build-custom-mcp-server

Build Custom MCP Server

Create custom MCP server exposing domain-specific tools to AI assistants.

When Use

• Need to expose custom functionality to Claude Code or Claude Desktop
• Building specialized tools beyond what mcptools provides
• Creating domain-specific AI assistant integration
• Wrapping existing APIs or services as MCP tools

Inputs

• Required: List of tools to expose (name, description, parameters, behavior)
• Required: Implementation language (Node.js or R)
• Required: Transport type (stdio or HTTP)
• Optional: Authentication requirements
• Optional: Docker packaging needs

Steps

Step 1: Define Tool Specifications

Before writing code, define each tool:

tools:
  - name: query_database
    description: Execute a read-only SQL query against the analysis database
    parameters:
      query:
        type: string
        description: SQL SELECT query to execute
        required: true
      limit:
        type: integer
        description: Maximum rows to return
        default: 100
    returns: JSON array of result rows

  - name: run_analysis
    description: Execute a predefined statistical analysis by name
    parameters:
      analysis_name:
        type: string
        description: Name of the analysis to run
        enum: [descriptive, regression, survival]
      dataset:
        type: string
        description: Dataset identifier
        required: true

Got: YAML or markdown spec for each tool with name, description, parameters (types, defaults, required flags), return type documented before writing code.

If fail: Tool specifications unclear? Interview domain expert or review existing API documentation for parameter types and return formats.

Step 2: Implement in Node.js (Using MCP SDK)

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

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

// Define tools
server.tool(
  "query_database",
  "Execute a read-only SQL query against the analysis database",
  {
    query: z.string().describe("SQL SELECT query"),
    limit: z.number().default(100).describe("Max rows to return"),
  },
  async ({ query, limit }) => {
    // Validate read-only
    if (!/^\s*SELECT/i.test(query)) {
      return {
        content: [{ type: "text", text: "Error: Only SELECT queries allowed" }],
        isError: true,
      };
    }

    const results = await executeQuery(query, limit);
    return {
      content: [{ type: "text", text: JSON.stringify(results, null, 2) }],
    };
  }
);

server.tool(
  "run_analysis",
  "Execute a predefined statistical analysis",
  {
    analysis_name: z.enum(["descriptive", "regression", "survival"]),
    dataset: z.string().describe("Dataset identifier"),
  },
  async ({ analysis_name, dataset }) => {
    const result = await runAnalysis(analysis_name, dataset);
    return {
      content: [{ type: "text", text: JSON.stringify(result, null, 2) }],
    };
  }
);

// Start server with stdio transport
const transport = new StdioServerTransport();
await server.connect(transport);