Skip to main content
Glama
StudentOfJS

MCP Frontend Testing Server

testReactComponent

Test React components by validating component code, generating or executing test cases, and analyzing results using Jest or Cypress frameworks. Simplifies frontend testing workflows on the MCP Frontend Testing Server.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
autoGenerateTestNo
componentCodeYes
frameworkNojest
propsNo
testCodeNo

Implementation Reference

  • The main handler function implementing the 'testReactComponent' tool. Determines language, generates test code if needed, sets up temporary test directory, installs deps, runs tests with jest or cypress, returns results or error, and cleans up.
    async ({ componentCode, testCode, framework, props, autoGenerateTest }) => {
      try {
        // Determine language based on code
        const language = componentCode.includes('tsx') || componentCode.includes(':') ? 
          'tsx' : (componentCode.includes('jsx') ? 'jsx' : 'javascript');
        
        // Generate test if not provided
        let finalTestCode = testCode;
        if (!finalTestCode && autoGenerateTest) {
          finalTestCode = await generateTestCode(
            componentCode, 
            framework, 
            'component', 
            language
          );
        }
        
        if (!finalTestCode) {
          throw new Error('No test code provided or generated');
        }
        
        // Create temporary test environment
        const testId = crypto.randomUUID();
        const testDir = path.join(os.tmpdir(), 'mcp-test-server', testId);
        
        // Set up files for component testing
        await setupTestEnvironment(testDir, componentCode, finalTestCode, framework, 'component', props);
        
        // Install dependencies
        await executeCommand('npm install', testDir);
        
        try {
          // Run the test
          const results = await executeTest(testDir, framework, 'component');
          
          return {
            content: [{ 
              type: 'text', 
              text: JSON.stringify(results, null, 2),
            }],
          };
        } finally {
          // Clean up
          try {
            await rm(testDir, { recursive: true, force: true });
          } catch (error) {
            console.error('Error cleaning up test environment:', error);
          }
        }
      } catch (error) {
        return {
          isError: true,
          content: [{ 
            type: 'text', 
            text: `Error testing component: ${String(error)}`,
          }],
        };
      }
    }
  • Input schema using Zod for validating parameters: required component code, optional test code/framework/props/auto-generate flag.
    {
      componentCode: z.string(),
      testCode: z.string().optional(),
      framework: z.enum(['jest', 'cypress']).default('jest'),
      props: z.record(z.any()).optional(),
      autoGenerateTest: z.boolean().default(true)
    },
  • Registration function that defines and registers the 'testReactComponent' tool on the MCP server, including schema and handler.
    export function registerComponentTesterTool(server: McpServer): void {
      server.tool(
        'testReactComponent',
        {
          componentCode: z.string(),
          testCode: z.string().optional(),
          framework: z.enum(['jest', 'cypress']).default('jest'),
          props: z.record(z.any()).optional(),
          autoGenerateTest: z.boolean().default(true)
        },
        async ({ componentCode, testCode, framework, props, autoGenerateTest }) => {
          try {
            // Determine language based on code
            const language = componentCode.includes('tsx') || componentCode.includes(':') ? 
              'tsx' : (componentCode.includes('jsx') ? 'jsx' : 'javascript');
            
            // Generate test if not provided
            let finalTestCode = testCode;
            if (!finalTestCode && autoGenerateTest) {
              finalTestCode = await generateTestCode(
                componentCode, 
                framework, 
                'component', 
                language
              );
            }
            
            if (!finalTestCode) {
              throw new Error('No test code provided or generated');
            }
            
            // Create temporary test environment
            const testId = crypto.randomUUID();
            const testDir = path.join(os.tmpdir(), 'mcp-test-server', testId);
            
            // Set up files for component testing
            await setupTestEnvironment(testDir, componentCode, finalTestCode, framework, 'component', props);
            
            // Install dependencies
            await executeCommand('npm install', testDir);
            
            try {
              // Run the test
              const results = await executeTest(testDir, framework, 'component');
              
              return {
                content: [{ 
                  type: 'text', 
                  text: JSON.stringify(results, null, 2),
                }],
              };
            } finally {
              // Clean up
              try {
                await rm(testDir, { recursive: true, force: true });
              } catch (error) {
                console.error('Error cleaning up test environment:', error);
              }
            }
          } catch (error) {
            return {
              isError: true,
              content: [{ 
                type: 'text', 
                text: `Error testing component: ${String(error)}`,
              }],
            };
          }
        }
      );
    }
  • src/server.ts:32-32 (registration)
    Invocation of the registration function in the main server creation, adding the tool to the MCP server.
    registerComponentTesterTool(server);
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/StudentOfJS/mcp-frontend-testing'

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