Skip to main content
Glama
usama-dtc

Salesforce MCP Server

by usama-dtc

salesforce_manage_object

Create or modify custom Salesforce objects to extend CRM functionality. Define fields, relationships, and sharing settings for new or existing objects.

Instructions

Create new custom objects or modify existing ones in Salesforce:

  • Create: New custom objects with fields, relationships, and settings

  • Update: Modify existing object settings, labels, sharing model Examples: Create Customer_Feedback__c object, Update object sharing settings Note: Changes affect metadata and require proper permissions

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
operationYesWhether to create new object or update existing
objectNameYesAPI name for the object (without __c suffix)
labelNoLabel for the object
pluralLabelNoPlural label for the object
descriptionNoDescription of the object
nameFieldLabelNoLabel for the name field
nameFieldTypeNoType of the name field
nameFieldFormatNoDisplay format for AutoNumber field (e.g., 'A-{0000}')
sharingModelNoSharing model for the object

Implementation Reference

  • The `handleManageObject` function implements the core logic for creating or updating Salesforce custom objects. It uses the Salesforce Metadata API to deploy changes, handles validation, prepares metadata, and returns success/error responses.
    export async function handleManageObject(conn: any, args: ManageObjectArgs) {
      const { operation, objectName, label, pluralLabel, description, nameFieldLabel, nameFieldType, nameFieldFormat, sharingModel } = args;
    
      try {
        if (operation === 'create') {
          if (!label || !pluralLabel) {
            throw new Error('Label and pluralLabel are required for object creation');
          }
    
          // Prepare metadata for the new object
          const metadata = {
            fullName: `${objectName}__c`,
            label,
            pluralLabel,
            nameField: {
              label: nameFieldLabel || `${label} Name`,
              type: nameFieldType || 'Text',
              ...(nameFieldType === 'AutoNumber' && nameFieldFormat ? { displayFormat: nameFieldFormat } : {})
            },
            deploymentStatus: 'Deployed',
            sharingModel: sharingModel || 'ReadWrite'
          } as MetadataInfo;
    
          if (description) {
            metadata.description = description;
          }
    
          // Create the object using Metadata API
          const result = await conn.metadata.create('CustomObject', metadata);
    
          if (result && (Array.isArray(result) ? result[0].success : result.success)) {
            return {
              content: [{
                type: "text",
                text: `Successfully created custom object ${objectName}__c`
              }],
              isError: false,
            };
          }
        } else {
          // For update, first get existing metadata
          const existingMetadata = await conn.metadata.read('CustomObject', [`${objectName}__c`]);
          const currentMetadata = Array.isArray(existingMetadata) ? existingMetadata[0] : existingMetadata;
    
          if (!currentMetadata) {
            throw new Error(`Object ${objectName}__c not found`);
          }
    
          // Prepare update metadata
          const metadata = {
            ...currentMetadata,
            label: label || currentMetadata.label,
            pluralLabel: pluralLabel || currentMetadata.pluralLabel,
            description: description !== undefined ? description : currentMetadata.description,
            sharingModel: sharingModel || currentMetadata.sharingModel
          } as MetadataInfo;
    
          // Update the object using Metadata API
          const result = await conn.metadata.update('CustomObject', metadata);
    
          if (result && (Array.isArray(result) ? result[0].success : result.success)) {
            return {
              content: [{
                type: "text",
                text: `Successfully updated custom object ${objectName}__c`
              }],
              isError: false,
            };
          }
        }
    
        return {
          content: [{
            type: "text",
            text: `Failed to ${operation} custom object ${objectName}__c`
          }],
          isError: true,
        };
    
      } catch (error) {
        return {
          content: [{
            type: "text",
            text: `Error ${operation === 'create' ? 'creating' : 'updating'} custom object: ${error instanceof Error ? error.message : String(error)}`
          }],
          isError: true,
        };
      }
    }
  • The `MANAGE_OBJECT` Tool definition provides the name, description, and detailed inputSchema for parameter validation. The `ManageObjectArgs` TypeScript interface reinforces the expected input types.
    export const MANAGE_OBJECT: Tool = {
      name: "salesforce_manage_object",
      description: `Create new custom objects or modify existing ones in Salesforce:
      - Create: New custom objects with fields, relationships, and settings
      - Update: Modify existing object settings, labels, sharing model
      Examples: Create Customer_Feedback__c object, Update object sharing settings
      Note: Changes affect metadata and require proper permissions`,
      inputSchema: {
        type: "object",
        properties: {
          operation: {
            type: "string",
            enum: ["create", "update"],
            description: "Whether to create new object or update existing"
          },
          objectName: {
            type: "string",
            description: "API name for the object (without __c suffix)"
          },
          label: {
            type: "string",
            description: "Label for the object"
          },
          pluralLabel: {
            type: "string",
            description: "Plural label for the object"
          },
          description: {
            type: "string",
            description: "Description of the object",
            optional: true
          },
          nameFieldLabel: {
            type: "string",
            description: "Label for the name field",
            optional: true
          },
          nameFieldType: {
            type: "string",
            enum: ["Text", "AutoNumber"],
            description: "Type of the name field",
            optional: true
          },
          nameFieldFormat: {
            type: "string",
            description: "Display format for AutoNumber field (e.g., 'A-{0000}')",
            optional: true
          },
          sharingModel: {
            type: "string",
            enum: ["ReadWrite", "Read", "Private", "ControlledByParent"],
            description: "Sharing model for the object",
            optional: true
          }
        },
        required: ["operation", "objectName"]
      }
    };
    
