@tsmztech/mcp-server-salesforce

Q: What can @tsmztech/mcp-server-salesforce do?

salesforce record crud operations via mcp protocol, salesforce soql query execution with result streaming, salesforce object metadata introspection and schema discovery, salesforce authentication and session management via mcp, salesforce batch record operations with error handling, salesforce relationship traversal and record linking, salesforce field validation and constraint enforcement

MCP ServerFree

A Salesforce connector MCP Server.

Open Source

/ 100

7 capabilities2 data sources

Capabilities7 decomposed

salesforce record crud operations via mcp protocol

Medium confidence

Exposes Salesforce object create, read, update, and delete operations through the Model Context Protocol (MCP) as callable tools. Implements MCP's tool schema interface to translate Claude function calls into Salesforce REST API requests, handling authentication via OAuth 2.0 or session tokens and marshaling responses back as structured JSON for LLM consumption.

Solves for

I want Claude to create or update Salesforce records (accounts, contacts, opportunities) without leaving the conversationI need to query Salesforce data and have Claude analyze or summarize the results in real-timeI want to build an AI agent that can autonomously manage Salesforce records based on business logic

Best for

Teams building AI agents that need Salesforce integration without custom API wrappers

Salesforce admins automating record management through Claude conversations

Developers prototyping Salesforce-connected AI workflows

Requires

Salesforce org with API access enabled

Valid OAuth 2.0 credentials or session token for Salesforce

Node.js 16+ runtime

Limitations

No built-in transaction support — multi-step operations are not atomic; partial failures require manual rollback

Rate limiting depends on Salesforce org limits; no client-side throttling or backoff strategy documented

Batch operations not explicitly supported — each record operation is a separate API call, causing N+1 performance issues at scale

What makes it unique

Implements MCP's tool schema protocol specifically for Salesforce, allowing Claude to natively call Salesforce operations without intermediate API gateway or custom function definitions — the MCP server acts as a direct bridge translating Claude's tool calls into Salesforce REST API requests with automatic authentication handling.

vs alternatives

Tighter integration than generic REST API wrappers because it uses MCP's native tool protocol, eliminating the need for developers to manually define function schemas or manage authentication state in their Claude prompts.

salesforce soql query execution with result streaming

Medium confidence

Executes Salesforce Object Query Language (SOQL) queries through the MCP interface and returns paginated or streamed result sets. The server parses SOQL syntax, validates against Salesforce object metadata, and streams large result sets back to Claude in chunks to avoid context window overflow, with automatic handling of Salesforce's 2000-record query result limits.

Solves for

I want Claude to run a SOQL query and analyze the results without me manually exporting dataI need to find specific Salesforce records based on complex criteria and have Claude summarize findingsI want to build a search agent that queries Salesforce and returns relevant records to users

Best for

Salesforce analysts building AI-powered reporting and search tools

Teams needing ad-hoc Salesforce queries without writing custom reports

Developers building conversational Salesforce data exploration interfaces

Requires

Salesforce org with API access and query permissions

Valid authentication token with query permissions on target objects

Node.js 16+

Limitations

SOQL syntax validation is limited — complex joins or subqueries may fail silently if not properly formatted

No query optimization — inefficient SOQL (e.g., queries without WHERE clauses) can timeout on large orgs

Pagination is manual — Claude must explicitly request next pages; no automatic result aggregation across pages

What makes it unique

Integrates SOQL query execution directly into MCP's tool interface, allowing Claude to construct and execute queries conversationally without leaving the chat context, with built-in pagination handling to work within Claude's context window constraints.

vs alternatives

More natural than exporting Salesforce reports or using REST API explorers because Claude can iteratively refine queries based on results, and the MCP protocol ensures queries are executed with the authenticated user's permissions automatically.

salesforce object metadata introspection and schema discovery

Medium confidence

Provides Claude with real-time access to Salesforce object schemas, field definitions, relationships, and picklist values through MCP tools. The server queries Salesforce's Describe API endpoints to fetch metadata about available objects, their fields (type, length, required status), and valid field values, enabling Claude to construct valid SOQL queries and CRUD operations without hardcoding field names.

