Skip to main content
Glama
devlimelabs

MCP Troubleshooter

by devlimelabs

generate-mcp-server-template

Create customizable MCP server templates for Typescript or Python with options for basic, tools-only, resources-only, or complete features to streamline server setup and diagnostics.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
featuresYesFeatures to include in the template
serverNameYesName for the MCP server
serverTypeYesType of server to generate

Implementation Reference

  • The main handler function for the 'generate-mcp-server-template' tool. It generates complete MCP server template code in either TypeScript or Python based on the provided serverName, serverType, and features parameters. Includes multiple template variants (basic, tools-only, resources-only, complete) with embedded setup instructions.
      async ({ serverName, serverType, features }) => {
        try {
          let template = "";
          
          if (serverType === "typescript") {
            if (features === "basic" || features === "tools-only") {
              template = `
    import { McpServer } from "@modelcontextprotocol/sdk/server/mcp.js";
    import { StdioServerTransport } from "@modelcontextprotocol/sdk/server/stdio.js";
    import { z } from "zod";
    
    // Create server with clear naming
    const server = new McpServer({
      name: "${serverName}",
      version: "1.0.0"
    });
    
    // Add a simple echo tool
    server.tool(
      "echo",
      {
        message: z.string().describe("Message to echo back")
      },
      async ({ message }) => {
        try {
          return {
            content: [{ type: "text", text: \`Echo: \${message}\` }]
          };
        } catch (error) {
          return {
            isError: true,
            content: [{ type: "text", text: \`Error: \${error.message}\` }]
          };
        }
      }
    );
    
    // Connect transport
    async function main() {
      const transport = new StdioServerTransport();
      await server.connect(transport);
      console.error("${serverName} started");
    }
    
    main().catch(console.error);`;
            } else if (features === "resources-only") {
              template = `
    import { McpServer, ResourceTemplate } from "@modelcontextprotocol/sdk/server/mcp.js";
    import { StdioServerTransport } from "@modelcontextprotocol/sdk/server/stdio.js";
    
    // Create server with clear naming
    const server = new McpServer({
      name: "${serverName}",
      version: "1.0.0"
    });
    
    // Add a static resource
    server.resource(
      "static-resource",
      "static://example",
      async (uri) => ({
        contents: [{
          uri: uri.href,
          text: "This is a static resource example."
        }]
      })
    );
    
    // Add a dynamic resource with template
    server.resource(
      "dynamic-resource",
      new ResourceTemplate("dynamic://{param}", { list: undefined }),
      async (uri, { param }) => ({
        contents: [{
          uri: uri.href,
          text: \`This is a dynamic resource with parameter: \${param}\`
        }]
      })
    );
    
    // Connect transport
    async function main() {
      const transport = new StdioServerTransport();
      await server.connect(transport);
      console.error("${serverName} started");
    }
    
    main().catch(console.error);`;
            } else { // complete
              template = `
    import { McpServer, ResourceTemplate } from "@modelcontextprotocol/sdk/server/mcp.js";
    import { StdioServerTransport } from "@modelcontextprotocol/sdk/server/stdio.js";
    import { z } from "zod";
    
    // Create server with clear naming
    const server = new McpServer({
      name: "${serverName}",
      version: "1.0.0"
    });
    
    // Add a tool
    server.tool(
      "echo",
      {
        message: z.string().describe("Message to echo back")
      },
      async ({ message }) => {
        try {
          return {
            content: [{ type: "text", text: \`Echo: \${message}\` }]
          };
        } catch (error) {
          return {
            isError: true,
            content: [{ type: "text", text: \`Error: \${error.message}\` }]
          };
        }
      }
    );
    
    // Add a static resource
    server.resource(
      "static-resource",
      "static://example",
      async (uri) => ({
        contents: [{
          uri: uri.href,
          text: "This is a static resource example."
        }]
      })
    );
    
    // Add a dynamic resource with template
    server.resource(
      "dynamic-resource",
      new ResourceTemplate("dynamic://{param}", { list: undefined }),
      async (uri, { param }) => ({
        contents: [{
          uri: uri.href,
          text: \`This is a dynamic resource with parameter: \${param}\`
        }]
      })
    );
    
    // Add a prompt template
    server.prompt(
      "greet",
      {
        name: z.string().describe("Name to greet")
      },
      ({ name }) => ({
        messages: [{
          role: "user",
          content: {
            type: "text",
            text: \`Please greet \${name} in a friendly way.\`
          }
        }]
      })
    );
    
    // Connect transport
    async function main() {
      const transport = new StdioServerTransport();
      await server.connect(transport);
      console.error("${serverName} started");
    }
    
    main().catch(console.error);`;
            }
          } else { // python
            if (features === "basic" || features === "tools-only") {
              template = `
    from mcp.server.fastmcp import FastMCP
    
    # Create MCP server
    mcp = FastMCP("${serverName}")
    
    @mcp.tool()
    async def echo(message: str) -> str:
        """Echo a message back.
        
