Connect your data to Claude in 1 minute. No code needed Try it now
Salesforce MCP

Salesforce MCP

Your pipeline already knows which deals are slipping. Ask Claude or ChatGPT and get the answer in plain language, with the math done in SQL. Coupler.io runs a hosted Salesforce MCP server that keeps your CRM data synced on the schedule you pick.
  • 200K+ Users
  • 400+ Data Sources
  • SOC 2 Type II
  • GDPR
  • HIPAA
  • DORA

How Salesforce MCP server by Coupler.io works

Your AI tool never touches Salesforce directly. It asks Coupler.io, which runs the calculation on your synced CRM data and returns only the computed result.

Connect

Shape your Salesforce data for AI before anyone asks a question

  • Pick Salesforce objects like Opportunity, Account, Lead, and Case, any custom object, tabular reports, or your own SOQL queries
  • Join them with Google Ads, LinkedIn Ads, Stripe, or any of 400+ other sources
  • Hide fields the AI shouldn't read, like contact emails or discount notes
  • Add business context: what makes an opportunity qualified and when a deal counts as stalled
Connect Salesforce to AI with Coupler.io MCP

Why use the Salesforce MCP connector?

Most pipeline questions wait until someone has time to build a report. Here you ask in plain language and have the breakdown before the call ends.
Prep the pipeline review in minutes icon

Prep the pipeline review in minutes

Ask which opportunities slipped their close date twice or sat in one stage past 30 days, and get the list before the meeting. The sales analytics skill repeats the same pipeline checks every week.
Check the math behind the forecast icon

Check the math behind the forecast

Coupler.io's Analytical Engine computes win rates and pipeline coverage in SQL. Your AI tool explains the result, and you can open the query whenever a number looks off.
Teach the AI how your team sells icon

Teach the AI how your team sells

Save your definitions once: which stages count as late pipeline and how you weight each forecast category. The AI reads that context with every question.
See Salesforce next to your ad spend icon

See Salesforce next to your ad spend

Bring Google Ads, LinkedIn Ads or HubSpot into the same Coupler.io workspace. Trace closed-won revenue back to the campaigns that sourced it.
Gabriel Solberg photo

I'm not getting AI's best guess. Coupler.io does that actual math. Claude just helps me ask the right question and understand the results conversationally

Salesforce MCP use cases and prompts

Copy a prompt into your AI tool and swap in your own dates and quota.

Find stalled deals

Which open opportunities over $25,000 have stayed in the same stage for more than 30 days? Group them by owner and tell me which ones to push this week.

Explain a win-rate drop

Our win rate fell this quarter. Compare it with the last two quarters by lead source, segment, and deal size, and point to the biggest driver.

Check pipeline coverage

Is our Q4 pipeline coverage above 3x quota? Show weighted and unweighted pipeline by region and flag every region below target.

Spot slipping close dates

List opportunities whose close date moved more than twice in the last 60 days. Which reps have the most, and what's the total amount at risk?

Compare rep performance

Show win rate, average deal size, and median sales cycle for each rep over the last 6 months. Leave out reps with fewer than 10 closed deals.

Find stage bottlenecks

How many days do opportunities spend in each stage this year, on median? Where is stage-to-stage conversion lowest?

Trace revenue to campaigns

Which campaigns sourced the most closed-won revenue in the last 90 days? Put it next to Google Ads and LinkedIn Ads spend and rank campaigns by return.

Review lost deals

Break down closed-lost opportunities from last quarter by loss reason and competitor. Which reason grew fastest compared with the quarter before?

Draft a forecast summary

Write a one-page pipeline summary for leadership: commit versus best case by forecast category, the five largest deals at risk, and what changed since last week.

Salesforce MCP top skills

A skill is a written procedure your AI follows step by step. This week's pipeline review checks exactly what last week's did.

Salesforce HubSpot Pipedrive 2 more

Sales analytics

Analyzes pipeline and CRM data from Salesforce, HubSpot, Pipedrive, and more. Covers win rate, deal velocity, stage conversion, and rep performance. Works as a standalone skill or combined with marketing-analytics for full-funnel orchestration.

Coupler.io

Report generation

Turns raw analysis into a clean, decision-ready report. Runs validation on figures and claims before delivery so you can share it with stakeholders without a second pass. Outputs markdown, summarize-ready text, or formatted tables.

Coupler.io

Generate dataset context

Reads your dataset and documents its structure so analytics skills know exactly what data they're working with. Run this first for more accurate results. Think of it as giving the AI domain expertise about your specific data.

Coupler.io

Coupler io live dashboard

Builds a live dashboard over your Coupler.io data that you can reopen every morning and that refreshes on a schedule.

How to connect Salesforce MCP to your custom AI agent

Building your own AI agents, or automating in n8n or Make? The Custom MCP destination turns a Salesforce data flow into an endpoint any MCP-compatible client can query.

  1. Create a Salesforce data flow

    Sign in to your Salesforce org and set a refresh schedule.

  2. Choose Custom MCP as the destination

    Coupler.io generates a token and a server URL.

