Skip to main content
Glama
devskido

Playwright MCP Server

by devskido

end_codegen_session

End a Playwright browser automation session and generate the corresponding test file from recorded interactions.

Instructions

End a code generation session and generate the test file

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
sessionIdYesID of the session to end

Implementation Reference

  • Full Tool definition including the handler function that ends the codegen session by generating and saving a Playwright test file from recorded actions, cleaning up browser resources, and returning the generated file path.
    export const endCodegenSession: Tool = {
      name: 'end_codegen_session',
      description: 'End the current code generation session and generate Playwright test',
      parameters: {
        type: 'object',
        properties: {
          sessionId: {
            type: 'string',
            description: 'ID of the session to end'
          }
        },
        required: ['sessionId']
      },
      handler: async ({ sessionId }: { sessionId: string }) => {
        try {
          const recorder = ActionRecorder.getInstance();
          const session = recorder.endSession(sessionId);
    
          if (!session) {
            throw new Error(`Session ${sessionId} not found`);
          }
    
          if (!session.options) {
            throw new Error(`Session ${sessionId} has no options configured`);
          }
    
          const generator = new PlaywrightGenerator(session.options);
          const result = await generator.generateTest(session);
    
          // Double check output directory exists
          const outputDir = path.dirname(result.filePath);
          await fs.mkdir(outputDir, { recursive: true });
          
          // Write test file
          try {
            await fs.writeFile(result.filePath, result.testCode, 'utf-8');
          } catch (writeError: any) {
            throw new Error(`Failed to write test file: ${writeError.message}`);
          }
    
          // Close Playwright browser and cleanup
          try {
            if (global.browser?.isConnected()) {
              await global.browser.close();
            }
          } catch (browserError: any) {
            console.warn('Failed to close browser:', browserError.message);
          } finally {
            global.browser = undefined;
            global.page = undefined;
          }
    
          const absolutePath = path.resolve(result.filePath);
    
          return {
            filePath: absolutePath,
            outputDirectory: outputDir,
            testCode: result.testCode,
            message: `Generated test file at: ${absolutePath}\nOutput directory: ${outputDir}`
          };
        } catch (error: any) {
          // Ensure browser cleanup even on error
          try {
            if (global.browser?.isConnected()) {
              await global.browser.close();
            }
          } catch {
            // Ignore cleanup errors
          } finally {
            global.browser = undefined;
            global.page = undefined;
          }
          
          throw new Error(`Failed to end codegen session: ${error.message}`);
        }
      }
    };
  • MCP tool schema definition used for input validation and tool registration.
      name: "end_codegen_session",
      description: "End a code generation session and generate the test file",
      inputSchema: {
        type: "object",
        properties: {
          sessionId: { 
            type: "string", 
            description: "ID of the session to end" 
          }
        },
        required: ["sessionId"]
      }
    },
  • Registration and dispatch logic in the main tool handler that routes 'end_codegen_session' calls to its handler function.
    // Handle codegen tools
    switch (name) {
      case 'start_codegen_session':
        return await handleCodegenResult(startCodegenSession.handler(args));
      case 'end_codegen_session':
        return await handleCodegenResult(endCodegenSession.handler(args));
      case 'get_codegen_session':
        return await handleCodegenResult(getCodegenSession.handler(args));
      case 'clear_codegen_session':
        return await handleCodegenResult(clearCodegenSession.handler(args));
    }
  • src/tools.ts:484-490 (registration)
    Array listing codegen tools including 'end_codegen_session' for categorization and tool list composition.
    // Codegen tools
    export const CODEGEN_TOOLS = [
      'start_codegen_session',
      'end_codegen_session',
      'get_codegen_session',
      'clear_codegen_session'
    ];
Behavior2/5

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It mentions generating a test file, which adds context beyond the basic action, but fails to describe critical traits like whether this is a destructive operation (likely yes, as it ends a session), what permissions are needed, or what happens to the session data. This leaves significant gaps for an agent to understand the tool's behavior.

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

Conciseness5/5

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

The description is a single, efficient sentence that front-loads the core action ('End a code generation session') and adds the secondary outcome ('generate the test file') without unnecessary words. Every part earns its place by clarifying the tool's purpose.

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

Completeness2/5

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

Given the complexity of ending a session and generating a test file, with no annotations and no output schema, the description is incomplete. It lacks details on what the tool returns (e.g., the generated test file content or confirmation), error conditions, or side effects, making it inadequate for an agent to fully understand the tool's context.

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

Parameters3/5

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

The input schema has 100% description coverage, with the single parameter 'sessionId' well-documented in the schema. The description does not add any meaning beyond what the schema provides, such as format examples or constraints, but the high schema coverage justifies a baseline score of 3.

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

Purpose4/5

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

The description clearly states the verb 'end' and resource 'code generation session' with the additional action 'generate the test file', making the purpose specific and actionable. It distinguishes from siblings like 'clear_codegen_session' (which likely clears without generating) and 'get_codegen_session' (which retrieves without ending), though it doesn't explicitly name these alternatives.

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

Usage Guidelines2/5

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

No guidance is provided on when to use this tool versus alternatives like 'clear_codegen_session' or 'start_codegen_session', nor does it mention prerequisites such as requiring an active session. The description implies usage after a session but lacks explicit context or exclusions.

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

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/devskido/customed-playwright'

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