@salesforce/mcp
MCP ServerFreeMCP Server for interacting with Salesforce instances
Capabilities12 decomposed
salesforce org connection management via mcp protocol
Medium confidenceEstablishes and manages authenticated connections to Salesforce instances through the Model Context Protocol, handling OAuth2 flows and session management. The MCP server acts as a bridge between LLM clients and Salesforce APIs, abstracting authentication complexity and maintaining connection state across multiple tool invocations without requiring clients to manage credentials directly.
Implements MCP protocol natively for Salesforce, eliminating the need for custom API wrappers or REST client boilerplate. Uses Salesforce CLI's underlying authentication infrastructure (jsforce or similar) to delegate credential handling to the platform's standard tooling.
Simpler than building custom Salesforce API clients for each LLM framework because MCP standardizes the tool interface; more secure than embedding API keys in prompts because credentials stay server-side.
soql query execution with result streaming
Medium confidenceExecutes Salesforce Object Query Language (SOQL) queries against connected orgs and streams results back to the LLM client through MCP. The server parses SOQL syntax, validates queries against the org's schema, executes via Salesforce REST API, and formats results as structured JSON or CSV for downstream processing by the LLM.
Exposes SOQL as a first-class MCP tool rather than requiring LLMs to construct REST API calls manually. Integrates with Salesforce CLI's query parser to validate syntax before execution, reducing API call waste from malformed queries.
More direct than REST API clients because SOQL is Salesforce's native query language; faster than building custom query builders because it delegates to Salesforce's optimized query engine.
salesforce custom action invocation with parameter mapping
Medium confidenceInvokes Salesforce custom actions (Quick Actions, Custom Actions) from MCP tools with dynamic parameter mapping. The server calls Salesforce Action API, maps LLM-provided parameters to action inputs, executes the action, and returns results. Enables LLMs to trigger org-specific custom logic without hardcoding action details.
Exposes Salesforce custom actions as MCP tools, allowing LLMs to invoke org-specific logic without embedding action names or parameters in prompts. Handles parameter mapping and result formatting server-side.
More flexible than hardcoded workflows because custom actions can be modified in Salesforce UI; more integrated than external APIs because actions stay within Salesforce ecosystem.
salesforce event publishing and platform event handling
Medium confidencePublishes events to Salesforce Platform Events and subscribes to event streams through MCP tools. The server manages event publishing via REST API, handles event payload serialization, and optionally streams incoming events to LLM clients. Enables LLMs to trigger event-driven workflows and react to Salesforce events in real-time.
Exposes Salesforce Platform Events as MCP tools, allowing LLMs to publish events and optionally subscribe to event streams. Abstracts event serialization and subscription management server-side.
More event-driven than REST API because it supports publish-subscribe patterns; more real-time than polling because events are pushed to subscribers immediately.
record crud operations (create, read, update, delete) via mcp tools
Medium confidenceProvides atomic MCP tools for creating, retrieving, updating, and deleting Salesforce records. Each operation maps to Salesforce REST API endpoints, handles field validation, enforces org-level permissions, and returns operation results with error details. The server abstracts REST API complexity and provides consistent error handling across all CRUD operations.
Wraps Salesforce REST API CRUD endpoints as discrete MCP tools, allowing LLMs to call create/read/update/delete as separate functions rather than constructing HTTP requests. Integrates field-level validation and permission checking at the server level.
Simpler than raw REST API clients because MCP abstracts HTTP details; safer than embedding API calls in LLM prompts because the server enforces org permissions and validates field types.
salesforce metadata schema introspection and field discovery
Medium confidenceExposes Salesforce org metadata (object definitions, field types, relationships, picklist values) as queryable MCP tools. The server calls Salesforce Metadata API or Describe endpoints to fetch schema information, caches results to reduce API calls, and returns structured metadata that LLMs can use to construct valid queries and mutations without trial-and-error.
Caches Salesforce metadata at the MCP server level, reducing redundant API calls when LLMs query schema multiple times. Exposes metadata as structured MCP tools rather than requiring LLMs to parse raw Salesforce API responses.
More efficient than querying Salesforce API directly for each schema lookup because caching reduces API call overhead; more reliable than hardcoding field names because it adapts to custom orgs dynamically.
batch record operations with error handling and partial success tracking
Medium confidenceExecutes bulk operations on multiple Salesforce records (create, update, delete) in a single MCP call, with granular error tracking per record. The server batches requests to Salesforce Bulk API or REST API batch endpoints, tracks success/failure for each record, and returns detailed results including which records succeeded and which failed with specific error reasons.
Abstracts Salesforce Bulk API complexity into a single MCP tool call, handling job creation, polling, and result parsing server-side. Provides per-record error tracking without requiring clients to implement async polling logic.
More efficient than individual CRUD calls for large datasets because it batches requests; more transparent than raw Bulk API because it tracks per-record success/failure and returns results in a single response.
salesforce report and dashboard data retrieval
Medium confidenceFetches data from Salesforce Reports and Dashboards through MCP tools, executing reports with optional filters and returning results as structured data. The server calls Salesforce Analytics API or Report API endpoints, applies filter parameters, and formats results for LLM consumption (JSON, CSV, or summary statistics).
