Binspire

Binspire MCP is an integration server that connects large language models (LLMs) to the Binspire API, providing standardized tools and contextual data to help you build autonomous, AI-driven waste management agents. It enables you to run MCP either locally via STDIO (a small, in-process server) or as a remote HTTP service, giving you flexible deployment options for your workflow.

How to use

You interact with Binspire MCP through an MCP client. Choose the transport that best fits your setup: STDIO for a local process integration or HTTP to run a remote service. In both modes, you can access the same set of standardized tools and context data provided by the Binspire API to enable your AI agents to perform waste management tasks.

How to install

Prerequisites you need before starting:

• Node.js >= 20.19 or nvm

• Claude Desktop (with MCP support)

• Bun latest runtime

How to install

# Bun setup
# Install Bun using the official installer
$ curl -fsSL https://bun.sh/install | bash
# Verify Bun
$ bun -version

# Clone the repository
$ git clone https://github.com/binspireai/mcp.git
$ cd mcp

# Install dependencies
$ bun install

# Copy example env file and configure
$ cp env.example .env

# Development servers
# STDIO development server
$ bun run dev:stdio

# HTTP development server
$ bun run dev:http

# Production servers
# STDIO production server
$ bun run start:stdio

# HTTP production server
$ bun run start:http

# Build for production
$ bun run build

How to install

If you are configuring a local development environment, follow the steps above to install dependencies, set up environment variables, and run development or production servers using the provided Bun commands.

Configuration examples

Configure your MCP client (Claude Desktop) to connect to Binspire MCP in either STDIO or HTTP mode. The following examples show how to reference the local processes or HTTP endpoint.

{
  "mcpServers": {
    "binspire": {
      "command": "node",
      "args": ["/path/to/binspire-mcp/dist/index.js"],
      "env": {
        "TRANSPORT": "stdio",
        "DATABASE_URL": "your_database_url_here"
      }
    }
  }
}

Configuration examples

{
  "mcpServers": {
    "binspire": {
      "url": "http://localhost:3000",
      "env": {
        "DATABASE_URL": "your_database_url_here"
      }
    }
  }
}