ADA Turbo turns your IDE into an agency operating system via MCP, providing structured AI workflow commands, role playbooks, and live office visualizations.
Trigger agency workflows with commands like /copy tagline, /strateji yaratici-brief, /cfo runway, or free-form tasks via ada_workflow.
Retrieve the full list of ADA agency commands organized by department via ada_komutlar.
Get core behavioral rules and output formats via ada_kurallar for consistent AI responses.
Connect to Claude Desktop, Cursor, Antigravity, Claude Code, or Windsurf through MCP.
Access 26 specialized AI roles across strategy, creative, marketing, client operations, and analytics/tech.
Launch the Pixel Office web visualizer with real-time character animations, SSE event streaming, and offline/live LLM testing for workflows.
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., "@ADA Turbo Generate a creative brief for a new ad campaign"
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.
🇺🇸 English Documentation | 🇹🇷 Türkçe Dokümantasyon
🏢 Pixel Office Visualizer | 🧪 CRT Workflow Playground |
|
|
Related MCP server: Cognitive Core
uvx (Recommended)You can run ADA Turbo instantly without cloning or managing virtual environments:
uvx ada-turbo-ai-mcp(Or launch just the web visualizer: uvx ada-turbo-ai-mcp --web)
# 1. Clone the repository
git clone https://github.com/adacreativeco/ada-turbo-ai-mcp.git
cd ada-turbo-ai-mcp
# 2. Install dependencies
pip install -r requirements.txt
# 3. Start Unified Dual-Mode (MCP stdio + Web Visualizer)
python server.pyOpen http://localhost:8000 (auto-fallback to 8001, 8002... if occupied) in your browser.
Unified Dual-Mode Architecture:
MCP Mode (Default): Runs as an MCP stdio server. Concurrently starts the Pixel Office Web Server in the background. Seamlessly connects to Antigravity, Claude Desktop, Cursor, Claude Code, and Windsurf.
Pixel Office Web Mode: Starts a local, highly-optimized retro CRT-effect web workspace (python server.py --web).
⚡ Real-Time Server-Sent Events (SSE):
Zero-latency event streaming (/api/events). When an agent is triggered in your IDE, the corresponding character visually walks to their desk in real-time!
🧠 Direct Live LLM Engine:
Multi-provider AI execution directly in the browser via /api/llm-generate:
🟢 Built-in Template Engine (Offline): Instant access to professional agency workflow templates without API keys.
✨ Google Gemini: gemini-2.0-flash, gemini-1.5-flash, gemini-1.5-pro
🧠 OpenAI: gpt-4o-mini, gpt-4o, o3-mini
⚡ Anthropic Claude: claude-3-5-sonnet-20241022, claude-3-5-haiku-20241022
Safe local credential storage in browser localStorage.
Developer Tools (CRT Console Modals):
Playground (Workflow & Live AI Tester): Select commands and test tasks with offline templates or live LLM models with typewriter output.
AI Model Configurator: Switch providers, enter API keys safely, and select model presets.
Setup Wizard: Dynamically outputs ready-to-copy configuration blocks for Cursor, Antigravity, Claude Desktop, and Claude Code.
Pixel Characters & Animations: 26 unique agency characters with idle (breathing, blinking) and walking cycles across custom office floors.
Full Bilingual Support (TR / EN): One-click toggle for all UI elements, status badges, modals, agent prompts, and knowledge references.
Add to your mcp_config.json:
{
"mcpServers": {
"ada-turbo": {
"command": "uvx",
"args": ["ada-turbo-ai-mcp"]
}
}
}Add to ~/.cursor/mcp.json (global) or .cursor/mcp.json (project-level):
{
"mcpServers": {
"ada-turbo": {
"command": "uvx",
"args": ["ada-turbo-ai-mcp"]
}
}
}Add to your claude_desktop_config.json:
{
"mcpServers": {
"ada-turbo": {
"command": "uvx",
"args": ["ada-turbo-ai-mcp"]
}
}
}claude mcp add ada-turbo -- uvx ada-turbo-ai-mcp(Note: If using local clone, replace "command": "uvx" and "args": ["ada-turbo-ai-mcp"] with "command": "python" and "args": ["/ABSOLUTE/PATH/server.py"])
ADA Turbo organizes 26 specialized agents across 5 key departments:
Strategy & Brand: Brand Director, Brand Strategist, Consumer Insight Lead, Naming Specialist, Creative Technologist.
Creative & Design: Creative Director, Senior Copywriter, Art Director, UX/UI Lead, 3D/Motion Designer.
Marketing & Growth: Growth Marketing Director, Performance Marketing Specialist, SEO/Content Strategist, Social Media Lead, CRM & Retention Manager.
Client & Operations: Account Director, Senior Account Manager, Agency Producer, Operations Director, Traffic Manager.
Analytics & Tech: Chief Data Officer, Marketing Data Analyst, Full-Stack Lead, AI Solutions Architect, QA & Delivery Lead.
ada-turbo-mcp/
├── server.py ← Unified dual-mode entry point (MCP + Web)
├── index.html ← Retro CRT Pixel Office single-page UI
├── pyproject.toml ← Package metadata & entry points
├── smithery.yaml ← Smithery.ai 1-click install configuration
├── requirements.txt ← Project dependencies
├── references/ ← Bilingual domain knowledge bases (.md)
│ ├── strategy-brand.md / strateji-marka.md
│ ├── creative-team.md / yaratici-ekip.md
│ ├── marketing-growth.md / pazarlama-buyume.md
│ ├── client-operations.md / musteri-operasyon.md
│ └── analytics-product-tech.md / analitik-urun-teknik.md
├── karakterler/ ← Pixel character graphics and generator scripts
├── animasyonlar/ ← Character walk/idle spritesheets & GIF previews
├── office-bina/ & office-zon/ ← Procedural pixel art building generation assets
├── skill/ ← Pre-packaged .skill distribution bundle
└── src/ ← Python modules
├── mcp_server.py ← FastMCP server definitions & tool registrations
├── web_server.py ← Multi-threaded HTTP server, SSE broadcaster & LLM proxy
└── workflow_manager.py ← Command routing, action listener dispatch & templatesDistributed under the PolyForm Noncommercial License 1.0.0. See LICENSE for details.
