MCP Integration

The Model Context Protocol (MCP) is an open standard for connecting AI models to external tools and data sources. LW AI supports MCP for building agentic workflows.

What is MCP?

MCP enables:

Tool use — Models can call external functions (APIs, databases, file systems)
Resource access — Models can read contextual data from external sources
Prompt templates — Standardized prompt structures for consistent interactions

Using MCP with LW AI

LW AI models support MCP through function calling. Define MCP tools as function definitions in your API request:

from openai import OpenAI

client = OpenAI(
    base_url="https://openapi.linkwo.ai/v1",
    api_key="YOUR_API_KEY"
)

mcp_tools = [
    {
        "type": "function",
        "function": {
            "name": "query_database",
            "description": "Query the company database",
            "parameters": {
                "type": "object",
                "properties": {
                    "sql": {"type": "string", "description": "SQL query to execute"},
                    "database": {"type": "string", "enum": ["production", "staging"]}
                },
                "required": ["sql"]
            }
        }
    },
    {
        "type": "function",
        "function": {
            "name": "read_file",
            "description": "Read a file from the project directory",
            "parameters": {
                "type": "object",
                "properties": {
                    "path": {"type": "string", "description": "File path relative to project root"}
                },
                "required": ["path"]
            }
        }
    }
]

response = client.chat.completions.create(
    model="deepseek/deepseek-v4-pro",
    messages=[{"role": "user", "content": "Show me the user table schema"}],
    tools=mcp_tools,
    tool_choice="auto"
)

MCP Server Setup

To expose your tools via MCP protocol, you can build an MCP server:

import { McpServer } from "@modelcontextprotocol/sdk/server/mcp.js";
import { StdioServerTransport } from "@modelcontextprotocol/sdk/server/stdio.js";

const server = new McpServer({ name: "my-tools", version: "1.0.0" });

server.tool("query_database", { sql: z.string() }, async ({ sql }) => {
  const results = await executeQuery(sql);
  return { content: [{ type: "text", text: JSON.stringify(results) }] };
});

const transport = new StdioServerTransport();
await server.connect(transport);

Compatible MCP Clients

Client	Description
Claude Code	Terminal-based coding agent
Cline	VS Code autonomous agent
Roo Code	VS Code autonomous agent
Continue	VS Code AI assistant

Best Practices

Describe tools clearly — Good descriptions help the model choose the right tool
Validate inputs — Sanitize tool inputs before execution
Return structured data — Use JSON for tool results
Handle errors — Return error messages as tool results so the model can self-correct

Function Calling — Detailed tool calling guide
Claude Code — Claude Code configuration

VS Code