Skip to main content
Glama
mohalmah

Google Apps Script MCP Server

by mohalmah

script_run

Execute Google Apps Script code by providing the script ID to automate tasks in Google Workspace applications.

Instructions

Run a Google Apps Script.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
scriptIdYesThe ID of the script to run.
fieldsNoSelector specifying which fields to include in a partial response.
altNoData format for response.
keyNoAPI key for the project.
access_tokenNoOAuth access token.
oauth_tokenNoOAuth 2.0 token for the current user.
quotaUserNoAvailable to use for quota purposes for server-side applications.
prettyPrintNoReturns response with indentations and line breaks.

Implementation Reference

  • Handler function that executes the 'script_run' tool by making an authenticated POST request to the Google Apps Script API endpoint `/v1/scripts/{scriptId}:run`.
    const executeFunction = async ({ scriptId, fields, alt = 'json', key, access_token, oauth_token, quotaUser, prettyPrint = true }) => {
      const baseUrl = 'https://script.googleapis.com';
      const url = new URL(`${baseUrl}/v1/scripts/${scriptId}:run`);
      
      // Append query parameters to the URL
      const params = new URLSearchParams({
        fields,
        alt,
        key,
        access_token,
        oauth_token,
        quotaUser,
        prettyPrint: prettyPrint.toString(),
        '$.xgafv': '1',
        upload_protocol: 'raw',
        uploadType: 'raw'
      });
      
      url.search = params.toString();
    
      try {
        // Get OAuth headers
        const headers = await getAuthHeaders();
        headers['Content-Type'] = 'application/json';
        // Perform the fetch request
        const response = await fetch(url.toString(), {
          method: 'POST',
          headers
        });
    
        // Check if the response was successful
        if (!response.ok) {
          const errorData = await response.json();
          throw new Error(errorData);
        }
    
        // Parse and return the response data
        const data = await response.json();
        return data;
      } catch (error) {
        const errorDetails = {
          message: error.message,
          stack: error.stack,
          scriptId,
          timestamp: new Date().toISOString(),
          errorType: error.name || 'Unknown'
        };
    
        logger.error('SCRIPT_RUN', 'Error running the script', errorDetails);
        
        console.error('❌ Error running the script:', errorDetails);
        
        // Return detailed error information for debugging
        return { 
          error: true,
          message: error.message,
          details: errorDetails,
          rawError: {
            name: error.name,
            stack: error.stack
          }
        };
      }
    };
  • Schema definition for the 'script_run' tool, specifying input parameters and required fields.
      type: 'function',
      function: {
        name: 'script_run',
        description: 'Run a Google Apps Script.',
        parameters: {
          type: 'object',
          properties: {
            scriptId: {
              type: 'string',
              description: 'The ID of the script to run.'
            },
            fields: {
              type: 'string',
              description: 'Selector specifying which fields to include in a partial response.'
            },
            alt: {
              type: 'string',
              enum: ['json', 'xml'],
              description: 'Data format for response.'
            },
            key: {
              type: 'string',
              description: 'API key for the project.'
            },
            access_token: {
              type: 'string',
              description: 'OAuth access token.'
            },
            oauth_token: {
              type: 'string',
              description: 'OAuth 2.0 token for the current user.'
            },
            quotaUser: {
              type: 'string',
              description: 'Available to use for quota purposes for server-side applications.'
            },
            prettyPrint: {
              type: 'boolean',
              description: 'Returns response with indentations and line breaks.'
            }
          },
          required: ['scriptId']
        }
      }
    }
  • lib/tools.js:8-64 (registration)
    Central tool registration via dynamic discovery of all `apiTool` exports from paths listed in tools/paths.js, including the 'script_run' tool.
    export async function discoverTools() {
      logger.info('DISCOVERY', `Starting tool discovery for ${toolPaths.length} tool paths`);
      
      const toolPromises = toolPaths.map(async (file) => {
        try {
          logger.debug('DISCOVERY', `Loading tool from: ${file}`);
          const module = await import(`../tools/${file}`);
          
          if (!module.apiTool) {
            logger.warn('DISCOVERY', `Tool file missing apiTool export: ${file}`);
            return null;
          }
    
          const toolName = module.apiTool.definition?.function?.name;
          if (!toolName) {
            logger.warn('DISCOVERY', `Tool missing function name: ${file}`);
            return null;
          }
    