        Args:
            message: Message to echo back
        """
        try:
            return f"Echo: {message}"
        except Exception as e:
            return f"Error: {str(e)}"
    
    if __name__ == "__main__":
        # Run the server
        mcp.run(transport='stdio')`;
            } else if (features === "resources-only") {
              template = `
    from mcp.server.fastmcp import FastMCP
    import mcp.types as types
    from typing import List
    
    # Create MCP server
    mcp = FastMCP("${serverName}")
    
    @mcp.resource("static://example")
    async def static_resource() -> str:
        """Return a static resource."""
        return "This is a static resource example."
    
    @mcp.resource("dynamic://{param}")
    async def dynamic_resource(param: str) -> str:
        """Return a dynamic resource.
        
        Args:
            param: Parameter value
        """
        return f"This is a dynamic resource with parameter: {param}"
    
    if __name__ == "__main__":
        # Run the server
        mcp.run(transport='stdio')`;
            } else { // complete
              template = `
    from mcp.server.fastmcp import FastMCP
    import mcp.types as types
    from typing import List
    
    # Create MCP server
    mcp = FastMCP("${serverName}")
    
    @mcp.tool()
    async def echo(message: str) -> str:
        """Echo a message back.
        
        Args:
            message: Message to echo back
        """
        try:
            return f"Echo: {message}"
        except Exception as e:
            return f"Error: {str(e)}"
    
    @mcp.resource("static://example")
    async def static_resource() -> str:
        """Return a static resource."""
        return "This is a static resource example."
    
    @mcp.resource("dynamic://{param}")
    async def dynamic_resource(param: str) -> str:
        """Return a dynamic resource.
        
        Args:
            param: Parameter value
        """
        return f"This is a dynamic resource with parameter: {param}"
    
    @mcp.prompt()
    async def greet(name: str) -> List[types.PromptMessage]:
        """Define a greeting prompt.
        
        Args:
            name: Name to greet
        """
        return [
            types.PromptMessage(
                role="user",
                content=types.TextContent(
                    type="text",
                    text=f"Please greet {name} in a friendly way."
                )
            )
        ]
    
    if __name__ == "__main__":
        # Run the server
        mcp.run(transport='stdio')`;
            }
          }
          
          return {
            content: [{ 
              type: "text", 
              text: `# ${serverName} Template (${serverType})\n\nHere's a ${features} template for your MCP server:\n\n\`\`\`${serverType === "typescript" ? "typescript" : "python"}\n${template}\n\`\`\`\n\n## Setup Instructions\n\n${serverType === "typescript" ? 
                `1. Create a new directory for your project
    2. Initialize a new npm project: \`npm init -y\`
    3. Install dependencies: \`npm install @modelcontextprotocol/sdk zod\`
    4. Install dev dependencies: \`npm install -D typescript @types/node\`
    5. Create a tsconfig.json file
    6. Save the above code to src/index.ts
    7. Compile with TypeScript: \`npx tsc\`
    8. Run the server: \`node build/index.js\`` 
                : 
                `1. Create a new directory for your project
    2. Create a virtual environment: \`python -m venv venv\`
    3. Activate the virtual environment: \`source venv/bin/activate\` (Linux/Mac) or \`venv\\Scripts\\activate\` (Windows)
    4. Install dependencies: \`pip install mcp\`
    5. Save the above code to server.py
    6. Run the server: \`python server.py\``}` 
            }]
          };
        } catch (error) {
          return {
            isError: true,
            content: [{ type: "text", text: `Error generating template: ${error.message}` }]
          };
        }
      }
  • Zod schema defining the input parameters for the tool: serverName (string), serverType (enum: typescript/python), features (enum: basic/tools-only/resources-only/complete).
    {
      serverName: z.string().describe("Name for the MCP server"),
      serverType: z.enum(["typescript", "python"]).describe("Type of server to generate"),
      features: z.enum(["basic", "tools-only", "resources-only", "complete"]).describe("Features to include in the template")
    },
  • src/index.ts:651-963 (registration)
    Registration of the 'generate-mcp-server-template' tool on the McpServer instance using server.tool(name, inputSchema, handlerFn).
    server.tool(
      "generate-mcp-server-template",
      {
        serverName: z.string().describe("Name for the MCP server"),
        serverType: z.enum(["typescript", "python"]).describe("Type of server to generate"),
        features: z.enum(["basic", "tools-only", "resources-only", "complete"]).describe("Features to include in the template")
      },
      async ({ serverName, serverType, features }) => {
        try {
          let template = "";
          
