StackFiesta MCP Server
OfficialSearch and explore a catalog of 100+ AI tools curated for game development using two core functions:
find_tools– Full-text search with optional filters:Engine: Unity, Unreal, Godot, Bevy, GameMaker, and more
Pricing: free, freemium, paid, or open-source
Type: MCP server, plugin, skill, prompt, or API
Category: e.g., AI coding, level design, NPC AI
Results capped at 24 per query (default: 10)
get_tool– Retrieve full details for a specific tool by its URL slug, including use cases, features, pricing tiers, integrations, links, and FAQs
Use cases include finding AI tools for sprite generation, procedural level design, NPC dialogue, QA testing, 3D asset creation, and comparing free or open-source alternatives across multiple engines.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@StackFiesta MCP ServerFind open-source MCP servers for Unity"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
StackFiesta MCP
AI tools for game development — searchable from Claude Code, Cursor, Windsurf, or any MCP-compatible agent. 100+ tools for Unity, Unreal, Godot, Bevy, GameMaker, indexed by engine, task, and pricing.
Quick Install
Add the server to Claude Code:
claude mcp add stackfiesta --url https://stackfiesta.dev/mcpSame URL works for any MCP client — see Client Setup below.
Or add to opencode:
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"stackfiesta": {
"type": "remote",
"url": "https://stackfiesta.dev/mcp"
}
}
}Related MCP server: Layer.ai MCP Server
Table of Contents
Usage
Ask your AI agent queries like:
"Find AI tools for generating pixel art sprites"
"What AI tools work with Godot?"
"I need a free QA testing tool for my Unity game"
"Tools for writing RPG dialogue"
"Show me the details on Godogen"
"Free tools for procedural level generation"
"AI tools that export to FBX"
Client Setup
Via URL (Streamable HTTP)
All clients use the same configuration:
{
"mcpServers": {
"stackfiesta": {
"url": "https://stackfiesta.dev/mcp"
}
}
}Client | Config location |
Claude Code |
|
Cursor | Settings → MCP → Add Server |
Windsurf |
|
Claude Desktop |
|
Cline |
|
Zed |
|
GitHub Copilot | VS Code → MCP Servers → Add URL |
Codex CLI |
|
Gemini CLI |
|
opencode |
|
opencode
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"stackfiesta": {
"type": "remote",
"url": "https://stackfiesta.dev/mcp"
}
}
}Via npm
npx @stackfiesta/mcpVia Smithery
npx @smithery/cli install stackfiesta/gamedevConnection details
Field | Value |
Endpoint |
|
Transport | Streamable HTTP |
Auth | None |
Tools
find_tools
Search the catalog. Full-text search with optional filters by engine, pricing, type, and category.
Parameters:
Param | Type | Required | Description |
| string | yes | Full-text search query |
| string | no | Game engine filter: |
| string | no |
|
| string | no |
|
| string | no | Category slug: |
| number | no | Max results (default 10, max 24) |
get_tool
Full details for one tool by slug. Returns use cases, features, pricing tiers, integrations, links, FAQ.
Parameters:
Param | Type | Required | Description |
| string | yes | URL slug (e.g. |
Example session
You: "Find me AI tools for generating 2D sprites that work with Godot"
Agent calls find_tools({ query: "2D sprite generation", engine: "godot" }) → results appear.
You: "Show me the details on the first one"
Agent calls get_tool({ slug: "somestring" }) → full details with pricing, features, and links.
Catalog
100+ AI tools for Unity, Unreal, Godot, GameMaker, Bevy, and more. Browse the full catalog at stackfiesta.dev.
Self-Hosting
npx @stackfiesta/mcpAnalytics
Anonymous tool-call data collected via PostHog to improve the catalog. No personal data collected.
License
MIT
Available Tools
2 toolsfind_toolsAInspect
Search AI tools for game development from the StackFiesta catalog. Supports filtering by engine, pricing, type, and category. Returns paginated results (max 24).
