Biz

You deploy an MCP server that exposes a JSON-RPC MCP endpoint to orchestrate business tools. This server lets Evolution AI Agents call tools, list available tools, and read resources through a standardized MCP interface, enabling you to integrate external business logic and data sources with AI workflows.

How to use

You connect an MCP client to the server by pointing it at the MCP endpoint and then using the supported methods to initialize, list tools, or call specific tools. The server provides a stable, extensible interface for invoking business tools and accessing resources from your AI-driven workflows. Start by confirming the server is healthy, then query the available tools, and finally invoke the tools that match your business use cases, such as data enrichment, calculations, or external service orchestration.

How to install

Prerequisites you need before installation are:

• Python 3.11+
• Git
• (optional) Docker if you want to run in a container Proceed with the following steps to set up and run the MCP server locally.

# 1) Clone the project repository
git clone https://github.com/<ВАШ_АККАУНТ>/<ВАШ_РЕПОЗИТОРИЙ>.git
cd mcp-biz-master

# 2) Create a Python virtual environment
python -m venv .venv
# Windows:
.\.venv\Scripts\activate
# Linux/macOS:
source .venv/bin/activate

# 3) Install dependencies
pip install -r requirements.txt

# 4) Start the MCP server
python -m uvicorn app.main:app --host 0.0.0.0 --port 8000 --reload

Additional sections

Configuration and runtime details closely follow the project’s setup and deployment flow. You will provide essential credentials and environment variables to enable secure interaction with external services and evolution agents.

Security and operational notes to consider as you deploy:

• Keep sensitive keys out of version control by using a local environment file and adding it to your .gitignore.
• Use a strong SECRET_KEY to sign internal tokens.
• If you expose the MCP endpoint publicly, consider implementing authentication, rate limiting, and monitoring to protect your business tools.

Troubleshooting tips:

• If the server does not start, verify that Python 3.11+ is installed and that the virtual environment is activated.
• Check that the health endpoint responds with status "ok" to confirm the server is running.
• Ensure environment variables EVOLUTION_API_KEY and SECRET_KEY are correctly set in your environment or in the .env file before starting the server.

Available tools

initialize

Prepare and configure the MCP session for a client, establishing context and readiness to list or call tools.

tools/list

Return the list of available MCP tools with their input schemas so you know what arguments you can pass.

tools/call

Execute a specific MCP tool by name with the provided arguments, returning the tool output.

resources/list

List data or external resources accessible to MCP tools (placeholder in MVP).

resources/read

Read data from a specific resource through the MCP interface (placeholder in MVP).