          if (serverType === "typescript") {
            if (features === "basic" || features === "tools-only") {
              template = `
    import { McpServer } from "@modelcontextprotocol/sdk/server/mcp.js";
    import { StdioServerTransport } from "@modelcontextprotocol/sdk/server/stdio.js";
    import { z } from "zod";
    
    // Create server with clear naming
    const server = new McpServer({
      name: "${serverName}",
      version: "1.0.0"
    });
    
    // Add a simple echo tool
    server.tool(
      "echo",
      {
        message: z.string().describe("Message to echo back")
      },
      async ({ message }) => {
        try {
          return {
            content: [{ type: "text", text: \`Echo: \${message}\` }]
          };
        } catch (error) {
          return {
            isError: true,
            content: [{ type: "text", text: \`Error: \${error.message}\` }]
          };
        }
      }
    );
    
    // Connect transport
    async function main() {
      const transport = new StdioServerTransport();
      await server.connect(transport);
      console.error("${serverName} started");
    }
    
    main().catch(console.error);`;
            } else if (features === "resources-only") {
              template = `
    import { McpServer, ResourceTemplate } from "@modelcontextprotocol/sdk/server/mcp.js";
    import { StdioServerTransport } from "@modelcontextprotocol/sdk/server/stdio.js";
    
    // Create server with clear naming
    const server = new McpServer({
      name: "${serverName}",
      version: "1.0.0"
    });
    
    // Add a static resource
    server.resource(
      "static-resource",
      "static://example",
      async (uri) => ({
        contents: [{
          uri: uri.href,
          text: "This is a static resource example."
        }]
      })
    );
    
    // Add a dynamic resource with template
    server.resource(
      "dynamic-resource",
      new ResourceTemplate("dynamic://{param}", { list: undefined }),
      async (uri, { param }) => ({
        contents: [{
          uri: uri.href,
          text: \`This is a dynamic resource with parameter: \${param}\`
        }]
      })
    );
    
    // Connect transport
    async function main() {
      const transport = new StdioServerTransport();
      await server.connect(transport);
      console.error("${serverName} started");
    }
    
    main().catch(console.error);`;
            } else { // complete
              template = `
    import { McpServer, ResourceTemplate } from "@modelcontextprotocol/sdk/server/mcp.js";
    import { StdioServerTransport } from "@modelcontextprotocol/sdk/server/stdio.js";
    import { z } from "zod";
    
    // Create server with clear naming
    const server = new McpServer({
      name: "${serverName}",
      version: "1.0.0"
    });
    
    // Add a tool
    server.tool(
      "echo",
      {
        message: z.string().describe("Message to echo back")
      },
      async ({ message }) => {
        try {
          return {
            content: [{ type: "text", text: \`Echo: \${message}\` }]
          };
        } catch (error) {
          return {
            isError: true,
            content: [{ type: "text", text: \`Error: \${error.message}\` }]
          };
        }
      }
    );
    
    // Add a static resource
    server.resource(
      "static-resource",
      "static://example",
      async (uri) => ({
        contents: [{
          uri: uri.href,
          text: "This is a static resource example."
        }]
      })
    );
    
    // Add a dynamic resource with template
    server.resource(
      "dynamic-resource",
      new ResourceTemplate("dynamic://{param}", { list: undefined }),
      async (uri, { param }) => ({
        contents: [{
          uri: uri.href,
          text: \`This is a dynamic resource with parameter: \${param}\`
        }]
      })
    );
    
    // Add a prompt template
    server.prompt(
      "greet",
      {
        name: z.string().describe("Name to greet")
      },
      ({ name }) => ({
        messages: [{
          role: "user",
          content: {
            type: "text",
            text: \`Please greet \${name} in a friendly way.\`
          }
        }]
      })
    );
    
    // Connect transport
    async function main() {
      const transport = new StdioServerTransport();
      await server.connect(transport);
      console.error("${serverName} started");
    }
    
    main().catch(console.error);`;
            }
          } else { // python
            if (features === "basic" || features === "tools-only") {
              template = `
    from mcp.server.fastmcp import FastMCP
    
    # Create MCP server
    mcp = FastMCP("${serverName}")
    
    @mcp.tool()
    async def echo(message: str) -> str:
        """Echo a message back.
        