Solves for

I want Claude to know what fields exist on a Salesforce object before constructing a queryI need Claude to suggest valid picklist values when updating a Salesforce recordI want to explore Salesforce schema interactively and have Claude explain object relationships

Best for

Salesforce developers building AI-assisted schema exploration tools

Teams onboarding new Salesforce orgs and needing AI-guided schema documentation

Builders creating intelligent Salesforce form builders or query assistants

Requires

Salesforce org with Metadata API or Describe API access

Valid authentication token with metadata read permissions

Node.js 16+

Limitations

Metadata caching is not documented — repeated schema queries may incur repeated Salesforce API calls, impacting rate limits

Custom objects and fields are supported but custom metadata types are not explicitly documented

Relationship metadata (lookup, master-detail) is returned but traversal across relationships is not automated

What makes it unique

Exposes Salesforce's Describe API as MCP tools, allowing Claude to dynamically discover and reason about object schemas in real-time rather than relying on static documentation or pre-configured field mappings, enabling adaptive query and form generation.

vs alternatives

More flexible than static schema documentation because Claude can query metadata on-demand and adapt its behavior based on actual org configuration, and more reliable than hardcoded field lists because it reflects the current state of the Salesforce org.

salesforce authentication and session management via mcp

Medium confidence

Manages OAuth 2.0 authentication flows and session token lifecycle for Salesforce API access. The MCP server handles credential storage, token refresh, and session validation, abstracting authentication complexity from Claude so that tool calls are automatically authenticated without requiring Claude to manage tokens or credentials directly.

Solves for

I want Claude to access Salesforce without me manually managing API tokens in the conversationI need secure credential handling so API keys are never exposed to Claude or the userI want to set up once and have Claude automatically re-authenticate if tokens expire

Best for

Teams deploying MCP servers in production and needing secure credential management

Salesforce admins setting up Claude integration without exposing API keys

Developers building multi-user Salesforce AI agents with per-user authentication

Requires

Salesforce OAuth 2.0 app configured with client ID and client secret

Valid Salesforce user account with API permissions

Node.js 16+

Limitations

Credential storage mechanism is not documented — unclear if tokens are stored in memory, environment variables, or encrypted files

No built-in support for multiple Salesforce orgs — appears to support single org per MCP server instance

Token refresh logic is not explicitly documented — unclear if refresh tokens are stored or if re-authentication is required

What makes it unique

Encapsulates Salesforce OAuth 2.0 handling within the MCP server itself, so Claude never sees or manages credentials — authentication is transparent to the LLM, reducing security surface area compared to passing tokens through prompts or function parameters.

vs alternatives

More secure than embedding API keys in prompts or requiring Claude to manage tokens because credentials are server-side only, and more user-friendly than manual token refresh because the MCP server handles token lifecycle automatically.

salesforce batch record operations with error handling

Medium confidence

Supports bulk create, update, or delete operations on multiple Salesforce records in a single MCP tool call. The server batches requests using Salesforce's Composite API or Bulk API, handles partial failures gracefully by returning per-record success/failure status, and provides detailed error messages for failed records without rolling back successful operations.

Solves for

I want Claude to update 100 accounts at once instead of making 100 separate API callsI need to bulk import contacts from a CSV and have Claude handle failures gracefullyI want to delete multiple records based on criteria without individual delete calls

Best for

Teams performing bulk data migrations or imports through Claude

Salesforce admins automating large-scale record updates

Developers building batch processing workflows in AI agents

Requires

Salesforce org with Composite API or Bulk API access

Valid authentication token with create/update/delete permissions on target objects

Node.js 16+

Limitations

Batch size limits are not documented — unclear if there are hard limits on records per batch or if Salesforce's 25MB payload limit applies

No automatic retry logic for transient failures — failed records are reported but not automatically retried

Partial failure handling requires manual inspection of per-record error responses — no built-in rollback or compensation logic

