mcp
@salesforcecli
mcp について
MCP Server for interacting with Salesforce instances
設定
以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。
{
"mcpServers": {
"Salesforce DX": {
"command": "npx",
"args": [
"-y",
"@salesforce/mcp",
"--orgs",
"DEFAULT_TARGET_ORG",
"--toolsets",
"orgs,metadata,data,users",
"--tools",
"run_apex_test",
"--allow-non-ga-tools"
]
}
}
}ツール
ツールは検出されませんでした
ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。
概要
What is mcp?
mcp is a Model Context Protocol (MCP) server that enables large language models (LLMs) to interact with Salesforce orgs. It provides a robust set of tools for reading, managing, and operating Salesforce resources securely.
How to use mcp?
Install and configure mcp by adding its JSON configuration to your MCP client’s settings. The server is run via npx -y @salesforce/mcp with required --orgs flag and optional --toolsets, --tools, and other flags. See the README for client-specific examples (VS Code, Claude Code, Cline, Cursor, etc.).
Key features of mcp
- Interact with Salesforce orgs through LLMs securely.
- Selectively enable tool groups via toolsets (orgs, metadata, data, users).
- Specify individual tools with the
--toolsflag. - Support for multiple authorized orgs using the
--orgsflag. - Boolean flags for debug logging, non‑GA tools, dynamic tool discovery, and telemetry control.
- Works with various MCP clients (VS Code, Claude Code, Cline, Cursor, etc.).
Use cases of mcp
- Query and manage Salesforce metadata, data, and users through an LLM.
- Run Apex tests and retrieve results via natural language.
- Automate Salesforce administrative tasks using AI assistants.
- Build custom AI‑powered workflows that interact with Salesforce orgs.
FAQ from mcp
What toolsets does mcp support?
The --toolsets flag accepts sets like orgs, metadata, data, users, or all to enable all tools. Toolsets group related functionality to reduce LLM context.
How do I specify which org mcp can access?
Use the required --orgs flag with values such as DEFAULT_TARGET_ORG, DEFAULT_TARGET_DEV_HUB, ALLOW_ALL_ORGS, or a specific username/alias. Org must be authorized locally first.
Does mcp require any additional runtime or dependencies?
mcp is installed via npx from the @salesforce/mcp npm package. No extra runtime is needed beyond Node.js and a compatible MCP client.
Can I enable only specific tools instead of entire toolsets?
Yes, use the --tools flag to list individual tool names (e.g., run_apex_test). You can combine --toolsets and --tools to fine‑tune which tools are active.
Is telemetry enabled by default? How can I disable it?
Telemetry is enabled by default. To disable it, include the --no-telemetry Boolean flag in the args option of your MCP client configuration.
よくある質問
What toolsets does mcp support?
The `--toolsets` flag accepts sets like `orgs`, `metadata`, `data`, `users`, or `all` to enable all tools. Toolsets group related functionality to reduce LLM context.
How do I specify which org mcp can access?
Use the required `--orgs` flag with values such as `DEFAULT_TARGET_ORG`, `DEFAULT_TARGET_DEV_HUB`, `ALLOW_ALL_ORGS`, or a specific username/alias. Org must be authorized locally first.
Does mcp require any additional runtime or dependencies?
mcp is installed via `npx` from the `@salesforce/mcp` npm package. No extra runtime is needed beyond Node.js and a compatible MCP client.
Can I enable only specific tools instead of entire toolsets?
Yes, use the `--tools` flag to list individual tool names (e.g., `run_apex_test`). You can combine `--toolsets` and `--tools` to fine‑tune which tools are active.
Is telemetry enabled by default? How can I disable it?
Telemetry is enabled by default. To disable it, include the `--no-telemetry` Boolean flag in the `args` option of your MCP client configuration.
基本情報
「その他」の他のコンテンツ
Blender
ahujasidOpen-source MCP to use Blender with any LLM
Unity MCP ✨
justinpbarnettUnity MCP acts as a bridge between AI assistants and your Unity Editor. Give your LLM tools to manage assets, control scenes, edit scripts, and automate tasks within Unity.
MCP Registry
modelcontextprotocolA community driven registry service for Model Context Protocol (MCP) servers.

Peekaboo MCP – lightning-fast macOS screenshots for AI agents
steipetePeekaboo is a macOS CLI & optional MCP server that enables AI agents to capture screenshots of applications, or the entire system, with optional visual question answering through local or remote AI models.

Sequential Thinking
modelcontextprotocolModel Context Protocol Servers
コメント