Crmcloud

io.github.CloudCorpRecords由 GitHub 账号 CloudCorpRecords 发布v0.1.0更新于 Nov 3, 2026

Salesforce org 访问:SOQL 查询、SOSL 搜索、SObject CRUD、限制以及用户信息。

AI 翻译由 AI 模型根据下方的原文描述翻译,可能有误。

原文描述

Salesforce org access: SOQL queries, SOSL search, SObject CRUD, limits, and user info.

已验证STDIO仅桌面商业与电商

概览

Crmcloud 的本地 MCP 服务;无需登录;STDIO。

暂无 AI 概览:以下信息来自注册中心条目和服务本身。

安装

在 SourceWeft 中

  1. 打开 控制台中的 Crmcloud,将其添加到工作区。
  2. 为需要使用其工具的对话启用该服务。

Desktop only,通过 STDIO。 STDIO 服务会启动本地进程,因此需要 SourceWeft 桌面宿主。

其他 MCP 客户端

参照 仓库 中的启动说明。

README

crmcloud

crmcloud is a thin, honest window into one Salesforce org. Everything in an org hangs off the same few shapes — SObjects with fields, records addressed by type and ID, SOQL for asking questions, SOSL for searching across objects — and crmcloud maps those shapes directly: run a query, run a search, list and describe the objects, then create, read, update, and delete records, with org limits and the current user's identity alongside. One binary serves a command-line interface and a stdio MCP server.

Two environment variables configure every call:

  • SALESFORCE_INSTANCE_URL — your org's instance URL, for example https://your-org.my.salesforce.com (a trailing slash is fine).
  • SALESFORCE_ACCESS_TOKEN — an access token for that org, sent as an Authorization: Bearer header and never printed.

When either variable is missing, every call fails before any request is made, with an error that names the missing variable. Data calls go to <instance>/services/data/v59.0; the user-info call goes to <instance>/services/oauth2/userinfo, where Salesforce puts it.

This is a core subset on purpose: org and scratch-org management, Apex and Lightning tooling, metadata deploy/retrieve, and bulk data import/export — the parts of the wider Salesforce tooling world that drive the sf CLI — are not included. crmcloud covers the REST data surface only.

Install

bash
npx @reneturcios/crmcloud sobjects

Or run the container image:

bash
docker run -i -e SALESFORCE_INSTANCE_URL -e SALESFORCE_ACCESS_TOKEN ghcr.io/cloudcorprecords/crmcloud

The container defaults to the MCP server (see below). Pass CLI arguments to use it as a CLI instead.

CLI

bash
export SALESFORCE_INSTANCE_URL=https://your-org.my.salesforce.comexport SALESFORCE_ACCESS_TOKEN=<redacted>
crmcloud query "SELECT Id, Name FROM Account LIMIT 5"crmcloud search "FIND {Acme} IN NAME FIELDS RETURNING Account(Id, Name)"crmcloud sobjectscrmcloud describe Accountcrmcloud get Account 001xx000003DGb2AAGcrmcloud create Account '{"Name":"Acme","Industry":"Technology"}'crmcloud update Account 001xx000003DGb2AAG '{"Name":"Acme II"}'crmcloud delete Account 001xx000003DGb2AAGcrmcloud limitscrmcloud userinfo
crmcloud --version

Each command prints the upstream JSON payload. Salesforce answers updates and deletes with an empty 204, so those two commands print a small {"success": true, "id": ..., "sobject": ...} confirmation instead. Exit codes: 0 on success, 1 when a call fails (including a missing environment variable or an API error), 2 for usage errors.

MCP server

One bin serves both faces. The mcp subcommand starts a stdio MCP server:

bash
npx -y @reneturcios/crmcloud mcp

MCP client configuration:

json
{  "mcpServers": {    "crmcloud": {      "command": "npx",      "args": ["-y", "@reneturcios/crmcloud", "mcp"],      "env": {        "SALESFORCE_INSTANCE_URL": "https://your-org.my.salesforce.com",        "SALESFORCE_ACCESS_TOKEN": "..."      }    }  }}

Tools

ToolInputWhat it returns
run_soql_queryquery (required)The SOQL result set: total size, done flag, and records.
search_recordssearch (required)The SOSL search records.
list_sobjects(none)The org's SObjects, with describe-global metadata.
describe_sobjectsobject (required)The object's fields, child relationships, and record types.
get_recordsobject, id (required)The record's field values.
create_recordsobject, fields (required)The upstream create result: new record id, success, errors.
update_recordsobject, id, fields (required)A success confirmation (upstream replies 204 with no body).
delete_recordsobject, id (required)A success confirmation (upstream replies 204 with no body).
get_org_limits(none)The org's API usage limits and remaining amounts.
get_user_info(none)The identity of the user the access token belongs to.

API errors surface the HTTP status plus Salesforce's own error message and error code when the org returns them.

Development

bash
npm installnpm run build   # tsc -> dist/npm test        # node test runner over test/*.test.ts, no network (fake fetch fixtures)npm run dev     # run the CLI from source via tsx

License

MIT — see LICENSE.

来源:README.md,提交 11643f4

工具

0
SourceWeft 尚未在沙箱中启动过该软件包,因此其工具未知。

版本历史

1
  1. v0.1.0最新Nov 3, 2026

评分

已满足适用检查项的 50%

该评分衡量此收录条目的完整程度,依据注册中心条目、端点与公开来源计算得出。它不是对服务器本身的评价,也不表示服务器安全或当前可用:可连通性是带日期的检查结果,评分也不包含安装量或用户评价。

  • 近 30 天内可连通25 分

    请保持端点能够响应 MCP 握手;SourceWeft 每 30 天探测一次。

  • 已声明认证方式10 分

    请在注册中心条目中声明凭据请求头,或保持端点能够响应探测,以便判定其认证方式。

  • 已列出工具15 分

    请让服务器在无凭据时响应 tools/list,或发布可在沙箱中无凭据启动的软件包。

  • 描述必需15 分
  • 图标10 分
  • 文档15 分
  • 许可证10 分