Salesforce Ai Agent Mcp Server

MCPAI代理

提供方 pratapsfdc22-dev

AI代理 stdio · 本地进程 OAuth 授权 社区 / 第三方 Claude DesktopClaudeCursorVS Code
查看接入方式

MCP Server for Salesforce Configuration through Jira,n8n, and Claude Integration

一句话选型结论

按资料字段整理

Salesforce Ai Agent Mcp Server 属于AI代理类 MCP 服务器,stdio · 本地进程,OAuth 授权,可直接接入 Claude Desktop、Claude、Cursor 等,有可直接执行的安装命令。接入前先确认权限范围;涉及写入、删除或付款的操作,建议先在测试环境验证。

分类AI代理 传输方式stdio · 本地进程 鉴权OAuth 授权 部署方式本地部署
GitHub 星标 未标注 仓库热度,无公开仓库时显示未标注
工具数 未标注 暴露给模型的工具数量
资源 / 提示词 0 / 0 资源与提示词模板数量
维护方 社区 / 第三方 核验等级 仅资料核对

工具与能力

AI代理
数量来自来源目录的标注,具体工具清单以官方文档为准
工具数量未标注暴露给模型可调用的工具个数
资源数量0可读取的资源条目
提示词数量0内置提示词模板数量

能力标签

salesforce jira n8n enterprise crm automation metadata deployment

支持客户端

适用场景

salesforcejiran8n

安装与配置

stdio · 本地进程 OAuth 授权
客户端在本机拉起子进程,数据不出本机
node /absolute/path/to/salesforce-ai-agent-mcp/dist/index.js

这条命令只是入口,具体启动参数请按官方文档补齐,不要直接照搬到别的服务器。

  1. 1
    准备运行环境

    stdio 服务在本地起进程,需要先装好 node,再按安装命令拉取依赖。

  2. 2
    安装服务

    复制上面的安装命令执行;命令里带占位符的位置,换成自己的密钥或路径。

  3. 3
    写入客户端配置

    在客户端的 MCP 配置里填好启动命令和参数,保存后完全退出客户端再打开,让新配置生效。

  4. 4
    验证是否可用

    连接成功后随便调一个只读工具,确认能返回结果,再接入正式流程。

典型使用场景

3 类
按分类与标签整理的常见用法,具体以官方文档为准
给代理接外部能力

让代理在任务中途调用搜索、数据库等真实工具。

多步任务编排

把一串操作拆成步骤,由代理按顺序执行。

自动化重复流程

把固定流程交给代理跑,减少手工操作。

选择建议

选之前先看这几条
按条目字段给出的判断,不替你决定用不用

值得选的地方

  • 有现成的安装命令,不用自己找入口,照着跑就能起服务。
  • 已适配 Claude Desktop、Claude、Cursor,换客户端不用重新研究配置。

先想清楚的地方

  • stdio 方式要求本地装好运行时(如 Node.js),换机器要重新装一遍。
  • 使用前要准备好OAuth 授权对应的凭据,并按最小权限配置。
  • 资料没标注工具数量,实际能力要装好后确认。
  • 版本更新与行为细节以官方仓库为准。

更适合

  • 需要在AI代理场景里让模型直接调用外部能力的人。
  • 已经在用 Claude Desktop、Claude 的用户,接入路径最短。
  • 想先快速试一下、能接受在本地或自有环境跑服务的人。

不太适合

  • 完全不想在本地装环境的人。
  • 不方便管理密钥或第三方授权的人。
  • 需要厂商级 SLA 和技术支持的生产环境。

同类对比

6 个同类
同分类里挑最接近的几条,字段以各自详情页为准
MCP 服务器工具数传输方式部署方式安装命令最后核验
Salesforce Ai Agent Mcp Server当前 未标注 stdio · 本地进程 本地部署 有 未标注
Filesystem 560c4363 13 未标注 本地部署 无 2026-05-17
Server Everything (everything) 11 stdio · 本地进程 本地部署 有 2026-05-17
Time 7365cb6d 2 SSE · 服务端推送 远程部署 有 2026-05-18
Everything Claude Code 未标注 stdio · 本地进程 本地部署 有 2026-05-17
Openmemory 557e1585 未标注 stdio · 本地进程 本地部署 有 2026-05-17

服务器档案

AI代理
字段来自项目仓库与公开索引,中文说明由本站标注
提供方pratapsfdc22-dev上游标注的维护方 pratapsfdc22-dev
分类AI代理本站按上游分类展示
连接方式stdio · 本地进程客户端在本机拉起子进程,数据不出本机
鉴权方式OAuth 授权远程服务建议用最小权限凭据
维护方社区 / 第三方核验等级 仅资料核对
包名 / 运行时未标注 · node本地安装时用到的包标识与运行时
部署类型本地部署上游给出的部署形态
最近核验未标注上游最后核验时间

详细介绍

10.0 KB
来自项目仓库与上游目录的原文,未做删改

Salesforce AI Agent MCP Server

A production-grade Model Context Protocol (MCP) server that gives Claude direct, structured access to Jira Cloud, Salesforce (Tooling + Metadata APIs), and n8n workflows.