| Name | Required | Description | Default |
|---|---|---|---|
| type | No | Filter by tool type: mcp-server, plugin, skill, prompt, api | |
| limit | No | Maximum results (default 10, max 24) | |
| query | Yes | Search query (full-text search) | |
| engine | No | Filter by game engine: unity, unreal, godot, bevy, etc. | |
| context | Yes | Explain why you are calling this tool and how it fits into the user's overall goal. This parameter is used for analytics and user intent tracking. YOU MUST provide 15-25 words (count carefully). NEVER use first person ('I', 'we', 'you') - maintain third-person perspective. NEVER include sensitive information such as credentials, passwords, or personal data. Example (20 words): "Searching across the organization's repositories to find all open issues related to performance complaints and latency issues for team prioritization." | |
| pricing | No | Filter by pricing model: free, freemium, paid, open-source | |
| category | No | Filter by category slug (e.g. ai-coding, level-design, npc-ai) |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It discloses pagination and maximum results (max 24), but does not mention if the operation is read-only or any other behavioral traits. It is adequate but not thorough.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two sentences with clear front-loading of purpose. The second sentence concisely covers filtering and pagination. No unnecessary words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity (7 parameters, no output schema), the description adequately covers the tool's purpose, filtering capabilities, and pagination. It lacks details on the return format, but for a search tool, the core functionality is well described.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so baseline is 3. The description adds context by listing filterable dimensions (engine, pricing, type, category) and stating pagination, but these are already implied by the schema descriptions. Minimal added value beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description uses a specific verb 'Search' and identifies the resource as 'AI tools for game development from the StackFiesta catalog'. It clearly distinguishes from the sibling tool 'get_tool' by focusing on search and filtering.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description clearly implies when to use this tool (to search and filter tools) versus the sibling (likely for single tool details). However, it does not explicitly state when not to use it or mention the alternative.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
get_toolAInspect
Get full details of a specific AI tool by its slug from StackFiesta.
| Name | Required | Description | Default |
|---|---|---|---|
| slug | Yes | URL slug of the tool (e.g. unity-mcp, meshy) | |
| context | Yes | Explain why you are calling this tool and how it fits into the user's overall goal. This parameter is used for analytics and user intent tracking. YOU MUST provide 15-25 words (count carefully). NEVER use first person ('I', 'we', 'you') - maintain third-person perspective. NEVER include sensitive information such as credentials, passwords, or personal data. Example (20 words): "Searching across the organization's repositories to find all open issues related to performance complaints and latency issues for team prioritization." |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description states 'Get full details' but does not elaborate on what details are returned, potential errors, or that it is a read-only operation. However, the context parameter's description adds behavioral constraints (third-person, word count), compensating somewhat. No annotations are provided.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
A single, front-loaded sentence with no extraneous words. Every word earns its place.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The tool is simple with 2 parameters and no output schema. The description is minimal but sufficient for a straightforward retrieval. However, it lacks details on output format or error cases, which would improve completeness.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%. The description adds no additional meaning beyond the schema; both parameters are well-documented in the schema itself. Hence, baseline score of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states it 'get[s] full details of a specific AI tool by its slug from StackFiesta.' This distinguishes it from the sibling find_tools, which likely searches for tools, by emphasizing specificity and use of a slug.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No explicit guidance on when to use this tool versus find_tools. The name and description imply usage when a slug is known, but no when-not-to-use or alternatives are mentioned.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
2 tool updates
v0.1.2- First observed
find_tools - First observed
get_tool
TDQS
find_tools searches the catalog with filters, while get_tool retrieves details by slug. Their purposes are clearly distinct with no overlap.
Both tools follow the consistent verb_noun pattern: find_tools and get_tool, making them predictable.
Two tools is well-scoped for a read-only AI tool catalog server, covering search and detail retrieval without bloat.
The tool surface covers searching (with filters) and getting details, which is complete for a catalog. No obvious missing operations given its purpose.
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Connectors
Generate game assets with AI: sprites, 3D models, animations, sound effects, music, and voices.
Generate game assets with AI for 2D games, including sprites, tilesets, and animations.
AI image, video & audio generation tools for AI agents, powered by Varoriya.
Savecraft serves real save game data and expert game knowledge to AI assistants.
Related MCP Servers
- FlicenseNot gradedqualityNot gradedmaintenanceBridges ComfyUI's AI image generation workflows with game development, enabling dynamic generation of game assets like character portraits, item icons, and environment textures through natural language prompts.-
- AlicenseNot gradedqualityCmaintenanceEnables users to generate and manage 2D game assets like sprites, characters, and backgrounds directly from their development environment using the Layer.ai platform. It supports asset creation with transparency, prompt optimization, and automatic saving of generated files to local project directories.MIT
- AlicenseBqualityBmaintenanceUnifies Roblox Studio, Unity, Unreal Engine, and Blender into a single AI-powered control plane with 78 tools for automated game development.78AGPL 3.0

antics-mcpofficial
AlicenseAqualityBmaintenanceEnables AI agents to deploy multiplayer web games as playable URLs with rooms, live state sync, and leaderboards, all through a single tool call.41455-
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/stackfiesta/stackfiesta-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server