        Args:
            message: Message to echo back
        """
        try:
            return f"Echo: {message}"
        except Exception as e:
            return f"Error: {str(e)}"
    
    if __name__ == "__main__":
        # Run the server
        mcp.run(transport='stdio')`;
            } else if (features === "resources-only") {
              template = `
    from mcp.server.fastmcp import FastMCP
    import mcp.types as types
    from typing import List
    
    # Create MCP server
    mcp = FastMCP("${serverName}")
    
    @mcp.resource("static://example")
    async def static_resource() -> str:
        """Return a static resource."""
        return "This is a static resource example."
    
    @mcp.resource("dynamic://{param}")
    async def dynamic_resource(param: str) -> str:
        """Return a dynamic resource.
        
        Args:
            param: Parameter value
        """
        return f"This is a dynamic resource with parameter: {param}"
    
    if __name__ == "__main__":
        # Run the server
        mcp.run(transport='stdio')`;
            } else { // complete
              template = `
    from mcp.server.fastmcp import FastMCP
    import mcp.types as types
    from typing import List
    
    # Create MCP server
    mcp = FastMCP("${serverName}")
    
    @mcp.tool()
    async def echo(message: str) -> str:
        """Echo a message back.
        
        Args:
            message: Message to echo back
        """
        try:
            return f"Echo: {message}"
        except Exception as e:
            return f"Error: {str(e)}"
    
    @mcp.resource("static://example")
    async def static_resource() -> str:
        """Return a static resource."""
        return "This is a static resource example."
    
    @mcp.resource("dynamic://{param}")
    async def dynamic_resource(param: str) -> str:
        """Return a dynamic resource.
        
        Args:
            param: Parameter value
        """
        return f"This is a dynamic resource with parameter: {param}"
    
    @mcp.prompt()
    async def greet(name: str) -> List[types.PromptMessage]:
        """Define a greeting prompt.
        
        Args:
            name: Name to greet
        """
        return [
            types.PromptMessage(
                role="user",
                content=types.TextContent(
                    type="text",
                    text=f"Please greet {name} in a friendly way."
                )
            )
        ]
    
    if __name__ == "__main__":
        # Run the server
        mcp.run(transport='stdio')`;
            }
          }
          
          return {
            content: [{ 
              type: "text", 
              text: `# ${serverName} Template (${serverType})\n\nHere's a ${features} template for your MCP server:\n\n\`\`\`${serverType === "typescript" ? "typescript" : "python"}\n${template}\n\`\`\`\n\n## Setup Instructions\n\n${serverType === "typescript" ? 
                `1. Create a new directory for your project
    2. Initialize a new npm project: \`npm init -y\`
    3. Install dependencies: \`npm install @modelcontextprotocol/sdk zod\`
    4. Install dev dependencies: \`npm install -D typescript @types/node\`
    5. Create a tsconfig.json file
    6. Save the above code to src/index.ts
    7. Compile with TypeScript: \`npx tsc\`
    8. Run the server: \`node build/index.js\`` 
                : 
                `1. Create a new directory for your project
    2. Create a virtual environment: \`python -m venv venv\`
    3. Activate the virtual environment: \`source venv/bin/activate\` (Linux/Mac) or \`venv\\Scripts\\activate\` (Windows)
    4. Install dependencies: \`pip install mcp\`
    5. Save the above code to server.py
    6. Run the server: \`python server.py\``}` 
            }]
          };
        } catch (error) {
          return {
            isError: true,
            content: [{ type: "text", text: `Error generating template: ${error.message}` }]
          };
        }
      }
    );
Behavior1/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Tool has no description.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness1/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Tool has no description.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness1/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Tool has no description.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters1/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Tool has no description.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose1/5

Does the description clearly state what the tool does and how it differs from similar tools?

Tool has no description.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines1/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Tool has no description.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

Related Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/devlimelabs/mcp-troubleshooter-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server