          // Wrap the original function with logging
          const originalFunction = module.apiTool.function;
          const wrappedFunction = withLogging(toolName, originalFunction);
    
          logger.debug('DISCOVERY', `Successfully loaded tool: ${toolName}`, {
            file,
            toolName,
            description: module.apiTool.definition?.function?.description
          });
    
          return {
            ...module.apiTool,
            function: wrappedFunction,
            path: file,
          };
        } catch (error) {
          logger.error('DISCOVERY', `Failed to load tool: ${file}`, {
            file,
            error: {
              message: error.message,
              stack: error.stack
            }
          });
          return null;
        }
      });
      
      const tools = (await Promise.all(toolPromises)).filter(Boolean);
      
      logger.info('DISCOVERY', `Tool discovery completed`, {
        totalPaths: toolPaths.length,
        successfullyLoaded: tools.length,
        failed: toolPaths.length - tools.length,
        toolNames: tools.map(t => t.definition?.function?.name).filter(Boolean)
      });
      
      return tools;
    }
  • tools/paths.js:1-18 (registration)
    Explicit listing of tool paths for discovery, including 'google-app-script-api/apps-script-api/script-scripts-run.js' at line 10.
    export const toolPaths = [
      'google-app-script-api/apps-script-api/script-projects-deployments-delete.js',
      'google-app-script-api/apps-script-api/script-projects-create.js',
      'google-app-script-api/apps-script-api/script-projects-versions-create.js',
      'google-app-script-api/apps-script-api/script-projects-deployments-create.js',
      'google-app-script-api/apps-script-api/script-projects-deployments-update.js',
      'google-app-script-api/apps-script-api/script-projects-deployments-list.js',
      'google-app-script-api/apps-script-api/script-projects-update-content.js',
      'google-app-script-api/apps-script-api/script-projects-deployments-get.js',
      'google-app-script-api/apps-script-api/script-scripts-run.js',
      'google-app-script-api/apps-script-api/script-projects-get.js',
      'google-app-script-api/apps-script-api/script-processes-list-script-processes.js',
      'google-app-script-api/apps-script-api/script-projects-get-metrics.js',
      'google-app-script-api/apps-script-api/script-projects-get-content.js',
      'google-app-script-api/apps-script-api/script-projects-versions-list.js',
      'google-app-script-api/apps-script-api/script-projects-versions-get.js',
      'google-app-script-api/apps-script-api/script-processes-list.js'
    ];
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 but offers minimal information. It states the action ('Run') but doesn't describe what happens during execution (e.g., synchronous/asynchronous, side effects, error handling, permissions required, or rate limits). For a tool that likely performs mutations, this lack of detail is a significant gap.

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 with zero waste. It's front-loaded with the core action and resource, making it immediately clear. Every word earns its place, and there's no redundancy or unnecessary elaboration.

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 running a script (likely a mutation with side effects), no annotations, and no output schema, the description is incomplete. It doesn't explain what the tool returns, error conditions, execution context, or how it differs from sibling tools. For a tool with 8 parameters and significant potential impact, more context is needed to guide safe and effective use.

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 semantics beyond what the input schema provides. However, schema description coverage is 100%, with all 8 parameters well-documented in the schema (e.g., scriptId, fields, alt, key). This meets the baseline of 3, as the schema does the heavy lifting, but the description doesn't enhance understanding of how parameters interact or affect execution.

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 ('Run') and resource ('a Google Apps Script'), making the purpose immediately understandable. It distinguishes this execution tool from sibling tools that focus on metrics, processes, projects, deployments, versions, or content updates. However, it doesn't specify what 'run' entails (e.g., execution of a function, deployment, or script trigger).

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. The description doesn't mention prerequisites (e.g., needing a script ID from another tool), appropriate contexts (e.g., testing vs. production), or comparisons to siblings like 'script_projects_deployments_create' or 'update_script_content'. Usage is implied but not explicitly defined.

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/mohalmah/google-appscript-mcp-server'

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