What makes it unique

Implements Salesforce Composite or Bulk API batching within MCP tools, allowing Claude to perform bulk operations in a single tool call rather than looping through individual CRUD operations, with per-record error reporting to enable intelligent error recovery.

vs alternatives

More efficient than individual record operations because it reduces API call overhead and network latency, and more resilient than naive batch loops because it provides granular error reporting per record without requiring Claude to implement retry logic.

salesforce relationship traversal and record linking

Medium confidence

Enables Claude to navigate Salesforce object relationships (lookups, master-detail, many-to-many) by following foreign key references and retrieving related records. The server resolves relationship metadata to construct efficient SOQL queries with JOINs, allowing Claude to fetch parent/child records and traverse relationship chains without manually constructing complex queries.

Solves for

I want Claude to fetch an account and all its related contacts in one operationI need to find all opportunities for a specific account and analyze their pipelineI want to traverse a chain of relationships (Account -> Contacts -> Cases) to build a complete view

Best for

Salesforce analysts building AI-powered relationship exploration tools

Teams needing to understand Salesforce data relationships without writing complex SOQL

Developers building knowledge graph or entity relationship visualizations

Requires

Salesforce org with relationship metadata available

Valid authentication token with read permissions on related objects

Node.js 16+

Limitations

Relationship traversal depth is not documented — unclear if there are limits on how many levels deep Claude can traverse

Circular relationship handling is not documented — could cause infinite loops if relationships form cycles

Many-to-many relationships through junction objects may not be fully supported — documentation is unclear

What makes it unique

Abstracts Salesforce relationship navigation into high-level MCP tools that Claude can call without understanding SOQL JOIN syntax or relationship cardinality, automatically constructing efficient queries based on metadata.

vs alternatives

More intuitive than writing SOQL JOINs because Claude can express relationships in natural language, and more efficient than fetching records individually because the server constructs optimized queries with proper JOINs.

salesforce field validation and constraint enforcement

Medium confidence

Validates record data against Salesforce field constraints (required fields, field length, data type, picklist values, formula fields) before submission. The server uses Salesforce metadata to enforce validation rules, preventing invalid API calls and providing Claude with detailed validation error messages that explain why a field value is invalid and what corrections are needed.

Solves for

I want Claude to validate a record before creating it so it doesn't fail with cryptic Salesforce errorsI need Claude to know which fields are required and which are optional before constructing a recordI want helpful error messages that explain field constraints so Claude can correct invalid data

Best for

Teams building Salesforce data entry assistants that need to guide users through valid data

Developers creating AI-powered form builders with client-side validation

Salesforce admins automating data quality checks in AI workflows

Requires

Salesforce org with metadata API access

Valid authentication token with metadata read permissions

Node.js 16+

Limitations

Custom validation rules are not enforced — only field-level constraints are validated, not org-specific business rules

Formula fields and rollup fields are not validated — their values are read-only and validation is skipped

Dependent picklists are not fully supported — validation may not account for picklist dependencies

What makes it unique

Implements client-side validation using Salesforce metadata before submitting API requests, preventing invalid submissions and providing Claude with detailed constraint information so it can self-correct without trial-and-error.

vs alternatives

More efficient than server-side validation because it prevents failed API calls and reduces round-trips, and more helpful than raw Salesforce error messages because it explains constraints in a way Claude can understand and act on.

Capabilities are decomposed by AI analysis. Each maps to specific user intents and improves with match feedback.

Related Artifactssharing capabilities

Artifacts that share capabilities with @tsmztech/mcp-server-salesforce, ranked by overlap. Discovered automatically through the match graph.

