Salesforce MCP | OAuth Salesforce connector for AI agents

CALL ANY TOOL

Read and write accounts, contacts, leads, opportunities, and cases. Run SOQL queries for custom data retrieval.

salesforce_soql_query

Run SOQL query

Execute an arbitrary Salesforce Object Query Language query for custom data retrieval across any object.

Parameters

Name

Type

Required

Description

query

string

Required

SOQL query string (e.g. SELECT Id, Name FROM Account LIMIT 10)

salesforce_record_search

Search records

salesforce_record_get

Get record

salesforce_record_create

Create record

salesforce_record_update

Update record

salesforce_task_create

Log activity

Build your Agent

Drop the toolkit in, point it at the user, and your agent can query Salesforce records and run SOQL from the first run.

Copied

import { ScalekitClient } from "@scalekit-sdk/node";
import { DynamicStructuredTool } from "@langchain/core/tools";
import { createReactAgent } from "@langchain/langgraph/prebuilt";
import { z } from "zod";

const sk = new ScalekitClient(envUrl, clientId, clientSecret);

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["salesforce"], toolNames: ["salesforce_soql_query", "salesforce_record_search", "salesforce_record_get"] },
  pageSize: 100,
});

const lcTools = tools.map((t) => new DynamicStructuredTool({
  name: t.tool.definition.name,
  description: t.tool.definition.description,
  schema: z.object({}).passthrough(),
  func: async (args) => {
    const { data } = await sk.tools.executeTool({
      toolName: t.tool.definition.name,
      identifier: "user_123",
      params: args,
    });
    return JSON.stringify(data);
  },
}));

const agent = createReactAgent({ llm, tools: lcTools });

Copied

import { ScalekitClient } from "@scalekit-sdk/node";
import OpenAI from "openai";

const sk = new ScalekitClient(envUrl, clientId, clientSecret);
const openai = new OpenAI();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["salesforce"], toolNames: ["salesforce_soql_query", "salesforce_record_search", "salesforce_record_get"] },
  pageSize: 100,
});

const llmTools = tools.map((t) => ({
  type: "function",
  function: {
    name: t.tool.definition.name,
    description: t.tool.definition.description,
    parameters: t.tool.definition.input_schema,
  },
}));

const resp = await openai.responses.create({
  model: "gpt-4o", input: prompt, tools: llmTools,
});

import { ScalekitClient } from "@scalekit-sdk/node";
import Anthropic from "@anthropic-ai/sdk";

const sk = new ScalekitClient(envUrl, clientId, clientSecret);
const anthropic = new Anthropic();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["salesforce"], toolNames: ["salesforce_soql_query", "salesforce_record_search", "salesforce_record_get"] },
  pageSize: 100,
});

const llmTools = tools.map((t) => ({
  name: t.tool.definition.name,
  description: t.tool.definition.description,
  input_schema: t.tool.definition.input_schema,
}));

const msg = await anthropic.messages.create({
  model: "claude-sonnet-4-6", max_tokens: 1024,
  tools: llmTools,
  messages: [{ role: "user", content: prompt }],
});

Copied

import { Agent } from "@google/adk/agents";
import {
  MCPToolset, StreamableHTTPConnectionParams,
} from "@google/adk/tools/mcp";

const toolset = new MCPToolset({
  connectionParams: new StreamableHTTPConnectionParams({
    url: "https://mcp.scalekit.com/salesforce",
    headers: { Authorization: `Bearer ${userScopedToken}` },
  }),
});

const agent = new Agent({
  name: "agent", model: "gemini-2.0-flash",
  tools: await toolset.getTools(),
});

Try these prompts

Paste any prompt into your agent to start pulling CRM intelligence from Salesforce.

Search & recall

Copy the prompt

Copied

Show me all open opportunities over $100K closing this quarter.

Copy the prompt

Copied

Find all contacts at [account name].

Copy the prompt

Copied

List all leads from [campaign name].

Copy the prompt

Copied

What cases are open with priority High?

Action & updates

Copy the prompt

Copied

Update the stage on [opportunity name] to Negotiation.

Copy the prompt

Copied

Create a new lead: [name], [company], [email].

Copy the prompt

Copied

Log a call with [contact name]: [notes].

