Salesforce Metadata MCP
@semwalajay83-sem
About Salesforce Metadata MCP
The most comprehensive Salesforce MCP server: 212 tools for managing your org from Claude in natural language. Create custom objects, fields, and page layouts; build and activate Flows; write and deploy Apex and LWC; manage permission sets, profiles, and users; reports and dashbo
Basic information
Config
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"salesforce": {
"command": "npx",
"args": [
"-y",
"salesforce-metadata-mcp"
],
"env": {
"SF_INSTANCE_URL": "https://your-org.my.salesforce.com",
"SF_ACCESS_TOKEN": "<YOUR_TOKEN>"
}
}
}
}Tools
No tools detected
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
Overview
What is Salesforce Metadata MCP?
Salesforce Metadata MCP is the most comprehensive Model Context Protocol server for Salesforce, providing 212 tools to build, configure, and automate Salesforce orgs directly from MCP clients like Claude.
How to use Salesforce Metadata MCP?
Install via npx -y salesforce-metadata-mcp or npm install -g salesforce-metadata-mcp. Add it to your MCP client configuration (e.g., claude_desktop_config.json) with the server command and required environment variables SF_INSTANCE_URL and SF_ACCESS_TOKEN (or other authentication methods).
Key features of Salesforce Metadata MCP
- 212 tools covering the full Salesforce metadata API
- Objects, fields, automation, security, and UI creation
- Apex and LWC deployment and testing
- Agentforce agent, action, and topic creation
- External integrations like Connected Apps and named credentials
- Change set creation and metadata deployment/retrieval
Use cases of Salesforce Metadata MCP
- Build a complete custom object with fields, validation rules, and page layouts
- Deploy Apex classes, triggers, and test classes to an org
- Create record-triggered flows with email alerts and follow-up tasks
- Set up an Agentforce agent with actions and topics wired together
- Manage deployment via outbound change sets and the Metadata API
FAQ from Salesforce Metadata MCP
How do I authenticate to my Salesforce org?
Set the SF_INSTANCE_URL (always required) and one of: SF_ACCESS_TOKEN for static tokens, SF_CLIENT_ID/SF_CLIENT_SECRET/SF_REFRESH_TOKEN for OAuth, or SF_ALIAS for Salesforce CLI authentication. See SETUP.md for details.
What transports and protocols are supported?
The server supports both stdio (default) and http transports, selectable via the TRANSPORT environment variable. The HTTP server port defaults to 3000 and can be changed with PORT.
What type of tools does the server include?
It includes tools for custom objects/fields, flows and approval processes, security (permission sets, roles, queues), Apex and LWC development, Experience Cloud sites, Agentforce agents, external integrations, and change set management.
Can I use it to deploy changes to production?
Yes, the server includes deployment tools like sf_deploy_metadata (with testLevel support), sf_check_deploy_status, and sf_retrieve_metadata, as well as sf_create_outbound_change_set and sf_add_to_change_set.
What dependencies are required to run it?
No external Salesforce CLI or SDK is required; the server runs on Node.js and connects directly to the Salesforce REST and Metadata APIs using the provided authentication credentials.
More Data & Analytics MCP servers
Google Ads MCP
cohnenAn MCP tool that connects Google Ads with Claude AI/Cursor and others, allowing you to analyze your advertising data through natural language conversations. This integration gives you access to campaign information, performance metrics, keyword analytics, and ad management—all th
MCP Deep Web Research Server (v0.3.0)
qpd-vEnhanced MCP server for deep web research
mcp-server-apache-airflow
yangkyeongmoFederal Reserve Economic Data MCP Server
stefanoamorelliOpen-source FRED MCP Server (Federal Reserve Economic Data)
Deep Research
u14appUse any LLMs (Large Language Models) for Deep Research. Support SSE API and MCP server.
Comments