Built for the Salesforce Developer AI Agent project — an automation pipeline that reads Jira stories, interprets Salesforce configuration requirements, and deploys metadata (custom fields, validation rules, etc.) directly into Salesforce.


Architecture```

Claude Desktop / Claude Code / VS Code
│ (stdio or SSE)
▼
salesforce-ai-agent-mcp
┌───────────────────────────┐
│ Tools (12 total) │
│ ├── Jira (4 tools) │──► Jira Cloud REST API v3
│ ├── Salesforce (6 tools) │──► Salesforce Tooling + Metadata APIs
│ └── n8n (2 tools) │──► n8n Webhook + REST API
└───────────────────────────┘


---

## Prerequisites

- Node.js ≥ 18
- npm ≥ 9
- A Jira Cloud account with API token
- A Salesforce org with a Connected App (OAuth 2.0)
- An n8n instance (optional, for workflow orchestration)

---

## Installation```bash
cd salesforce-ai-agent-mcp
npm install
npm run build

Configuration

Copy .env.example to .env and fill in your credentials:```bash
cp .env.example .env


### Jira

| Variable | Description |
|---|---|
| `JIRA_BASE_URL` | e.g. `https://your-org.atlassian.net` |
| `JIRA_EMAIL` | Your Atlassian account email |
| `JIRA_API_TOKEN` | Generate at Atlassian API Tokens |

### Salesforce

You need a **Connected App** with the **Username-Password OAuth flow** enabled.

1. In Salesforce Setup → App Manager → New Connected App
2. Enable OAuth settings
3. Add scope: `api`, `refresh_token`
4. Copy Consumer Key → `SF_CLIENT_ID`
5. Copy Consumer Secret → `SF_CLIENT_SECRET`

| Variable | Description |
|---|---|
| `SF_LOGIN_URL` | `https://login.salesforce.com` (prod) or `https://test.salesforce.com` (sandbox) |
| `SF_CLIENT_ID` | Connected App Consumer Key |
| `SF_CLIENT_SECRET` | Connected App Consumer Secret |
| `SF_USERNAME` | Your Salesforce username |
| `SF_PASSWORD` | Your Salesforce password |
| `SF_SECURITY_TOKEN` | Reset at Setup → Personal Information → Reset Security Token |
| `SF_API_VERSION` | API version, e.g. `v61.0` (default) |

### n8n

| Variable | Description |
|---|---|
| `N8N_BASE_URL` | Your n8n instance URL, e.g. `https://your-n8n.com` |
| `N8N_API_KEY` | Generate at n8n Settings → API → Create API Key |

---

## Usage

### stdio mode (Claude Desktop / Claude Code / VS Code)```bash
npm start
# or for development:
npm run dev

SSE mode (for remote/n8n integration)```bash

npm run start:sse

or for development:

npm run dev:sse


Endpoints available in SSE mode:
- `GET  http://localhost:3000/sse` — clients connect here
- `POST http://localhost:3000/messages?sessionId=` — clients send messages here
- `GET  http://localhost:3000/health` — liveness probe

Override the port:```bash
MCP_PORT=8080 npm run start:sse

Connecting to Claude Desktop

Add the following to your claude_desktop_config.json:

macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: `%APPDATA%\Claude\claude_desktop_config.json````json
{
"mcpServers": {
"salesforce-ai-agent": {
"command": "node",
"args": ["/absolute/path/to/salesforce-ai-agent-mcp/dist/index.js"],
"env": {
"JIRA_BASE_URL": "https://your-org.atlassian.net",
"JIRA_EMAIL": "you@company.com",
"JIRA_API_TOKEN": "your_token",
"SF_LOGIN_URL": "https://login.salesforce.com",
"SF_CLIENT_ID": "your_client_id",
"SF_CLIENT_SECRET": "your_client_secret",
"SF_USERNAME": "you@yourorg.com",
"SF_PASSWORD": "yourpassword",
"SF_SECURITY_TOKEN": "yourSecurityToken",
"N8N_BASE_URL": "https://your-n8n.com",
"N8N_API_KEY": "your_n8n_api_key"
}
}
}
}


