Provides tools to interact with Salesforce orgs, enabling SOQL/SOSL queries, CRUD operations on records, metadata exploration, report and dashboard access, Tooling API queries, and Apex execution.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@salesforce-mcp show me the top 10 accounts by revenue"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
A Model Context Protocol server that connects AI assistants to Salesforce orgs. Enables querying, searching, creating, updating, and managing Salesforce data through natural language via any MCP-compatible client.
Node.js 18+
A Salesforce org with API access
npm installCopy the example env file and fill in your Salesforce credentials:
cp .env.example .envVariable | Required | Default | Description |
| Yes | — | Salesforce username |
| Yes | — | Salesforce password |
| No |
| Security token (appended to password) |
| No |
| Login URL (use |
npm run build
npm startRelated MCP server: MCP Salesforce Connector
Add to your MCP client config (e.g. Claude Desktop claude_desktop_config.json):
{
"mcpServers": {
"salesforce": {
"command": "node",
"args": ["/absolute/path/to/salesforce_mcp/dist/index.js"],
"env": {
"SF_USERNAME": "your_username",
"SF_PASSWORD": "your_password",
"SF_SECURITY_TOKEN": "your_token",
"SF_LOGIN_URL": "https://login.salesforce.com"
}
}
}
}salesforce_query — Execute a SOQL query (first batch, up to 2000 records)
salesforce_query_all — SOQL query with automatic pagination (configurable max records)
salesforce_query_more — Fetch next batch using nextRecordsUrl
salesforce_search — Execute a SOSL search
salesforce_describe_object — Get fields, relationships, and record types for an sObject
salesforce_list_objects — List all sObjects in the org
salesforce_get_record — Get a record by ID
salesforce_create_record — Create a new record
salesforce_update_record — Update an existing record
salesforce_delete_record — Delete a record by ID
salesforce_list_reports — List all reports
salesforce_run_report — Execute a report by ID
salesforce_describe_report — Get report metadata (columns, filters, groupings)
salesforce_list_dashboards — List all dashboards
salesforce_get_dashboard — Get dashboard component data and status
salesforce_tooling_query — Query Apex classes, triggers, flows, validation rules, etc.
salesforce_get_metadata_component — Retrieve full source of a metadata component
salesforce_describe_tooling_object — Get fields for a Tooling API sObject
salesforce_execute_apex — Run anonymous Apex code
salesforce_get_org_limits — View API call limits, storage usage, etc.
salesforce_get_org_info — Org edition, instance, API version, user info
salesforce_rest_api — Generic REST API call for any endpoint
MIT
This server cannot be deployed
A comprehensive Model Context Protocol (MCP) server that enables AI assistants to interact with yo…
The HubSpot MCP Server acts as a bridge that enables AI assistants and Large Language Models to securely interact with HubSpot CRM data through natural conversation, without requiring users to understand complex API structures. It provides read-only access to standard CRM objects (contacts, companies, deals, tickets, products, invoices, and more) and their associations, secured via OAuth 2.0, allowing AI agents to perform tasks like summarizing deals, fetching company updates, and looking up record changes.
MCP server unifying ERPs, CRMs, APIs and knowledge base for Claude, ChatGPT and Gemini.
MCP server that lets AI assistants use all OneSchema features exposed via the public API.