MCP Server34

@salesforce/mcp

MCP Server for interacting with Salesforce instances

salesforce metadata introspection and schema discoverysalesforce soql query execution with mcp transportsalesforce record creation and update via mcp toolssalesforce custom object and field querying with dynamic schema binding

4 shared capabilities

MCP Server37

@salesforce/mcp

MCP Server for interacting with Salesforce instances

salesforce metadata schema introspection and field discoverysoql query execution with result streamingrecord crud operations (create, read, update, delete) via mcp toolssalesforce search (global and object-specific) via mcp

4 shared capabilities

MCP Server33

MCP-Salesforce

MCP Salesforce connector

soql query execution with llm-driven schema awarenessobject metadata discovery and field schema retrievalsalesforce api request formatting and response parsingmcp tool registration and schema exposure

4 shared capabilities

MCP Server26

@iflow-mcp/gbo37-sfmc-mcp-tool

MCP tool for connecting Claude to Salesforce Marketing Cloud REST API

salesforce marketing cloud rest api schema-based function calling

1 shared capability

Product29

Jigso

Optimize tasks, automate alerts, and retrieve data...

salesforce-data-retrieval-and-updates

1 shared capability

Best For

✓Teams building AI agents that need Salesforce integration without custom API wrappers
✓Salesforce admins automating record management through Claude conversations
✓Developers prototyping Salesforce-connected AI workflows
✓Salesforce analysts building AI-powered reporting and search tools
✓Teams needing ad-hoc Salesforce queries without writing custom reports
✓Developers building conversational Salesforce data exploration interfaces
✓Salesforce developers building AI-assisted schema exploration tools
✓Teams onboarding new Salesforce orgs and needing AI-guided schema documentation

Known Limitations

⚠No built-in transaction support — multi-step operations are not atomic; partial failures require manual rollback
⚠Rate limiting depends on Salesforce org limits; no client-side throttling or backoff strategy documented
⚠Batch operations not explicitly supported — each record operation is a separate API call, causing N+1 performance issues at scale
⚠No field-level security enforcement — relies entirely on Salesforce user permissions of the authenticated session
⚠SOQL syntax validation is limited — complex joins or subqueries may fail silently if not properly formatted
⚠No query optimization — inefficient SOQL (e.g., queries without WHERE clauses) can timeout on large orgs

Requirements

Salesforce org with API access enabledValid OAuth 2.0 credentials or session token for SalesforceNode.js 16+ runtimeMCP-compatible client (Claude Desktop, or custom MCP host)Salesforce org with API access and query permissionsValid authentication token with query permissions on target objectsNode.js 16+MCP-compatible client

Input / Output

Accepts: structured JSON object with Salesforce field names and values, SOQL query strings for record retrieval, Salesforce record IDs (18-character or 15-character format), SOQL query string (e.g., 'SELECT Id, Name FROM Account WHERE Industry = "Technology"'), pagination parameters (offset, limit), Salesforce object name (e.g., 'Account', 'Contact', custom objects like 'MyCustomObject__c'), field name for detailed field metadata, OAuth 2.0 authorization code (during initial setup), Salesforce username and password (for username-password flow, if supported), array of record objects with fields to create/update, array of record IDs for deletion, batch operation type (create, update, delete, upsert), parent record ID and relationship name (e.g., Account ID with 'Contacts' relationship), relationship traversal path (e.g., 'Account -> Contacts -> Cases'), record object with field values to validate, Salesforce object type (Account, Contact, etc.), operation type (create, update, upsert)

Produces: structured JSON with Salesforce record data, operation status (success/failure with error codes), query result sets with field metadata, JSON array of record objects with requested fields, pagination metadata (total count, has_more flag), error messages with SOQL syntax details, JSON schema with object fields, types, lengths, required status, picklist value arrays with labels and API names, relationship metadata (lookup targets, master-detail parents), field-level metadata (formula, rollup, auto-number status), access token (used internally by MCP server), authentication status (authenticated/expired/invalid), error messages for auth failures, batch operation result with per-record success/failure status, array of created/updated record IDs, detailed error messages for failed records (field validation errors, permission errors, etc.), batch summary (total processed, succeeded, failed), related record objects with specified fields, relationship metadata (cardinality, relationship type), nested JSON structure representing relationship hierarchy, validation result (valid/invalid), array of validation errors with field names and constraint details, suggestions for correcting invalid values (e.g., valid picklist options)

UnfragileRank

Adoption30%(30% weight)

Quality16%(25% weight)

Ecosystem47%(25% weight)

Match Graph10%(15% weight)

Freshness75%(5% weight)

UnfragileRank is computed from adoption signals, documentation quality, ecosystem connectivity, match graph feedback, and freshness. No artifact can pay for a higher rank.

