Skip to main content
Glama
simonl77

Salesforce MCP Server

by simonl77

salesforce_query_records

Query Salesforce records using SOQL to retrieve data from any object, including parent-child relationships and related object filtering.

Instructions

Query records from any Salesforce object using SOQL, including relationship queries.

NOTE: For queries with GROUP BY, aggregate functions (COUNT, SUM, AVG, etc.), or HAVING clauses, use salesforce_aggregate_query instead.

Examples:

  1. Parent-to-child query (e.g., Account with Contacts):

    • objectName: "Account"

    • fields: ["Name", "(SELECT Id, FirstName, LastName FROM Contacts)"]

  2. Child-to-parent query (e.g., Contact with Account details):

    • objectName: "Contact"

    • fields: ["FirstName", "LastName", "Account.Name", "Account.Industry"]

  3. Multiple level query (e.g., Contact -> Account -> Owner):

    • objectName: "Contact"

    • fields: ["Name", "Account.Name", "Account.Owner.Name"]

  4. Related object filtering:

    • objectName: "Contact"

    • fields: ["Name", "Account.Name"]

    • whereClause: "Account.Industry = 'Technology'"

Note: When using relationship fields:

  • Use dot notation for parent relationships (e.g., "Account.Name")

  • Use subqueries in parentheses for child relationships (e.g., "(SELECT Id FROM Contacts)")

  • Custom relationship fields end in "__r" (e.g., "CustomObject__r.Name")

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
objectNameYesAPI name of the object to query
fieldsYesList of fields to retrieve, including relationship fields
whereClauseNoWHERE clause, can include conditions on related objects
orderByNoORDER BY clause, can include fields from related objects
limitNoMaximum number of records to return

Implementation Reference

  • Main handler function that executes the SOQL query, validates relationship fields, formats results, and handles errors.
    export async function handleQueryRecords(conn: any, args: QueryArgs) {
      const { objectName, fields, whereClause, orderBy, limit } = args;
    
      try {
        // Validate relationship field syntax
        const validation = validateRelationshipFields(fields);
        if (!validation.isValid) {
          return {
            content: [{
              type: "text",
              text: validation.error!
            }],
            isError: true,
          };
        }
    
        // Construct SOQL query
        let soql = `SELECT ${fields.join(', ')} FROM ${objectName}`;
        if (whereClause) soql += ` WHERE ${whereClause}`;
        if (orderBy) soql += ` ORDER BY ${orderBy}`;
        if (limit) soql += ` LIMIT ${limit}`;
    
        const result = await conn.query(soql);
        
        // Format the output
        const formattedRecords = result.records.map((record: any, index: number) => {
          const recordStr = fields.map(field => {
            // Handle special case for subqueries (child relationships)
            if (field.startsWith('(SELECT')) {
              const relationshipName = field.match(/FROM\s+(\w+)/)?.[1];
              if (!relationshipName) return `    ${field}: Invalid subquery format`;
              const childRecords = record[relationshipName];
              return `    ${relationshipName}: [${childRecords?.length || 0} records]`;
            }
            return '    ' + formatRelationshipResults(record, field);
          }).join('\n');
          return `Record ${index + 1}:\n${recordStr}`;
        }).join('\n\n');
    
        return {
          content: [{
            type: "text",
            text: `Query returned ${result.records.length} records:\n\n${formattedRecords}`
          }],
          isError: false,
        };
      } catch (error) {
        // Enhanced error handling for relationship queries
        const errorMessage = error instanceof Error ? error.message : String(error);
        let enhancedError = errorMessage;
    
        if (errorMessage.includes('INVALID_FIELD')) {
          // Try to identify which relationship field caused the error
          const fieldMatch = errorMessage.match(/(?:No such column |Invalid field: )['"]?([^'")\s]+)/);
          if (fieldMatch) {
            const invalidField = fieldMatch[1];
            if (invalidField.includes('.')) {
              enhancedError = `Invalid relationship field "${invalidField}". Please check:\n` +
                `1. The relationship name is correct\n` +
                `2. The field exists on the related object\n` +
                `3. You have access to the field\n` +
                `4. For custom relationships, ensure you're using '__r' suffix`;
            }
          }
        }
    
        return {
          content: [{
            type: "text",
            text: `Error executing query: ${enhancedError}`
          }],
          isError: true,
        };
      }
    }
  • Tool schema definition including name, description, and input schema for parameters like objectName, fields, whereClause, etc.
    export const QUERY_RECORDS: Tool = {
      name: "salesforce_query_records",
      description: `Query records from any Salesforce object using SOQL, including relationship queries.
    
    NOTE: For queries with GROUP BY, aggregate functions (COUNT, SUM, AVG, etc.), or HAVING clauses, use salesforce_aggregate_query instead.
    