Exposes Salesforce Reports and Dashboards as queryable MCP tools, allowing LLMs to retrieve pre-aggregated data without constructing SOQL queries. Integrates with Salesforce Analytics API to support dynamic filtering.
More efficient than querying raw data with SOQL because reports are pre-aggregated; more accessible than raw analytics APIs because it abstracts API complexity into simple tool calls.
workflow and approval process triggering via mcp
Medium confidenceTriggers Salesforce workflows, approval processes, and custom actions from MCP tool calls. The server invokes Salesforce Process Builder, Flow, or Approval Process APIs with input parameters, monitors execution status, and returns results including approval decisions or workflow outcomes. Enables LLMs to initiate business processes without manual intervention.
Exposes Salesforce Flows and Approval Processes as MCP tools, allowing LLMs to trigger complex business logic without embedding Salesforce-specific code. Handles async execution and result polling server-side.
More powerful than CRUD operations because it enables multi-step business processes; more flexible than hardcoded workflows because Flows can be modified in Salesforce UI without code changes.
salesforce file and attachment management
Medium confidenceManages files and attachments in Salesforce through MCP tools, supporting upload, download, and metadata retrieval. The server handles file encoding/decoding, manages Salesforce ContentDocument and Attachment APIs, and tracks file relationships to records. Enables LLMs to attach documents to records or retrieve file content for processing.
Abstracts Salesforce ContentDocument and Attachment APIs into simple upload/download MCP tools, handling base64 encoding and file association server-side. Supports both legacy Attachments and modern Files (ContentDocument).
More convenient than raw Salesforce API because it handles encoding/decoding; more integrated than external file storage because files stay within Salesforce and maintain record relationships.
salesforce search (global and object-specific) via mcp
Medium confidenceExecutes Salesforce global search and object-specific searches through MCP tools, returning ranked results with relevance scoring. The server calls Salesforce Search API (SOSL), applies search filters, and formats results for LLM consumption. Enables full-text search across Salesforce data without constructing SOQL queries.
Exposes Salesforce Search (SOSL) as an MCP tool, allowing LLMs to perform full-text search without constructing SOQL queries. Integrates with Salesforce's search index for fast, ranked results.
Faster than SOQL for keyword searches because it uses Salesforce's search index; more user-friendly than SOQL because it accepts plain-text queries without syntax.
salesforce list view data retrieval and filtering
Medium confidenceRetrieves data from Salesforce list views through MCP tools, executing pre-configured filters and returning paginated results. The server calls Salesforce List View API, applies view-specific filters, and formats results for LLM consumption. Enables LLMs to access curated record sets without constructing SOQL queries.
Exposes Salesforce list views as queryable MCP tools, allowing LLMs to access pre-filtered record sets without SOQL knowledge. Integrates with Salesforce List View API for efficient pagination.
More efficient than SOQL for accessing pre-configured views because filters are pre-optimized; more user-friendly than SOQL because it requires only a list view ID.
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 @salesforce/mcp, ranked by overlap. Discovered automatically through the match graph.
@salesforce/mcp
MCP Server for interacting with Salesforce instances
@tsmztech/mcp-server-salesforce
A Salesforce connector MCP Server.
MCP-Salesforce
MCP Salesforce connector
@iflow-mcp/db-mcp-tool
Database Explorer MCP Tool - PostgreSQL, MySQL ve Firestore veritabanları için yönetim aracı
@iflow-mcp/gbo37-sfmc-mcp-tool
MCP tool for connecting Claude to Salesforce Marketing Cloud REST API
Zapier
** - Connect your AI Agents to 8,000 apps instantly.
Best For
- ✓AI agents and LLM applications integrating with Salesforce
- ✓Teams building Salesforce automation workflows with Claude, ChatGPT, or local LLMs
- ✓Developers migrating from REST API clients to MCP-based Salesforce integration
- ✓AI agents performing data retrieval and analysis on Salesforce data
- ✓LLM-powered reporting and insights generation from CRM data
- ✓Developers building Salesforce chatbots or virtual assistants
- ✓AI agents executing org-specific Salesforce actions
- ✓LLM-powered workflows that need to invoke custom business logic
Known Limitations
- ⚠Requires pre-configured Salesforce Connected App with OAuth credentials
- ⚠Session tokens expire after Salesforce's configured timeout (typically 2 hours); no automatic refresh mechanism documented
- ⚠Single MCP server instance handles one org at a time unless multiple server processes are spawned
- ⚠SOQL query complexity is limited by Salesforce API governor limits (e.g., 50,000 records per query)
- ⚠No built-in query optimization or cost estimation; poorly written queries can consume API call limits
- ⚠Result streaming may require pagination logic on client side for datasets exceeding 10,000 rows
Requirements
Input / Output
UnfragileRank
UnfragileRank is computed from adoption signals, documentation quality, ecosystem connectivity, match graph feedback, and freshness. No artifact can pay for a higher rank.
Repository Details
Package Details
About
MCP Server for interacting with Salesforce instances
Categories
Alternatives to @salesforce/mcp
Are you the builder of @salesforce/mcp?
Claim this artifact to get a verified badge, access match analytics, see which intents users search for, and manage your listing.
Get the weekly brief
New tools, rising stars, and what's actually worth your time. No spam.
Data Sources
Looking for something else?
Search →