AgentStack

v1.0.0Coding Agentsstable

AgentStack is a production-grade multi-agent framework built on Mastra, delivering 50+ enterprise tools, 25+ specialized agents, and A2A/MCP orchestration for scalable AI systems. Focuses on financial intelligence, RAG pipelines, observability, and s

a2aagentic-aiagentsai-agentschatbot
Share:
32
Stars
0
Downloads
0
Weekly
0/5

What is AgentStack?

AgentStack is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to agentstack is a production-grade multi-agent framework built on mastra, delivering 50+ enterprise tools, 25+ specialized agents, and a2a/mcp orchestration for scalable ai systems. focuses on financial...

AgentStack is a production-grade multi-agent framework built on Mastra, delivering 50+ enterprise tools, 25+ specialized agents, and A2A/MCP orchestration for scalable AI systems. Focuses on financial intelligence, RAG pipelines, observability, and s

This server falls under the Coding Agents category on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • AgentStack is a production-grade multi-agent framework built

Use Cases

Deploy multi-agent systems
Enterprise automation
RAG and observability
ssdeanx

Maintainer

LicenseMIT
Languagetypescript
Versionv1.0.0
UpdatedMay 15, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux

Installation

Manual Installation

npx agentstack

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use AgentStack

AgentStack is a production-grade multi-agent framework built on Mastra that ships 48+ specialized agents, 94+ enterprise tools, and 21 multi-step workflows out of the box. It integrates financial data APIs (Polygon, Finnhub, AlphaVantage), search tools (SerpAPI), a zero-config RAG pipeline with libSQL vector storage, browser automation via Chrome/CDP, and full observability through Langfuse. Teams building complex AI systems can use AgentStack as a foundation for financial intelligence, content creation pipelines, document processing, and scalable A2A/MCP orchestration.

Prerequisites

  • Node.js 20.9.0 or later
  • A Google Generative AI API key (GOOGLE_GENERATIVE_AI_API_KEY) for Gemini LLM and embeddings
  • A Turso database URL or local libSQL file path for persistence
  • A SerpAPI key (SERPAPI_API_KEY) for search tools
  • A Polygon API key (POLYGON_API_KEY) for financial data tools
1

Clone the repository

Clone the AgentStack repository and navigate into the project directory.

git clone https://github.com/ssdeanx/AgentStack.git
cd AgentStack
2

Install dependencies

Install all Node.js dependencies. Node.js 20.9.0 or later is required.

npm install
3

Configure environment variables

Create a .env file in the project root with your API keys and database configuration. At minimum, set the Gemini key and a database URL.

GOOGLE_GENERATIVE_AI_API_KEY=your-gemini-api-key
TURSO_DATABASE_URL=file:./data/mastra.db
SERPAPI_API_KEY=your-serpapi-key
POLYGON_API_KEY=your-polygon-key
# Optional
OPENAI_API_KEY=your-openai-key
LANGFUSE_BASE_URL=https://cloud.langfuse.com
4

Start the development server

Launch the AgentStack development server. The web interface will be available at http://localhost:3000.

npm run dev
5

Configure Claude Desktop to use AgentStack via MCP

Add AgentStack as an MCP server in your Claude Desktop configuration to expose its agents and tools to Claude.

{
  "mcpServers": {
    "agentstack": {
      "command": "npx",
      "args": ["agentstack"],
      "env": {
        "GOOGLE_GENERATIVE_AI_API_KEY": "your-gemini-api-key",
        "TURSO_DATABASE_URL": "file:./data/mastra.db",
        "SERPAPI_API_KEY": "your-serpapi-key",
        "POLYGON_API_KEY": "your-polygon-key"
      }
    }
  }
}
6

Run tests to verify your setup

Run the test suite to confirm all components are correctly configured. AgentStack ships with 97% test coverage.

npm test
npm run typecheck

AgentStack Examples

Client configuration

Claude Desktop configuration for AgentStack with the required API keys.

{
  "mcpServers": {
    "agentstack": {
      "command": "npx",
      "args": ["agentstack"],
      "env": {
        "GOOGLE_GENERATIVE_AI_API_KEY": "your-gemini-api-key",
        "TURSO_DATABASE_URL": "file:./data/mastra.db",
        "SERPAPI_API_KEY": "your-serpapi-key",
        "POLYGON_API_KEY": "your-polygon-key"
      }
    }
  }
}

Prompts to try

Example prompts that exercise AgentStack's financial intelligence, RAG, and multi-agent capabilities.

- "Generate a financial intelligence report for AAPL including recent price aggregates, fundamentals, and news sentiment."
- "Search the web for the latest trends in AI agent frameworks and summarize the top 5 findings."
- "Ingest this PDF document into the RAG pipeline and answer questions about its contents."
- "Delegate a content creation workflow: research the topic, draft an article, and return the final output."
- "What specialized agents are available and what can each one do?"

Troubleshooting AgentStack

Server fails to start with 'GOOGLE_GENERATIVE_AI_API_KEY is not set'

Ensure your .env file is in the project root and contains GOOGLE_GENERATIVE_AI_API_KEY. The server requires this key at startup. Verify with 'node -e "require(\"dotenv\").config(); console.log(process.env.GOOGLE_GENERATIVE_AI_API_KEY)"'.

libSQL/Turso connection fails on startup

For local development, use TURSO_DATABASE_URL=file:./data/mastra.db and ensure the data/ directory exists (mkdir -p data). For Turso cloud, verify the URL and auth token are correct in your .env file.

Financial data tools return empty results

Confirm POLYGON_API_KEY is set and valid. Polygon's free tier has rate limits and data restrictions. Check your Polygon dashboard for API usage and upgrade to a paid plan if you need real-time data or higher request limits.

Frequently Asked Questions about AgentStack

What is AgentStack?

AgentStack is a Model Context Protocol (MCP) server that agentstack is a production-grade multi-agent framework built on mastra, delivering 50+ enterprise tools, 25+ specialized agents, and a2a/mcp orchestration for scalable ai systems. focuses on financial intelligence, rag pipelines, observability, and s It connects AI assistants to external tools and data sources through a standardized interface.

How do I install AgentStack?

Follow the installation instructions on the AgentStack GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.

Which AI clients work with AgentStack?

AgentStack works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is AgentStack free to use?

Yes, AgentStack is open source and available under the MIT license. You can use it freely in both personal and commercial projects.

Browse More Coding Agents MCP Servers

Explore all coding agents servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

Quick Config Preview

{ "mcpServers": { "agentstack": { "command": "npx", "args": ["-y", "agentstack"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

Ready to use AgentStack?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides