Skip to main content
Glama
gologinapp

GoLogin MCP

Official
by gologinapp

post_workspaces

Create and customize workspaces for browser profiles, specifying OS and system details directly through GoLogin MCP. Simplify profile automation and configuration with tailored workspace setups.

Instructions

Create workspace

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
nameNoName of the workspace.
osNoGologin will create starting profiles with creating a workspace. If you want to create a workspace with a specific OS, you can specify it here.
osSpecNoHere you can specify OS specification. For example chip version for macos or version of windows.

Implementation Reference

  • Dynamic handler function that executes the 'post_workspaces' tool by proxying an HTTP POST request to the GoLogin API /workspaces endpoint, using parameters extracted from tool arguments and the loaded OpenAPI spec to determine path, method, and schema.
    private async callDynamicTool(
      toolName: string,
      parameters: CallParameters = {},
      headers: Record<string, string> = {}
    ): Promise<CallToolResult> {
      console.log('parameters', parameters.body);
      if (!this.apiSpec || !this.apiSpec.paths) {
        throw new Error('API specification not loaded');
      }
    
      let targetPath = '';
      let targetMethod = '';
      let operation: OpenAPIV3.OperationObject | undefined;
    
      for (const [path, pathItem] of Object.entries(this.apiSpec.paths)) {
        if (!pathItem) continue;
    
        for (const [method, op] of Object.entries(pathItem)) {
          if (['get', 'post', 'put', 'delete', 'patch', 'head', 'options'].includes(method) && op) {
            const opObj = op as OpenAPIV3.OperationObject;
            const generatedToolName = `${method}${path.replace('browser', 'profile').replace(/[^a-zA-Z0-9]/g, '_')}`;
    
            if (generatedToolName === toolName) {
              targetPath = path;
              targetMethod = method.toUpperCase();
              operation = opObj;
              break;
            }
          }
        }
        if (operation) break;
      }
    
    
      if (!operation) {
        throw new Error(`Tool "${toolName}" not found`);
      }
    
      let url = `${this.baseUrl}${targetPath}`;
      const requestHeaders: Record<string, string> = { ...headers };
      let requestBody: string | undefined;
    
      requestHeaders['User-Agent'] = 'gologin-mcp';
      console.error('this.token', this.token);
      if (this.token) {
        requestHeaders['Authorization'] = `Bearer ${this.token}`;
      }
    
      if (parameters.path) {
        for (const [key, value] of Object.entries(parameters.path)) {
          url = url.replace(`{${key}}`, encodeURIComponent(value));
        }
      }
    
      const queryParams = new URLSearchParams();
      if (parameters.query) {
        for (const [key, value] of Object.entries(parameters.query)) {
          if (value) {
            queryParams.append(key, value);
          }
        }
      }
    
      if (queryParams.toString()) {
        url += `?${queryParams.toString()}`;
      }
      if (parameters.body && ['POST', 'PUT', 'PATCH', 'DELETE'].includes(targetMethod)) {
        requestHeaders['Content-Type'] = 'application/json';
        requestBody = JSON.stringify(parameters.body);
      }
      console.log('requestBody', requestBody);
      try {
        const fetchOptions: RequestInit = {
          method: targetMethod,
          headers: requestHeaders,
        };
        console.error('fetchOptions', fetchOptions);
        if (requestBody) {
          fetchOptions.body = requestBody;
        }
        const response = await fetch(url, fetchOptions);
    
        const responseHeaders: Record<string, string> = {};
        response.headers.forEach((value, key) => {
          responseHeaders[key] = value;
        });
    
        let responseBody: any;
        const contentType = response.headers.get('content-type') || '';
    
    
        if (contentType.includes('application/json')) {
          try {
            responseBody = await response.json();
          } catch {
            responseBody = await response.text();
          }
        } else {
          responseBody = await response.text();
        }
        return {
          content: [
            {
              type: 'text',
              text: `API Call Result:\n` +
                `URL: ${url}\n` +
                `Method: ${targetMethod}\n` +
                `Status: ${response.status} ${response.statusText}\n\n` +
                `Response Headers:\n${JSON.stringify(responseHeaders, null, 2)}\n\n` +
                `Response Body:\n${typeof responseBody === 'object' ? JSON.stringify(responseBody, null, 2) : responseBody}`,
            },
          ],
        };
      } catch (error) {
        throw new Error(`API call failed: ${error instanceof Error ? error.message : String(error)}`);
      }
    }
  • src/index.ts:47-71 (registration)
    Dynamically registers the 'post_workspaces' tool in the MCP server by iterating over OpenAPI paths, generating tool name 'post_workspaces' for POST /workspaces, building input schema, and returning in list tools response.
    this.server.setRequestHandler(ListToolsRequestSchema, async () => {
      const tools: Tool[] = [];
      if (this.apiSpec && this.apiSpec.paths) {
        for (const [path, pathItem] of Object.entries(this.apiSpec.paths)) {
          if (!pathItem) continue;
    
          for (const [method, operation] of Object.entries(pathItem)) {
            if (['get', 'post', 'put', 'delete', 'patch', 'head', 'options'].includes(method) && operation) {
              const op = operation as OpenAPIV3.OperationObject;
              const toolName = `${method}${path.replace('browser', 'profile').replace(/[^a-zA-Z0-9]/g, '_')}`;
    
              const inputSchema = this.buildInputSchema(op, path);
    
              tools.push({
                name: toolName,
                description: op.summary || op.description || `${method.toUpperCase()} ${path}`,
                inputSchema,
              });
            }
          }
        }
      }
    
      return { tools };
    });
  • Builds the input schema for 'post_workspaces' tool from the OpenAPI specification's POST /workspaces operation, combining path params, query params, and request body schema.
    private buildInputSchema(operation: OpenAPIV3.OperationObject, path: string): any {
      const properties: any = {};
      const required: string[] = [];
    
      const pathParams = this.extractPathParameters(operation, path);
      const queryParams = this.extractQueryParameters(operation);
      const bodySchema = this.extractRequestBodySchema(operation);
    
      if (pathParams.properties && Object.keys(pathParams.properties).length > 0) {
        for (const [key, prop] of Object.entries(pathParams.properties)) {
          properties[key] = this.convertOpenAPISchemaToJsonSchema(prop as OpenAPIV3.SchemaObject | OpenAPIV3.ReferenceObject);
          if (pathParams.required.includes(key)) {
            required.push(key);
          }
        }
      }
    
      if (queryParams.properties && Object.keys(queryParams.properties).length > 0) {
        for (const [key, prop] of Object.entries(queryParams.properties)) {
          properties[key] = this.convertOpenAPISchemaToJsonSchema(prop as OpenAPIV3.SchemaObject | OpenAPIV3.ReferenceObject);
          if (queryParams.required.includes(key)) {
            required.push(key);
          }
        }
      }
    
      if (bodySchema && bodySchema.properties) {
        for (const [key, prop] of Object.entries(bodySchema.properties)) {
          properties[key] = this.convertOpenAPISchemaToJsonSchema(prop as OpenAPIV3.SchemaObject | OpenAPIV3.ReferenceObject);
          if (bodySchema.required && bodySchema.required.includes(key)) {
            required.push(key);
          }
        }
      }
    
      const schema: any = {
        type: 'object',
        properties,
      };
    
      if (required.length > 0) {
        schema.required = required;
      }
    
      return schema;
    }
  • Generates the exact tool name 'post_workspaces' from OpenAPI path '/workspaces' and POST method, replaces 'browser' with 'profile', normalizes to alphanumeric with underscores.
    const toolName = `${method}${path.replace('browser', 'profile').replace(/[^a-zA-Z0-9]/g, '_')}`;
    
    const inputSchema = this.buildInputSchema(op, path);
    
    tools.push({
      name: toolName,
      description: op.summary || op.description || `${method.toUpperCase()} ${path}`,
      inputSchema,
    });
  • Helper that extracts and categorizes input arguments for 'post_workspaces' into path, query, and body parameters by matching toolName to OpenAPI paths and parameters.
    private extractParametersFromArgs(toolName: string, args: Record<string, any>): CallParameters {
      if (!this.apiSpec || !this.apiSpec.paths) {
        return { body: args };
      }
    
      let operation: OpenAPIV3.OperationObject | undefined;
      let path = '';
    
      for (const [apiPath, pathItem] of Object.entries(this.apiSpec.paths)) {
        if (!pathItem) continue;
    
        for (const [method, op] of Object.entries(pathItem)) {
          if (['get', 'post', 'put', 'delete', 'patch', 'head', 'options'].includes(method) && op) {
            const opObj = op as OpenAPIV3.OperationObject;
            const generatedToolName = opObj.operationId || `${method}_${apiPath.replace(/[^a-zA-Z0-9]/g, '_')}`;
    
            if (generatedToolName === toolName) {
              operation = opObj;
              path = apiPath;
              break;
            }
          }
        }
        if (operation) break;
      }
    
      if (!operation) {
        return { body: args };
      }
    
      const pathParams: Record<string, string> = {};
      const queryParams: Record<string, string> = {};
      const bodyParams: any = {};
    
      const pathParamNames = path.match(/\{([^}]+)\}/g)?.map(p => p.slice(1, -1)) || [];
    
      if (operation.parameters) {
        operation.parameters.forEach(param => {
          if ('$ref' in param) return;
    
          const parameter = param as OpenAPIV3.ParameterObject;
          const paramName = parameter.name;
    
          if (parameter.in === 'path' && args[paramName] !== undefined) {
            pathParams[paramName] = String(args[paramName]);
          } else if (parameter.in === 'query' && args[paramName] !== undefined) {
            queryParams[paramName] = String(args[paramName]);
          }
        });
      }
    
      pathParamNames.forEach(paramName => {
        if (args[paramName] !== undefined && !pathParams[paramName]) {
          pathParams[paramName] = String(args[paramName]);
        }
      });
    
      const usedParams = new Set([...Object.keys(pathParams), ...Object.keys(queryParams)]);
      for (const [key, value] of Object.entries(args)) {
        if (!usedParams.has(key)) {
          bodyParams[key] = value;
        }
      }
    
      const parameters: CallParameters = {};
    
      if (Object.keys(pathParams).length > 0) {
        parameters.path = pathParams;
      }
    
      if (Object.keys(queryParams).length > 0) {
        parameters.query = queryParams;
      }
    
      if (Object.keys(bodyParams).length > 0) {
        parameters.body = bodyParams;
      }
    
      return parameters;
    }
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. While 'Create workspace' implies a write/mutation operation, the description doesn't disclose permissions required, whether this is idempotent, what happens on failure, rate limits, or what the response contains. For a mutation tool with zero annotation coverage, this is insufficient.

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 maximally concise with just two words that directly state the tool's purpose. There's zero wasted language, and the information is front-loaded appropriately for such a simple description.

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?

For a mutation tool with no annotations and no output schema, the description is incomplete. It doesn't explain what a 'workspace' represents in this system, what happens after creation, whether there are limitations or quotas, or what the response contains. The combination of mutation operation + zero annotation coverage requires more descriptive context than provided.

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 description adds no parameter information beyond what's already in the schema (which has 100% coverage). The schema already documents all three parameters with descriptions and enum values. The baseline score of 3 reflects that the schema does the heavy lifting, but the description adds no additional semantic context about parameter usage or relationships.

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 action ('Create') and resource ('workspace'), providing specific verb+resource pairing. However, it doesn't differentiate this tool from sibling tools like 'post_workspaces__wid__members' or 'post_workspaces__wid__profiles_transfer', which also create workspace-related resources but with different scopes.

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?

The description provides no guidance on when to use this tool versus alternatives. There's no mention of prerequisites, when this tool is appropriate versus other creation tools in the sibling list, or any contextual constraints for workspace creation.

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/gologinapp/gologin-mcp'

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