    export interface ManageObjectArgs {
      operation: 'create' | 'update';
      objectName: string;
      label?: string;
      pluralLabel?: string;
      description?: string;
      nameFieldLabel?: string;
      nameFieldType?: 'Text' | 'AutoNumber';
      nameFieldFormat?: string;
      sharingModel?: 'ReadWrite' | 'Read' | 'Private' | 'ControlledByParent';
    }
  • src/index.ts:36-47 (registration)
    Registration of the tool in the MCP server's listTools handler, making it discoverable by clients.
    server.setRequestHandler(ListToolsRequestSchema, async () => ({
      tools: [
        SEARCH_OBJECTS, 
        DESCRIBE_OBJECT, 
        QUERY_RECORDS, 
        DML_RECORDS,
        MANAGE_OBJECT,
        MANAGE_FIELD,
        SEARCH_ALL,
        UPLOAD_REPORT_XML  // Add new tool to the list
      ],
    }));
  • src/index.ts:99-116 (registration)
    Dispatch registration in the main CallToolRequestSchema switch statement, which validates arguments and invokes the handleManageObject handler.
    case "salesforce_manage_object": {
      const objectArgs = args as Record<string, unknown>;
      if (!objectArgs.operation || !objectArgs.objectName) {
        throw new Error('operation and objectName are required for object management');
      }
      const validatedArgs: ManageObjectArgs = {
        operation: objectArgs.operation as 'create' | 'update',
        objectName: objectArgs.objectName as string,
        label: objectArgs.label as string | undefined,
        pluralLabel: objectArgs.pluralLabel as string | undefined,
        description: objectArgs.description as string | undefined,
        nameFieldLabel: objectArgs.nameFieldLabel as string | undefined,
        nameFieldType: objectArgs.nameFieldType as 'Text' | 'AutoNumber' | undefined,
        nameFieldFormat: objectArgs.nameFieldFormat as string | undefined,
        sharingModel: objectArgs.sharingModel as 'ReadWrite' | 'Read' | 'Private' | 'ControlledByParent' | undefined
      };
      return await handleManageObject(conn, validatedArgs);
    }
Behavior3/5

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

With no annotations provided, the description carries full burden. It discloses important behavioral traits: 'Changes affect metadata' (not data), 'require proper permissions', and the dual create/update capability. However, it doesn't mention potential side effects, error conditions, or what happens during updates to existing objects (e.g., whether changes are reversible).

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

Conciseness4/5

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

The description is well-structured with a clear opening statement, bullet points for operations, examples, and a note about permissions. It's appropriately sized for a complex tool, though the bullet formatting could be more concise. Every sentence adds value, with no redundant information.

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

Completeness3/5

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

For a complex metadata mutation tool with 9 parameters and no annotations or output schema, the description provides adequate but incomplete coverage. It explains the core operations and permission requirements but lacks details about return values, error handling, and the full scope of what can be modified. The examples help but don't substitute for comprehensive behavioral documentation.

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?

Schema description coverage is 100%, so the schema already documents all 9 parameters thoroughly. The description adds minimal value beyond what's in the schema - it mentions 'fields, relationships, and settings' for create operations and 'settings, labels, sharing model' for updates, but doesn't provide additional semantic context beyond the parameter descriptions.

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

Purpose5/5

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

The description clearly states the tool's purpose with specific verbs ('Create new custom objects or modify existing ones') and resources ('in Salesforce'), distinguishing it from siblings like salesforce_describe_object (read-only) and salesforce_manage_field (field-level operations). It explicitly covers both create and update operations.

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

Usage Guidelines4/5

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

The description provides clear context for when to use this tool ('Create new custom objects or modify existing ones') and mentions permission requirements, but doesn't explicitly contrast with alternatives like salesforce_manage_field for field-level changes or salesforce_dml_records for data operations. The examples help but don't establish explicit boundaries.

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/usama-dtc/salesforce_mcp'

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