Type: MCP Server

7 capabilities

Visit @tsmztech/mcp-server-salesforce→

Package Details

npm

Registry

0.0.6

Version

1,519

Weekly Downloads

About

A Salesforce connector MCP Server.

Alternatives to @tsmztech/mcp-server-salesforce

IntelliCode50Extension

AI-assisted development

Compare →

GitHub Copilot Chat53Extension

AI chat features powered by Copilot

Compare →

GitHub Copilot52Extension

Your AI pair programmer

Compare →

Claude Code for VS Code52Extension

Claude Code for VS Code: Harness the power of Claude Code without leaving your IDE

Compare →

Are you the builder of @tsmztech/mcp-server-salesforce?

Claim this artifact to get a verified badge, access match analytics, see which intents users search for, and manage your listing.

Claim this artifact →Verification via email

Get the weekly brief

New tools, rising stars, and what's actually worth your time. No spam.

Data Sources

npmmcp registry

Looking for something else?

Search →

Capabilities7 decomposed

salesforce record crud operations via mcp protocol

Medium confidence

Solves for

Best for

Teams building AI agents that need Salesforce integration without custom API wrappers

Salesforce admins automating record management through Claude conversations

Developers prototyping Salesforce-connected AI workflows

Requires

Salesforce org with API access enabled

Valid OAuth 2.0 credentials or session token for Salesforce

Node.js 16+ runtime

Limitations

No built-in transaction support — multi-step operations are not atomic; partial failures require manual rollback

Rate limiting depends on Salesforce org limits; no client-side throttling or backoff strategy documented

Batch operations not explicitly supported — each record operation is a separate API call, causing N+1 performance issues at scale

What makes it unique

vs alternatives

salesforce soql query execution with result streaming

Medium confidence

Solves for

Best for

Salesforce analysts building AI-powered reporting and search tools

Teams needing ad-hoc Salesforce queries without writing custom reports

Developers building conversational Salesforce data exploration interfaces

Requires

Salesforce org with API access and query permissions

Valid authentication token with query permissions on target objects

Node.js 16+

Limitations

SOQL syntax validation is limited — complex joins or subqueries may fail silently if not properly formatted

No query optimization — inefficient SOQL (e.g., queries without WHERE clauses) can timeout on large orgs

Pagination is manual — Claude must explicitly request next pages; no automatic result aggregation across pages

What makes it unique

vs alternatives

salesforce object metadata introspection and schema discovery

Medium confidence

Solves for

Best for

Salesforce developers building AI-assisted schema exploration tools

Teams onboarding new Salesforce orgs and needing AI-guided schema documentation

Builders creating intelligent Salesforce form builders or query assistants

Requires

Salesforce org with Metadata API or Describe API access

Valid authentication token with metadata read permissions

Node.js 16+

Limitations

Metadata caching is not documented — repeated schema queries may incur repeated Salesforce API calls, impacting rate limits

Custom objects and fields are supported but custom metadata types are not explicitly documented

Relationship metadata (lookup, master-detail) is returned but traversal across relationships is not automated

What makes it unique

vs alternatives

salesforce authentication and session management via mcp

Medium confidence

Solves for

Best for

Teams deploying MCP servers in production and needing secure credential management

Salesforce admins setting up Claude integration without exposing API keys

Developers building multi-user Salesforce AI agents with per-user authentication

Requires

Salesforce OAuth 2.0 app configured with client ID and client secret

Valid Salesforce user account with API permissions

Node.js 16+

Limitations

Credential storage mechanism is not documented — unclear if tokens are stored in memory, environment variables, or encrypted files

No built-in support for multiple Salesforce orgs — appears to support single org per MCP server instance

Token refresh logic is not explicitly documented — unclear if refresh tokens are stored or if re-authentication is required

