Claude Salesforce MCP server

Register sf-intelligence as a read-only Salesforce MCP server for Claude Code, Claude Desktop, Cursor, Codex, or any MCP client. It is built for org understanding, not metadata deployment.

Claude Code setup

From a Salesforce DX project, register the server once:

claude mcp add --transport stdio --scope project sf-intelligence -- npx -y sf-intelligence mcp

Then run a read-only metadata refresh:

npx -y sf-intelligence init
npx -y sf-intelligence refresh --target-org my-org-alias

Works with MCP clients

ClientUse case
Claude CodeAsk org questions from the project where the metadata vault lives
Claude DesktopPoint a desktop assistant at a local read-only Salesforce knowledge base
CursorUse org metadata intelligence while editing Salesforce code
CodexGive coding agents structured, read-only Salesforce context
Any MCP clientRun the same stdio server and call the same 176 read-only tools

Why not use a write-capable server for this?

Deployment and retrieval MCP servers are useful for DevOps. sf-intelligence is deliberately different: it is a Salesforce org intelligence layer. It answers questions about dependencies, permissions, automation, Apex, Flows, and documentation from a local vault, and it has no write path to the org.

Searches this page targets

  • "Claude Salesforce MCP"
  • "Salesforce MCP server Claude Code"
  • "Cursor Salesforce MCP"
  • "Codex Salesforce MCP"
  • "read-only Salesforce MCP server"
  • "AI agent Salesforce metadata"

Next steps

For the full setup sequence, read getting started. For how it differs from Salesforce's official DevOps-oriented server, read sf-intelligence vs Salesforce DX MCP Server. For metadata search examples, read Salesforce metadata analysis.

Connect your AI client to Salesforce context.

Register the MCP server, run a read-only refresh, then ask questions from your agent.