Copy the prompt

Copied

Close won the [opportunity name] deal at [$amount].

Pipeline & reporting

Copy the prompt

Copied

Run a SOQL query: SELECT StageName, SUM(Amount) FROM Opportunity GROUP BY StageName.

Copy the prompt

Copied

What is my total pipeline value this quarter?

Copy the prompt

Copied

Which accounts have no activity in the last 30 days?

Copy the prompt

Copied

List all opportunities owned by [rep name].

SEE HOW AUTH WORKS

Users authorize Salesforce once. Their org credentials stay vaulted, every call is checked, and every action is logged.

1

Authorize

Your user connects

Salesforce

once. We tie it to their identity and the meetings they approved — no shared bot account, no org-wide access

Who:

user ‘A’

when:

Once per user

access:

Limited to user

2

Store

Their

Salesforce

token lives in a vault scoped to them. User A's meetings are never reachable by an agent acting for user B, even on the same connection

vault:

encrypted

scope:

per-user

tokens:

auto-refreshed

3

Resolve

When your agent calls a

Salesforce

tool, we fetch the right token server-side. It never touches your agent, never appears in the LLM context, never shows up in your logs

speed:

~40ms

check:

before every call

seen by:

nobody

4

Audit

Every

Salesforce

tool call is logged — who triggered it, which meeting was fetched, what came back. 90 days of history, tied to the user who authorized it

history:

90 days

export:

SIEM-ready

logged:

every call

Test other agents

Same per-user auth pattern across other sales agents and MCP connectors. Working code, live demos, fork what fits.

GTM

Salesforce customer insights agent

Surface Salesforce account activity, NPS signals, and renewal flags into Slack threads for the account team.

Salesforce

Slack

View agent

GTM

CRM AI agent

Log calls, update opportunity stages, and surface stalled deals across HubSpot or Salesforce. No manual data entry.

HubSpot

Salesforce

View agent

Why Scalekit

Secure your agent's access. Connectors ship in minutes

Other connector libraries treat auth as a demo afterthought. Scalekit starts with user identity, scope enforcement, and audit.

01.

Shared tokens bypass field-level security

A shared Salesforce token bypasses field-level security. In production, every SOQL query and record write runs under the integration profile, not the rep's. FLS rules break. Opportunity ownership breaks. Scalekit resolves the rep's profile at call time, so Salesforce enforces the right access rules.

// shared bot token
token = "sk_salesforce_shared_xxx"
audit → bot_service_account
rep_filter → broken

// scalekit · per-user
token = resolve(user_id)
audit → user_abc
scope → enforced ✓

02.

Authentication is not authorization

03.

Multi-tenancy is architectural

04.

Salesforce today. HubSpot, Attio, Apollo tomorrow.

“Our agents act across Salesforce, Gong, Google Drive, and more, on behalf of every customer. Scalekit behind the scenes meant we can keep adding tools without ever rebuilding how credentials or tool calling work.”

Venu Madhav Kattagoni

Head of Engineering / Von

FAQs

Frequently Asked Questions

Does the agent access Salesforce as the user or as a shared key?

As the user. Each workspace member authorizes once and Scalekit resolves their credential at request time. Audit logs attribute every action to that user, not a shared service account.

Where is the Salesforce oauth 2.0 stored?

In Scalekit's managed AES-256 token vault, namespaced per tenant. Refresh is automatic. Revocation is a single dashboard action. Tokens never appear in prompts, logs, or LLM context.

Can I limit what the agent is allowed to do in Salesforce?

Yes. Pass a tool name filter to listScopedTools so the sales agent only sees the subset you authorize. Pre-API-call scope checks block out-of-policy actions before the request reaches Salesforce.

What happens when a user revokes Salesforce access?

The connection is invalidated on the next tool call. Subsequent requests for that user fail closed with a clear error. Other users in the tenant remain unaffected. The event is logged for audit.

Does SOQL execution respect Salesforce field-level security?

Yes. SOQL queries run as the authorizing user. Field-level security, sharing rules, and profile permissions all apply. The agent cannot read or write what the user cannot.

Salesforce

Tools your sales agent reaches for on Salesforce, scoped per user.