---

## Connecting to Claude Code (VS Code Extension)

Add to your VS Code `settings.json` (or via the MCP extension UI):```json
{
  "mcp.servers": {
    "salesforce-ai-agent": {
      "command": "node",
      "args": ["${workspaceFolder}/salesforce-ai-agent-mcp/dist/index.js"],
      "env": {
        "JIRA_BASE_URL": "https://your-org.atlassian.net",
        "JIRA_EMAIL": "you@company.com",
        "JIRA_API_TOKEN": "your_token",
        "SF_LOGIN_URL": "https://login.salesforce.com",
        "SF_CLIENT_ID": "your_client_id",
        "SF_CLIENT_SECRET": "your_client_secret",
        "SF_USERNAME": "you@yourorg.com",
        "SF_PASSWORD": "yourpassword",
        "SF_SECURITY_TOKEN": "yourSecurityToken",
        "N8N_BASE_URL": "https://your-n8n.com",
        "N8N_API_KEY": "your_n8n_api_key"
      }
    }
  }
}

Alternatively, the mcp.json file at the root of this project is compatible with VS Code's MCP extension and will be auto-detected if placed in your workspace root.


Available Tools (12 total)

Jira Tools

jira_get_story

Fetch a Jira story by issue key. Returns summary, description, acceptance criteria, status, labels, and all custom fields.```
issueKey: "SFDC-123"


#### `jira_update_story_status`
Transition a Jira story to a new workflow status.```
issueKey: "SFDC-123"
targetStatus: "In Progress"   # must match an available transition

jira_post_comment

Post a comment to a Jira story (used by the AI agent to report results or ask for clarification).```
issueKey: "SFDC-123"
body: "Deployed Customer_Tier__c field to Account. Deployment ID: 0Af..."


#### `jira_search_stories`
JQL-based story search.```
jql: "label = \"sf-config\" AND status = \"To Do\" AND project = SFDC"
maxResults: 25

Salesforce Tools

salesforce_get_object_fields

Describe all fields on a Salesforce object.```
objectName: "Account"


#### `salesforce_create_custom_field`
Create a custom field via the Tooling API.```
objectName: "Account"
fieldLabel: "Customer Tier"
fieldApiName: "Customer_Tier"     # __c added automatically
fieldType: "Picklist"
picklistValues: ["Platinum", "Gold", "Silver", "Bronze"]
description: "Tier classification for account segmentation"

Lookup field example:```
objectName: "Case"
fieldLabel: "Related Contract"
fieldApiName: "Related_Contract"
fieldType: "Lookup"
referenceTo: "Contract"


#### `salesforce_create_validation_rule`
Create a validation rule via the Tooling API.```
objectName: "Account"
ruleName: "Require_Phone_For_Hot_Leads"
errorConditionFormula: "AND(Rating = \"Hot\", ISBLANK(Phone))"
errorMessage: "Phone number is required for Hot-rated accounts"
errorDisplayField: "Phone"
active: true

salesforce_deploy_metadata

Trigger a metadata deployment from a base64-encoded ZIP.```
zipFile: "<base64-encoded-zip>"
checkOnly: false
testLevel: "RunLocalTests"
rollbackOnError: true


#### `salesforce_get_deployment_status`
Poll a deployment&#x27;s status.```
deploymentId: &quot;0AfXXXXXXXXXXXXX&quot;

salesforce_query

Execute SOQL for validation and verification.```
soql: "SELECT Id, Name, Customer_Tier__c FROM Account WHERE Rating = 'Hot' LIMIT 10"


---

### n8n Tools

#### `n8n_trigger_workflow`
Trigger an n8n workflow via webhook URL.```
webhookUrl: &quot;https://your-n8n.com/webhook/abc123&quot;
payload: {
  &quot;issueKey&quot;: &quot;SFDC-123&quot;,
  &quot;environment&quot;: &quot;sandbox&quot;,
  &quot;triggeredBy&quot;: &quot;claude&quot;
}

n8n_get_execution_status

Check the status of an n8n execution.```
executionId: "12345"


---

## Example AI Agent Workflow```
You: &quot;Process Jira story SFDC-456 and deploy the Salesforce configuration&quot;

Claude:
1. jira_get_story(issueKey: &quot;SFDC-456&quot;)
   → reads requirements: &quot;Add Customer_Tier picklist to Account&quot;

