sf-intelligence
Offline-first, MCP-first knowledge base for a Salesforce org. Ask about your org's metadata, dependencies, permissions, and automation — grounded in real retri…
Developer Toolsnpx -y sf-intelligence{
"mcpServers": {
"sf-intelligence": {
"command": "npx",
"args": [
"-y",
"sf-intelligence"
]
}
}
}sf-intelligence is a community MCP server that connects AI assistants like Claude to offline-first, mcp-first knowledge base for a salesforce org. ask about your org's metadata, dependencies, permissions, and automation — grounded in real retri…. It runs locally on your machine, keeping your data private and giving you full control over the connection. Developers can use it to bring AI assistance directly into their build and coding environment.
About sf-intelligence
Overview
Offline-first, MCP-first knowledge base for a Salesforce org. Ask about your org's metadata, dependencies, permissions, and automation — grounded in real retrieved metadata. Ships the sfi CLI and an MCP server.
Links
Topics
salesforce, salesforce-metadata, mcp, mcp-server, model-context-protocol, claude, claude-code, cursor, cline, ai-agent, llm, cli, metadata, knowledge-base, offline, sfdx, apex, salesforce-cli
Who Should Use sf-intelligence?
- 1Speed up coding workflows by letting Claude interact with your dev environment
- 2Run terminal commands, manage processes, and inspect logs via AI
- 3Integrate AI assistance directly into your build and CI pipelines
- 4Automate repetitive dev tasks like scaffolding, linting, and testing
How to Install sf-intelligence
Before you start
You will need Node.js (v18 or later) installed on your machine — download it from nodejs.org if you haven't already.
- 1Open a terminal (Terminal on Mac, Command Prompt or PowerShell on Windows).
- 2Paste the install command above and press Enter — Node.js will download and run the server automatically.
- 3Add the server to your Claude Desktop config file (see the JSON snippet above) and restart Claude.
The Claude Desktop config snippet above can be copied and pasted directly into your claude_desktop_config.json file — no editing required.