .gladekit-asset.json sidecar recording the candidate id, provider, license, attribution string, source URL, and timestamp. list_imported_assets reads these for the audit report.
Asset Pipeline tools are gated by AssetPipelineGuard on the bridge side. A misconfigured client cannot bypass it.
Disabling the pipeline (for studio / curated-asset workflows):
Set GLADEKIT_MCP_DISABLE_ASSET_PIPELINE=1 in the MCP server's environment to suppress the three tools entirely. They will not appear in the tool list and dispatch will refuse with a clear error. This is the recommended setting for projects that already have a managed asset workflow (Perforce-tracked libraries, internal asset stores) where AI-driven external downloads aren't appropriate.
The Unity bridge enforces the same gate via EditorPrefs (GladeAI.AssetPipelineEnabled, default true). Toggle it via POST http://localhost:8765/api/settings { "assetPipelineEnabled": false }.
Cloud intelligence
Set GLADEKIT_API_KEY in your MCP config's env field to unlock cloud-powered features:
RAG knowledge base - get_relevant_tools queries a curated Unity knowledge base (API corrections, error patterns) and injects results alongside tool recommendations.
Cross-session persistent memory - facts stored with remember_for_session persist across sessions and are re-injected into the system prompt.
Convention extraction - coding patterns (naming, architecture, preferences) are distilled from your accumulated memories and surfaced in future sessions.
All cloud features degrade gracefully: if the key is missing or the cloud is unreachable, everything works normally.
GladeKit MCP supports two transports. stdio is the default and works with all MCP clients - every config above uses stdio.
Streamable HTTP is for clients that prefer URL-based config (Claude Desktop URL mode, custom clients). Launch the server manually, then point your client at the URL:
Binds loopback-only (127.0.0.1). Use --host 0.0.0.0 to expose on LAN - opt-in only.
DNS-rebinding protection enabled for loopback binds: requests with a Host header other than 127.0.0.1:<port> or localhost:<port> are rejected with 421 Misdirected Request.
Non-loopback binds disable rebinding protection (you've taken responsibility for the network) and print a warning on startup.
Set to 1 to suppress find_asset / import_asset / list_imported_assets (curated-asset workflows)
GLADEKIT_MCP_SUPPRESS_BRIDGE_WARNING
No
Set to 1 to silence the stderr warning when the Unity bridge is older than the recommended version
Troubleshooting
Bridge not connecting
Open Unity and wait for it to finish importing assets - the bridge starts automatically
Check Window > GladeKit MCP in Unity - the Bridge and AI Client indicators show connection status
Verify nothing else is using port 8765: lsof -i :8765 (Mac/Linux) or netstat -ano | findstr 8765 (Windows)
AI client can't find uvx
Install uv: curl -LsSf https://astral.sh/uv/install.sh | sh (Mac/Linux) or pip install uv
Or use pip install gladekit-mcp and change the config command from "uvx" to "python" with args ["-m", "gladekit_mcp"]
Tools not appearing in Claude Code
Claude Code has a practical ~128-tool limit. GladeKit shows ~80 curated core tools by default - this is intentional. All 260+ are dispatchable: use get_relevant_tools to find extended tools by task description.
GLADE.md not being picked up
The file must be named exactly GLADE.md (case-sensitive on Mac/Linux) and placed in the Unity project root (same directory as Assets/, Packages/, ProjectSettings/)
Stderr warning: Unity bridge X.Y.Z is older than recommended
Unity caches UPM git packages and never refetches, so an ?path=unity-bridge install drifts behind main over time. Update via Unity → Window > Package Manager > GladeKit MCP Bridge > Update, or pin the manifest entry to a specific tag so future updates are explicit:
The same warning also appears as a one-shot prefix on the next tool response so you see it in chat. To silence both: add "GLADEKIT_MCP_SUPPRESS_BRIDGE_WARNING": "1" to the env of your MCP client config.
Unity AI Gateway - server shows FailedToStart
Click Inspect in the Servers section for the error message
Most common cause: Unity can't find uvx. Under Path Configuration, paste your terminal's full PATH into User Path, then click Refresh Config File and Reload Servers
On Windows: echo %PATH% in Command Prompt. On Mac/Linux: echo $PATH
Alternative: use pip install gladekit-mcp and set the command to "python" with args ["-m", "gladekit_mcp"] - avoids the uvx PATH dependency
Validate outside Unity first: run uvx gladekit-mcp in a terminal (you should see the gladekit-mcp v... banner on stderr)
Add Register(new MyTool()); to the matching category registrar. Registration is explicit — an unregistered tool compiles fine but returns "Tool was blocked from executing or null." when dispatched.