Developed with ❤️ by ADA Creative Co.
Tüm ADA ajans komutlarını ve hangi alana ait olduklarını listeler.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden. It implies read-only behavior by stating 'lists', but does not disclose potential performance issues, pagination, or whether results are cached. For a simple listing tool, this is adequate but not exemplary.
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 a single sentence with no redundant words. It is front-loaded and efficiently conveys the core functionality.
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 tool has no parameters and an output schema exists (though not shown), the description sufficiently explains that the output lists commands and their areas. It lacks detail on output format or edge cases, but for a simple listing it is reasonably complete.
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?
The input schema has zero parameters, so the description does not need to add parameter-level information. The baseline score of 4 applies as no parameter documentation is required.
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 the tool lists all ADA agency commands and their associated area using a specific verb 'listeler' (lists) and resource 'ADA ajans komutları'. It effectively distinguishes from sibling tools like 'ada_kurallar' (rules) and 'ada_workflow' (workflow) by focusing on commands.
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 guidance is provided on when to use this tool versus alternatives. The description does not mention context, prerequisites, or exclusion criteria, leaving the agent to infer usage.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
ADA Turbo'nun temel davranış kurallarını döndürür (her görevde geçerli).
| Name | Required | Description | Default |
|---|---|---|---|
| lang | No | tr |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the burden. It states the tool 'returns' rules, indicating a read-only operation. However, it does not disclose any other behavioral traits like permissions or response format; the output schema may cover the latter.
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 a single, front-loaded sentence with no wasted words. However, it sacrifices completeness for brevity, missing parameter details.
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 tool's simplicity and the presence of an output schema, the description should at least mention the optional language parameter. Its omission makes the description incomplete for the agent to use correctly.
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?
Despite 0% schema description coverage, the description does not mention the 'lang' parameter at all. The agent cannot infer the parameter's purpose from the description, leaving a significant gap.
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 the tool returns the basic behavior rules of ADA Turbo. It uses a specific verb (döndürür) and resource (temel davranış kuralları), distinguishing it from sibling tools (ada_komutlar for commands, ada_workflow for workflows).
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 alternatives. The description only says 'valid for every task', which implies always applicable but lacks a clear use case or exclusion criteria.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
ADA ajans workflow'unu çalıştırmak için gereken talimat ve formatı döndürür.
Bir /komut (ör. '/copy tagline', '/strateji yaratici-brief', '/cfo runway') veya serbest görev tanımı ver. Bu araç, o workflow'a ait davranış kurallarını ve referans formatını döndürür; sen de bu formata göre çıktıyı üretirsin.
Args: komut: ADA komutu, ör. '/copy tagline' veya '/analitik aylik-rapor'. gorev: (Opsiyonel) Müşteri/proje bağlamı veya serbest görev tanımı. lang: (Opsiyonel) Çıktı dili ('tr' veya 'en'). Varsayılan 'tr'.
| Name | Required | Description | Default |
|---|---|---|---|
| lang | No | tr | |
| gorev | No | ||
| komut | Yes |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, and the description only states that the tool returns instructions. It does not disclose any behavioral traits such as read-only nature, authentication requirements, side effects, or rate limits. For a tool with no annotations, this is insufficient.
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 concise, with the main purpose upfront followed by usage instructions and parameter list. Every sentence serves a purpose, and the structure is logical. Minor redundancy could be trimmed, but overall efficient.
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 that an output schema exists (true), the tool description does not need to detail return values. It adequately explains the tool's input and behavior for a tool that returns workflow instructions. The mention that the agent must produce output according to the returned format provides necessary context.
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?
The schema has 0% description coverage, so the tool description must compensate. It provides basic meanings for each parameter (e.g., 'komut' is an ADA command, with examples; 'gorev' is optional context; 'lang' is language). While helpful, it lacks details like accepted formats or constraints beyond examples.
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 that the tool returns instructions and format for running an ADA workflow command. It uses a specific verb ('döndürür') and resource ('workflow talimat ve formatı'). However, it does not explicitly differentiate from sibling tools like ada_komutlar or ada_kurallar, though the implied distinction is present.
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 explains that the tool should be used when a /command or free task description is provided to retrieve workflow rules. It gives examples but does not mention when not to use it or provide alternatives (siblings), leaving room for ambiguity.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
v1.0.0ada_komutlarada_kurallarada_workflowEach tool has a clearly distinct purpose: listing commands, returning rules, and returning workflow instructions. No overlap or ambiguity.
All tools use the 'ada_' prefix, but 'ada_workflow' mixes Turkish and English while the others are entirely Turkish. Mostly consistent with a minor deviation.
With 3 tools, the set is small but seems appropriate for the narrow domain of ADA Turbo commands and workflows. No unnecessary tools.
The tools cover listing commands, returning rules, and workflow instructions. Minor gap: no tool to update or add new commands, but core functionality is present.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Creative-intelligence MCP for campaign strategy, ad builds, QA, and reporting.
The first portfolio AI agents can hire. Profile, products, pricing and briefs over MCP.
AI marketing platform your agent runs end to end: ads, analytics, content, and reports.
AgencyAI's public MCP for service discovery and AI-readiness assessment.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/adacreativeco/ada-turbo-ai-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
