mcpbeat Sign in

sf-intelligence — Salesforce org intelligence for AI agents MCP Server

local only

sf-intelligence — Salesforce org intelligence for AI agents runs on your own machine — the client starts it, so there is no endpoint to ping. 279 installs a week from npm. Last commit 20 Oct 2026.

Offline, read-only MCP knowledge base for one Salesforce org's metadata, deps & impact.

Installs per day peak 213 · avg 22 · +216% w/w
a month agotoday
279
Installs / week
npm · sf-intelligence
3
Stars
0 open issues
20 Oct 2026
Last commit
9 releases in 90 days
MIT
License
TypeScript

What the code does

We read the source, 2 d ago · rules 995398eba69f

Evidence

Things with no honest explanation: a promise that contradicts the code, code that runs at install time while hiding what it does, data leaving the machine.

const assert = spawnSync(process.execPath, [assertScript], {
Capabilities

What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.

File ships in the package but is absent from the source [пакет] demo-source/main/default/lwc/projectSummaryCard/projectSummaryCard.html:1, [пакет] demo-source/main/default/lwc/projectSummaryCard/projectSummaryCard.js:1
этот файл ставится пользователю, но в репозитории его нет
const assert = spawnSync(process.execPath, [assertScript], {
    const url = `${path}?q=${encodeURIComponent(`SELECT COUNT() FROM ${q.entity}`)}`;

Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.

We found things in this code

Code changes quietly between releases, and nobody reads the diff of a dependency. We do, on every release — watch sf-intelligence — Salesforce org intelligence for AI agents and you get told the day something new turns up.

Three servers free · no card

Connect this server

This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.

run in your terminal
claude mcp add sf-intelligence -e 'SFI_VAULT=<SFI_VAULT>' -- npx -y sf-intelligence
~/Library/Application Support/Claude/claude_desktop_config.json
{
  "mcpServers": {
    "sf-intelligence": {
      "command": "npx",
      "args": [
        "-y",
        "sf-intelligence"
      ],
      "env": {
        "SFI_VAULT": "<SFI_VAULT>"
      }
    }
  }
}
~/.codex/config.toml
[mcp_servers.sf-intelligence]
command = "npx"
args = ["-y", "sf-intelligence"]
env = { SFI_VAULT = "<SFI_VAULT>" }
.cursor/mcp.json
{
  "mcpServers": {
    "sf-intelligence": {
      "command": "npx",
      "args": [
        "-y",
        "sf-intelligence"
      ],
      "env": {
        "SFI_VAULT": "<SFI_VAULT>"
      }
    }
  }
}
.vscode/mcp.json
{
  "servers": {
    "sf-intelligence": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "sf-intelligence"
      ],
      "env": {
        "SFI_VAULT": "<SFI_VAULT>"
      }
    }
  }
}

Put your own value in place of <SFI_VAULT> (Absolute path to the org-kb vault this server should answer from, e.g. <your-sfdx-project>/org-kb. Set this: without it the server falls back to ./org-kb relative to whatever directory your MCP host happens to launch in, and an MCP host is almost never launched inside your Salesforce project. The server still starts without it and reports what it looked for via sfi.setup_status, but it will have no org to answer about). The author’s registry entry marks it as required.

Alternatives to sf-intelligence — Salesforce org intelligence for AI agents

same job, measured the same way
iknow
by iknow

Knowledge base MCP for AI agents on iknow.dev. Search, read, and maintain via OAuth.

answering
Sw Dev Knowledge Base MCP
by execuro

Read-only offline MCP server over a curated Shopware developer knowledge base

137 installs/wk local only
Agents Wiki
by agents-wiki

Knowledge base for AI agents: search, read, tasks; write, correct, report outcomes via /mcp/write.

6 tools answering
Krobot
by kromatic-innovation

Kromatic's public MCP server for read-only access to the Kromatic knowledge base.

answering
ForgeMesh Library MCP
by forgemeshlabs

A paid public-domain knowledge base for AI agents: full-text search, book metadata, chapters.

94 installs/wk local only
MCAI Knowledge Base
by meta-consciousness-ai

Meta-Consciousness Theory knowledge base: definitions, relations and citations for AI agents.

2 715 installs/wk local only
Pil
by pjpoulose

PIL: local-first knowledge base for your Instagram saved posts, with a read-only MCP server.

52 installs/wk local only
Blck Alpaca Agentic Audit & Knowledge Base
by blckalpaca

Audit a website for AI-agent readiness and GEO. Knowledge base on SEO, GEO and AI agents (de/en/sk).

5 tools answering

sf-intelligence — Salesforce org intelligence for AI agents — questions

Answers built from our own checks of this server.

Why is there no uptime for sf-intelligence — Salesforce org intelligence for AI agents?
sf-intelligence — Salesforce org intelligence for AI agents runs on your own machine over stdio — there is no network address to reach, so uptime cannot be measured for it by anyone. What can be measured is adoption: the npm package sf-intelligence was installed 279 times last week.
How do I connect sf-intelligence — Salesforce org intelligence for AI agents?
Copy the ready config from this page. We generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each in the form that client actually reads. It runs locally, so the command pulls sf-intelligence straight from npm; nothing to host, nothing to sign up for.
How many people use sf-intelligence — Salesforce org intelligence for AI agents?
The npm package sf-intelligence was installed 279 times in the last week. Week over week that is +216%. We show installs rather than GitHub stars on purpose: a star is a bookmark, an install is someone actually running it.
Is sf-intelligence — Salesforce org intelligence for AI agents open source?
Yes — it is published under the MIT licence, written in TypeScript and 3 stars on GitHub. The source link is on this page, so you can read exactly what it does with your data before you connect it.