Skip to main content
Glama
auto-browse

Unbundle OpenAPI Specs MCP

by auto-browse

split_openapi

Split large OpenAPI specifications into smaller, manageable files. Provide the input file path and output directory to organize and streamline API documentation.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
apiPathYesAbsolute path to the input OpenAPI definition file.
outputDirYesAbsolute path to the directory for split output files.

Implementation Reference

  • Handler function for 'split_openapi' tool that executes the Redocly CLI split command on the provided OpenAPI file path and outputs to the specified directory.
    async ({ apiPath, outputDir }, extra) => { // Arguments are the first parameter
        // Construct the command using npx to avoid global dependency issues
        // Quote paths to handle potential spaces
        const command = `npx @redocly/cli@latest split "${apiPath}" --outDir="${outputDir}"`;
        console.error(`Executing command: ${command}`); // Log the command being executed
    
        try
        {
            // Execute the command
            const { stdout, stderr } = await exec(command);
    
            // Log stdout/stderr for debugging
            if (stdout)
            {
                console.error("Command stdout:", stdout);
            }
            if (stderr)
            {
                console.error("Command stderr:", stderr);
            }
    
            // Redocly CLI often prints success messages to stdout
            // We'll return stdout as the primary result
            return {
                content: [{ type: "text", text: stdout || "Command executed successfully." }]
            };
    
        } catch (error: any)
        {
            console.error("Command execution failed:", error);
            // If the command fails, return the error message (often in stderr)
            const errorMessage = error.stderr || error.stdout || error.message || "Unknown error occurred";
            return {
                content: [{ type: "text", text: `Error: ${errorMessage}` }],
                isError: true
            };
        }
    }
  • Zod schema defining input arguments for the split_openapi tool: apiPath and outputDir.
    const SplitOpenApiArgsSchema = z.object({
        apiPath: z.string().describe("Absolute path to the input OpenAPI definition file."), // Changed description for consistency
        outputDir: z.string().describe("Absolute path to the directory for split output files.") // Changed description for consistency
        // Optional: Add other split options like 'separator' later if needed.
    });
  • src/index.ts:36-78 (registration)
    Registration of the 'split_openapi' tool using server.tool() with name, schema, and handler function.
    // Register the 'split_openapi' tool
    server.tool(
        "split_openapi", // Renamed tool
        SplitOpenApiArgsSchema.shape, // Use renamed schema variable
        async ({ apiPath, outputDir }, extra) => { // Arguments are the first parameter
            // Construct the command using npx to avoid global dependency issues
            // Quote paths to handle potential spaces
            const command = `npx @redocly/cli@latest split "${apiPath}" --outDir="${outputDir}"`;
            console.error(`Executing command: ${command}`); // Log the command being executed
    
            try
            {
                // Execute the command
                const { stdout, stderr } = await exec(command);
    
                // Log stdout/stderr for debugging
                if (stdout)
                {
                    console.error("Command stdout:", stdout);
                }
                if (stderr)
                {
                    console.error("Command stderr:", stderr);
                }
    
                // Redocly CLI often prints success messages to stdout
                // We'll return stdout as the primary result
                return {
                    content: [{ type: "text", text: stdout || "Command executed successfully." }]
                };
    
            } catch (error: any)
            {
                console.error("Command execution failed:", error);
                // If the command fails, return the error message (often in stderr)
                const errorMessage = error.stderr || error.stdout || error.message || "Unknown error occurred";
                return {
                    content: [{ type: "text", text: `Error: ${errorMessage}` }],
                    isError: true
                };
            }
        }
    );
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/auto-browse/unbundle_openapi_mcp'

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