    Examples:
    1. Parent-to-child query (e.g., Account with Contacts):
       - objectName: "Account"
       - fields: ["Name", "(SELECT Id, FirstName, LastName FROM Contacts)"]
    
    2. Child-to-parent query (e.g., Contact with Account details):
       - objectName: "Contact"
       - fields: ["FirstName", "LastName", "Account.Name", "Account.Industry"]
    
    3. Multiple level query (e.g., Contact -> Account -> Owner):
       - objectName: "Contact"
       - fields: ["Name", "Account.Name", "Account.Owner.Name"]
    
    4. Related object filtering:
       - objectName: "Contact"
       - fields: ["Name", "Account.Name"]
       - whereClause: "Account.Industry = 'Technology'"
    
    Note: When using relationship fields:
    - Use dot notation for parent relationships (e.g., "Account.Name")
    - Use subqueries in parentheses for child relationships (e.g., "(SELECT Id FROM Contacts)")
    - Custom relationship fields end in "__r" (e.g., "CustomObject__r.Name")`,
      inputSchema: {
        type: "object",
        properties: {
          objectName: {
            type: "string",
            description: "API name of the object to query"
          },
          fields: {
            type: "array",
            items: { type: "string" },
            description: "List of fields to retrieve, including relationship fields"
          },
          whereClause: {
            type: "string",
            description: "WHERE clause, can include conditions on related objects",
            optional: true
          },
          orderBy: {
            type: "string",
            description: "ORDER BY clause, can include fields from related objects",
            optional: true
          },
          limit: {
            type: "number",
            description: "Maximum number of records to return",
            optional: true
          }
        },
        required: ["objectName", "fields"]
      }
    };
  • src/index.ts:85-99 (registration)
    Dispatch handler in the main switch statement that validates arguments and calls the query handler function.
    case "salesforce_query_records": {
      const queryArgs = args as Record<string, unknown>;
      if (!queryArgs.objectName || !Array.isArray(queryArgs.fields)) {
        throw new Error('objectName and fields array are required for query');
      }
      // Type check and conversion
      const validatedArgs: QueryArgs = {
        objectName: queryArgs.objectName as string,
        fields: queryArgs.fields as string[],
        whereClause: queryArgs.whereClause as string | undefined,
        orderBy: queryArgs.orderBy as string | undefined,
        limit: queryArgs.limit as number | undefined
      };
      return await handleQueryRecords(conn, validatedArgs);
    }
  • src/index.ts:46-49 (registration)
    Tool registration in the ListToolsRequestSchema handler, including QUERY_RECORDS in the tools array.
    tools: [
      SEARCH_OBJECTS, 
      DESCRIBE_OBJECT, 
      QUERY_RECORDS, 
  • Helper function to validate relationship field syntax in SOQL queries.
    function validateRelationshipFields(fields: string[]): { isValid: boolean; error?: string } {
      for (const field of fields) {
        // Check for parent relationship syntax (dot notation)
        if (field.includes('.')) {
          const parts = field.split('.');
          // Check for empty parts
          if (parts.some(part => !part)) {
            return {
              isValid: false,
              error: `Invalid relationship field format: "${field}". Relationship fields should use proper dot notation (e.g., "Account.Name")`
            };
          }
          // Check for too many levels (Salesforce typically limits to 5)
          if (parts.length > 5) {
            return {
              isValid: false,
              error: `Relationship field "${field}" exceeds maximum depth of 5 levels`
            };
          }
        }
    
        // Check for child relationship syntax (subqueries)
        if (field.includes('SELECT') && !field.match(/^\(SELECT.*FROM.*\)$/)) {
          return {
            isValid: false,
            error: `Invalid subquery format: "${field}". Child relationship queries should be wrapped in parentheses`
          };
        }
      }
    
      return { isValid: true };
    }

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.5/5.0
Behavior3/5

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

No annotations are provided, so the description carries the burden of behavioral transparency. It does disclose relationship query nuances (dot notation, subqueries, __r suffixes) but does not explicitly state whether the operation is read-only, what permissions are needed, or any limits/timeout behavior. 'Query' implies a read, but not all behavioral traits are covered.

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 long but every section earns its place: a clear purpose sentence, a critical exclusion note, four varied examples, and a concise summary of relationship field rules. The structure front-loads the main idea and then layers detail logically. Nothing is redundant or filler.

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

Completeness4/5

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

For a moderately complex tool with no output schema and no annotations, the description covers essential query construction, relationship semantics, and aggregate query alternatives. It does not explicitly describe the shape of the returned records, but that is generally implicit for a query tool. The examples and notes provide enough context to use the tool correctly.

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

Parameters5/5

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

While schema coverage is 100% (baseline 3), the description adds substantial meaning beyond schema property descriptions. It provides detailed multi-level query examples for fields, explains how to construct relationship queries in whereClause, and introduces conventions like dot notation and subqueries that are not captured in the schema. This is exceptional parameter-level guidance.

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 opens with a specific verb-resource-scope statement: 'Query records from any Salesforce object using SOQL, including relationship queries.' It clearly distinguishes itself from sibling salesforce_aggregate_query by explicitly naming the alternative for aggregate queries, and from other tools like describe or search.

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

Usage Guidelines5/5

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

The description explicitly states when NOT to use this tool: 'For queries with GROUP BY, aggregate functions (COUNT, SUM, AVG, etc.), or HAVING clauses, use salesforce_aggregate_query instead.' This directly guides tool selection among siblings. Examples also clarify use cases for parent-child and child-parent queries.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.