mcpField
S
S2T Accelerators

S2T Accelerators

Local
github.com/S2TConsultingDeveloper Tools0Updated 32w ago

About S2T Accelerators

S2T Accelerators is an MCP server for Claude and other MCP clients, exposing tools for AWS infrastructure, AI workflows, and security tasks. Its documented capabilities include embeddings, CloudFormation/SAM generation, and OAuth validation.

Key features

  1. 01Generate text embeddings with chunking
  2. 02Create CloudFormation/SAM templates from descriptions
  3. 03Validate OAuth 2.0 configurations
  4. 04List accelerators and their capabilities and pricing
  5. 05Check API usage and remaining quota

Use cases

  1. 01Generate embeddings for RAG or semantic search
  2. 02Create templates from infrastructure requirements
  3. 03Check OAuth settings before deployment
  4. 04Review API quota usage

MCP support

The MCP server exposes accelerator tools to Claude and other MCP clients, including embedding generation, template generation, and OAuth validation.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
"mcpServers": {
"accelerators": {
"command": "npx",
"args": [
"-y",
"s2t-mcp-accelerators"
],
"env": {
"S2T_API_KEY": "<S2T_API_KEY>"
}
}
}
}
Run commandnpx -y s2t-mcp-accelerators
Environment variables to set
S2T_API_KEYSecretYour S2T Accelerator Platform API key. Get one free at https://dev.s2tconsulting.com/ai-sales/purchase.html

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npms2t-mcp-accelerators1.4.2

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

S2T Accelerators MCP Server

npm version License: MIT MCP Compatible

MCP server providing Claude with access to S2T's battle-tested enterprise accelerators:

  • Vector Embeddings (ACC-AI-001) - Generate embeddings for RAG, semantic search
  • CloudFormation Generator (ACC-AWS-001) - Generate production-ready SAM/CFN templates
  • OAuth Validator (ACC-INT-001) - Validate OAuth configurations before deployment

Quick Start

1. Install
npm install -g s2t-mcp-accelerators
2. Get an API Key

Visit https://dev.s2tconsulting.com/ai-sales/purchase.html to create an account and get your API key.

3. Configure Claude Desktop

Add to your Claude Desktop config file:

macOS/Linux: ~/.config/Claude/claude_desktop_config.json Windows: %APPDATA%\Claude\claude_desktop_config.json

{
  "mcpServers": {
    "s2t-accelerators": {
      "command": "npx",
      "args": ["s2t-mcp-accelerators"],
      "env": {
        "S2T_API_KEY": "sk_live_your_api_key_here"
      }
    }
  }
}

Restart Claude Desktop to activate the tools.

Available Tools

s2t_embed

Generate vector embeddings for text. Supports automatic chunking for long documents.

Input:
- text: string (required) - Text to embed (max 100,000 characters)
- model: "amazon.titan-embed-text-v2:0" | "amazon.titan-embed-text-v1"
- chunk_size: number (100-2000, default: 512)
- chunk_overlap: number (0-500, default: 50)

Output: Embedding vectors with metadata

Use cases: RAG systems, semantic search, document similarity, knowledge base indexing

s2t_generate_cloudformation

Generate CloudFormation/SAM templates from natural language descriptions.

Input:
- description: string (required) - What infrastructure you need (max 5000 chars)
- format: "sam" | "cloudformation" (default: sam)
- include_parameters: boolean (default: true)
- include_outputs: boolean (default: true)

Output: Complete YAML template with best practices

Supported resources: Lambda, API Gateway, DynamoDB, S3, SQS, SNS, EventBridge, IAM

s2t_validate_oauth

Validate OAuth 2.0 configuration and detect common misconfigurations.

Input:
- provider: "google" | "microsoft" | "github" | "quickbooks" | "generic"
- client_id: string (required)
- redirect_uris: string[] (required)
- scopes: string[] (required)
- token_endpoint: string (optional, for generic)
- authorization_endpoint: string (optional, for generic)

Output: Validation results, warnings, recommendations

Detects: Invalid client IDs, insecure redirect URIs, missing scopes, deprecated endpoints

s2t_catalog

List all available S2T accelerators with their capabilities and pricing.

s2t_usage

Check your API usage statistics and remaining quota.

Pricing

TierPriceRate LimitMonthly Limit
Free$010/min100
Developer$29/mo60/min5,000
Business$99/mo300/min50,000
Enterprise$299/mo1,000/minUnlimited

Local Development

git clone https://github.com/S2TConsulting/accelerators-mcp.git
cd accelerators-mcp
npm install
npm run build
npm test
MCP Inspector

Test the server interactively with the MCP Inspector:

npx @modelcontextprotocol/inspector node dist/index.js
Running Locally
# Set API key
export S2T_API_KEY="sk_live_your_api_key"

# Run server
npm start
Testing
npm test              # Run tests once
npm run test:watch    # Watch mode
npm run test:coverage # Coverage report

Configuration Options

Environment Variables
VariableDescriptionDefault
S2T_API_KEYYour S2T API key (required)-
S2T_API_URLCustom API endpointProduction API
Claude Code

For Claude Code projects, add to ~/.mcp.json (or project-level .mcp.json):

{
  "mcpServers": {
    "s2t-accelerators": {
      "command": "npx",
      "args": ["s2t-mcp-accelerators"],
      "env": {
        "S2T_API_KEY": "sk_live_your_api_key_here"
      }
    }
  }
}

Contributing

We welcome contributions! Here's how to get started:

  1. Fork the repo and create a feature branch
  2. Install dependencies: npm install
  3. Make your changes in src/
  4. Add tests for new functionality in src/handlers.test.ts
  5. Run the test suite: npm test
  6. Submit a PR with a clear description of the change

Please ensure all tests pass before submitting.

Support

License

MIT - See LICENSE file for details.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.