About AI Service Platform
AI Service Platform is a cloud-ready platform for hosting AI tool execution through REST APIs. It discovers MCP tools in a `servers/` directory and is intended for deployments that need stateless operation with persistent tool configuration and horizontal scaling.
Key features
- 01REST API for tool operations
- 02Automatic MCP tool discovery
- 03Stateless service design
- 04Persistent tool configuration
- 05Horizontal scaling support
Use cases
- 01Listing available tools through `/tools`
- 02Submitting natural-language queries to `/query`
- 03Deploying a scalable hosted tool service
MCP support
The platform discovers MCP tools in its `servers/` directory and provides a REST API for listing and querying available tools.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEAI Service Platform
A cloud-ready service platform for AI-powered tool execution with Model Context Protocol (MCP) integration.
Key Features
-
Cloud Native Architecture
- REST API endpoints for all operations
- Stateless design with persistent tool configuration
- Horizontal scaling support
-
Unified Tool Gateway
- Automatic discovery of MCP tools in
servers/directory
- Automatic discovery of MCP tools in
Cloud Deployment
Prerequisites
- Python 3.10+
API Usage
Endpoints
List Available Tools
GET /tools
Execute Natural Language Query
POST /query
{
"query": "5+5",
}
Development Setup
- Clone the repository:
git clone https://github.com/Daniel1989/mcp-server-cloud.git
cd mcp-server-cloud
- Set up virtual environment:
python -m venv venv
source venv/bin/activate
pip install -r requirements.txt
- Start development server:
FLASK_DEBUG=1 python flask.py
Resources
- python-sdk. https://github.com/modelcontextprotocol/python-sdk
- cline's prompt -- how to ask ai to select mcp server. https://github.com/cline/cline/blob/main/src/core/prompts/system.ts
- remote mcp server https://github.com/sidharthrajaram/mcp-sse
- https://actions.zapier.com/settings/mcp/
Comments
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.