2. salesforce_get_object_fields(objectName: &quot;Account&quot;)
   → confirms Customer_Tier__c doesn&#x27;t exist yet

3. salesforce_create_custom_field(
     objectName: &quot;Account&quot;,
     fieldLabel: &quot;Customer Tier&quot;,
     fieldApiName: &quot;Customer_Tier&quot;,
     fieldType: &quot;Picklist&quot;,
     picklistValues: [&quot;Platinum&quot;, &quot;Gold&quot;, &quot;Silver&quot;]
   )
   → creates the field

4. salesforce_query(soql: &quot;SELECT QualifiedApiName FROM FieldDefinition WHERE EntityDefinition.QualifiedApiName = &#x27;Account&#x27; AND QualifiedApiName = &#x27;Customer_Tier__c&#x27;&quot;)
   → verifies the field was created

5. jira_post_comment(
     issueKey: &quot;SFDC-456&quot;,
     body: &quot;✅ Customer_Tier__c picklist field created on Account object with values: Platinum, Gold, Silver.&quot;
   )

6. jira_update_story_status(issueKey: &quot;SFDC-456&quot;, targetStatus: &quot;Done&quot;)

Logging

All logs are written as structured JSON to stderr so they never interfere with the MCP stdio transport.

Control the log level via environment variable:```bash
LOG_LEVEL=debug npm start # debug | info | warn | error


---

## Development```bash
# Type-check only
npm run typecheck

# Build
npm run build

# Dev with hot reload (stdio)
npm run dev

# Dev with hot reload (SSE)
npm run dev:sse

Project Structure```

salesforce-ai-agent-mcp/
├── src/
│ ├── index.ts # Entry point — stdio & SSE transport setup
│ ├── server.ts # McpServer creation & tool registration
│ ├── tools/
│ │ ├── jira.ts # Jira tool definitions (4 tools)
│ │ ├── salesforce.ts # Salesforce tool definitions (6 tools)
│ │ └── n8n.ts # n8n tool definitions (2 tools)
│ ├── clients/
│ │ ├── jiraClient.ts # Jira REST API v3 client
│ │ ├── salesforceClient.ts # Salesforce Tooling/Metadata API + OAuth
│ │ ├── n8nClient.ts # n8n webhook + REST API client
│ │ └── logger.ts # Structured JSON logger (stderr)
│ └── types/
│ └── index.ts # Shared TypeScript types
├── .env.example # All required environment variables
├── mcp.json # VS Code MCP extension manifest
├── package.json
├── tsconfig.json
└── README.md
```

常见问题

8 问
答案由本站依据条目字段整理,不引用上游原文
Salesforce Ai Agent Mcp Server 怎么安装?

在客户端按下面的安装命令接入:node /absolute/path/to/salesforce-ai-agent-mcp/dist/index.js。装完在客户端配置里引用同一个包或端点。

Salesforce Ai Agent Mcp Server 怎么在 Claude Desktop、Claude、Cursor 里配置?

它的传输方式是stdio · 本地进程,在客户端的 MCP 配置里填好启动命令和参数,保存后完全退出客户端再打开,配置才会生效。

Salesforce Ai Agent Mcp Server 收费吗?

本站不代收费用,也没有标注具体价格。是否收费取决于服务本身和背后的接口额度,正式使用前按官方说明确认。

Salesforce Ai Agent Mcp Server 需要 API Key 吗?

资料标注需要OAuth 授权认证,使用前准备好对应凭据,并按最小权限配置。

Salesforce Ai Agent Mcp Server 支持哪些客户端?

资料标注支持 Claude Desktop、Claude、Cursor、VS Code、Codex、Zed;其他客户端只要能配置 MCP Server,也能用同样的命令或地址接入。

Salesforce Ai Agent Mcp Server 能提供哪些能力?

资料显示能力标签包括 salesforce、jira、n8n、enterprise、crm、automation。具体工具清单以官方文档为准。

Salesforce Ai Agent Mcp Server 需要什么运行环境?

运行时为 node;属于本地进程,需要在本机装好运行环境。

Salesforce Ai Agent Mcp Server 是本地还是远程?

它是本地进程(stdio),由客户端在本机拉起。传输方式为stdio · 本地进程。

热门专题

按标签挑服务器
全部专题 →

服务器信息以作者仓库与官方文档为准;分类、传输方式与鉴权方式的中文说明为中文整理,最近核验 未标注。