  3. Add both to your client config

    Claude Code, Cursor, and VS Code accept a remote server, as does any other client that supports the Model Context Protocol.

mcp.json
{
  "mcpServers": {
    "coupler": {
      "url": "https://mcp.coupler.io/mcp/10146",
      "headers": {
        "Authorization": "Bearer YOUR_TOKEN"
      }
    }
  }
}

Why RevOps teams choose Coupler.io for Salesforce MCP

Salesforce's hosted MCP servers became generally available in April 2026 as part of the Headless 360 push. They give AI agents live, permission-aware access to records, with read-only and write-enabled server options. Admins can also add custom tools built on flows, an Apex class, or named queries. For Salesforce developers, the Salesforce DX MCP server covers metadata and testing work inside the IDE. Coupler.io focuses on analysis: it syncs your Salesforce data and calculates the answers your AI tool explains.

Feature
Coupler.io Salesforce MCP
Salesforce hosted MCP servers
Setup
Coupler.io Salesforce MCP
Sign in to Salesforce with OAuth and pick objects, reports, or SOQL. No External Client App or callback URLs
Salesforce hosted MCP servers
An admin creates an External Client App, sets a callback URL for each AI client, enables PKCE and JWT-based tokens, then activates each server
Salesforce editions
Coupler.io Salesforce MCP
Standard, Professional, Enterprise and Unlimited
Salesforce hosted MCP servers
Enterprise Edition and above
Access
Coupler.io Salesforce MCP
Read-only. Nothing is written back to your org
Salesforce hosted MCP servers
Pick a server: SObject Reads for queries, SObject Mutations for create and update, SObject Deletes, or SObject All for full CRUD operations
Built for
Coupler.io Salesforce MCP
RevOps, sales leaders and analysts
Salesforce hosted MCP servers
Admins and Salesforce developers extending agents across the Salesforce ecosystem, Agentforce included
Calculations
Coupler.io Salesforce MCP
The Analytical Engine runs SQL and computes the result. The AI explains it
Salesforce hosted MCP servers
The model writes SOQL queries against live records and interprets what comes back
Business context
Coupler.io Salesforce MCP
Saved once per dataset and read with every question
Salesforce hosted MCP servers
Possible through Prompt Builder templates or custom MCP tools that your Salesforce team builds and maintains
Data freshness
Coupler.io Salesforce MCP
Synced on your schedule, as often as every 15 minutes
Salesforce hosted MCP servers
Live record access
Data sources
Coupler.io Salesforce MCP
Salesforce plus 400+ sources in one workspace
Salesforce hosted MCP servers
Salesforce records, plus separate Data 360 and Tableau Next servers
Skills
Coupler.io Salesforce MCP
Ready-made sales analytics skills
Salesforce hosted MCP servers
Not included
Security
Coupler.io Salesforce MCP
SOC 2 Type II, GDPR, HIPAA and DORA. AI tools never connect to Salesforce directly
Salesforce hosted MCP servers
Per-user authentication that respects field-level security and sharing rules. Actions show up in audit trails under the user's name

Ask your pipeline the hard questions

Connect Salesforce to your AI tool through Coupler.io and start with the deals that stopped moving. You don't need an External Client App or a server to host.

Frequently asked questions

Model Context Protocol (MCP) is an open standard that lets AI tools read data from other systems. A Salesforce MCP server connects your Salesforce org to an AI assistant, and you can ask about opportunities, accounts or pipeline in plain language from Anthropic's Claude AI, ChatGPT or Gemini. Coupler.io runs it as a hosted Salesforce MCP server connector. Sign in to Salesforce, pick your AI tool and start asking.

Salesforce offers two options. With the Salesforce hosted MCP servers, an admin activates servers such as SObject Reads, sets up an External Client App and connects AI clients through per-user authentication. These need Enterprise Edition or above. The Salesforce DX MCP server is a developer tool. It runs locally against orgs you've authorized with the Salesforce CLI and helps you deploy metadata or run Apex tests from VS Code, Cursor or Agentforce Vibes. Coupler.io's Salesforce MCP connector is built for analysis. It works with Standard and Professional editions too, calculates in SQL and blends Salesforce with 400+ other sources.

Coupler.io does the arithmetic and the AI does the explaining. The Analytical Engine runs SQL on your synced Salesforce data and returns computed results, which the LLM then puts into words. You can open the query behind any figure. Saved definitions, like how your team weights each forecast category, keep the model's reading in line with your own reports.

The connector reads from Salesforce and doesn't write back. You still update opportunities or reassign leads in Salesforce itself. Answers reflect your last sync, and the AI sees only the Salesforce objects and fields in your data flow. Report imports support tabular reports and return the first 2,000 rows. For bigger datasets, pull Objects or write SOQL queries. Connecting needs the REST API enabled for your org, and both production and sandbox orgs work.

No. Your AI tool never gets your Salesforce credentials or direct access to your org. When you ask a question, the Analytical Engine runs the query, and the model receives only column names, data types, a sample of rows, your saved context and the calculated result. Your full CRM data stays in Coupler.io, which is SOC 2 Type II certified and compliant with GDPR, HIPAA and DORA. Credentials are encrypted with AES-256, and data in transit is protected with TLS.