What makes it unique

vs alternatives

salesforce batch record operations with error handling

Medium confidence

Solves for

Best for

Teams performing bulk data migrations or imports through Claude

Salesforce admins automating large-scale record updates

Developers building batch processing workflows in AI agents

Requires

Salesforce org with Composite API or Bulk API access

Valid authentication token with create/update/delete permissions on target objects

Node.js 16+

Limitations

Batch size limits are not documented — unclear if there are hard limits on records per batch or if Salesforce's 25MB payload limit applies

No automatic retry logic for transient failures — failed records are reported but not automatically retried

Partial failure handling requires manual inspection of per-record error responses — no built-in rollback or compensation logic

What makes it unique

vs alternatives

salesforce relationship traversal and record linking

Medium confidence

Solves for

Best for

Salesforce analysts building AI-powered relationship exploration tools

Teams needing to understand Salesforce data relationships without writing complex SOQL

Developers building knowledge graph or entity relationship visualizations

Requires

Salesforce org with relationship metadata available

Valid authentication token with read permissions on related objects

Node.js 16+

Limitations

Relationship traversal depth is not documented — unclear if there are limits on how many levels deep Claude can traverse

Circular relationship handling is not documented — could cause infinite loops if relationships form cycles

Many-to-many relationships through junction objects may not be fully supported — documentation is unclear

What makes it unique

vs alternatives

salesforce field validation and constraint enforcement

Medium confidence

Solves for

Best for

Teams building Salesforce data entry assistants that need to guide users through valid data

Developers creating AI-powered form builders with client-side validation

Salesforce admins automating data quality checks in AI workflows

Requires

Salesforce org with metadata API access

Valid authentication token with metadata read permissions

Node.js 16+

Limitations

Custom validation rules are not enforced — only field-level constraints are validated, not org-specific business rules

Formula fields and rollup fields are not validated — their values are read-only and validation is skipped

Dependent picklists are not fully supported — validation may not account for picklist dependencies

What makes it unique

vs alternatives

Capabilities are decomposed by AI analysis. Each maps to specific user intents and improves with match feedback.

Alternatives to @tsmztech/mcp-server-salesforce

IntelliCode50Extension

AI-assisted development

Compare →

GitHub Copilot Chat53Extension

AI chat features powered by Copilot

Compare →

GitHub Copilot52Extension

Your AI pair programmer

Compare →

Claude Code for VS Code52Extension

Claude Code for VS Code: Harness the power of Claude Code without leaving your IDE

Compare →

@tsmztech/mcp-server-salesforce

Capabilities7 decomposed

salesforce record crud operations via mcp protocol

salesforce soql query execution with result streaming

salesforce object metadata introspection and schema discovery

salesforce authentication and session management via mcp

salesforce batch record operations with error handling

salesforce relationship traversal and record linking

salesforce field validation and constraint enforcement

Related Artifactssharing capabilities

@salesforce/mcp

@salesforce/mcp

MCP-Salesforce

@iflow-mcp/gbo37-sfmc-mcp-tool

Jigso

Best For

Known Limitations

Requirements

Input / Output

UnfragileRank

Package Details

About

Categories

Alternatives to @tsmztech/mcp-server-salesforce

Are you the builder of @tsmztech/mcp-server-salesforce?

Get the weekly brief

Data Sources

@tsmztech/mcp-server-salesforce

Capabilities7 decomposed

salesforce record crud operations via mcp protocol

salesforce soql query execution with result streaming

salesforce object metadata introspection and schema discovery

salesforce authentication and session management via mcp

salesforce batch record operations with error handling

salesforce relationship traversal and record linking

salesforce field validation and constraint enforcement

Related Artifactssharing capabilities

@salesforce/mcp

@salesforce/mcp

MCP-Salesforce

@iflow-mcp/gbo37-sfmc-mcp-tool

Jigso

Best For

Known Limitations

Requirements

Input / Output

UnfragileRank

Package Details

About

Categories

Alternatives to @tsmztech/mcp-server-salesforce

Are you the builder of @tsmztech/mcp-server-salesforce?

Get the weekly brief

Data Sources