Salesloft MCP | OAuth 2.0 Salesloft connector for AI agents

CALL ANY TOOL

OAuth-scoped per rep. Every cadence action and call log attributed to the authorizing sales rep.

salesloft_cadence_prospects_get

Get cadence prospects

List prospects enrolled in a cadence with their current step, due date, and full activity history filtered to the authorizing rep's assignments.

Parameters

Name

Type

Required

Description

cadence_id

string

Optional

Salesloft cadence ID (omit to list all assigned cadences)

step

integer

Optional

Filter by cadence step number

overdue_only

boolean

Optional

Return only overdue prospects

salesloft_activities_list

List activities

salesloft_cadence_step_execute

Execute cadence step

salesloft_prospects_search

Search prospects

salesloft_calls_log

Log call

Build your Agent

Drop the toolkit in, point it at the authorized rep, and your agent can query cadences and log activities 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: ["outreachmcp"], toolNames: ["outreach_prospects_search", "outreach_sequences_list", "outreach_tasks_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: ["outreachmcp"], toolNames: ["outreach_prospects_search", "outreach_sequences_list", "outreach_tasks_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: ["outreachmcp"], toolNames: ["outreach_prospects_search", "outreach_sequences_list", "outreach_tasks_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/outreachmcp",
    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 sales agent to start querying cadences and logging activities in Salesloft.

Search & recall

Copy the prompt

Copied

List all prospects currently in the [cadence name] cadence.

Copy the prompt

Copied

Show all email activities from the last 7 days and their reply rates.

Copy the prompt

Copied

Find all prospects at [company] and their current cadence step.

Action & enroll

Copy the prompt

Copied

Enroll [prospect name] in the [cadence name] cadence starting from step 1.

Copy the prompt

Copied

Log a call activity for [prospect name] with outcome: [outcome].

Copy the prompt

Copied

Create a new person record for [name] at [company] and enroll in [cadence].

SEE HOW AUTH WORKS

Reps authorize Salesloft once. Their OAuth token stays vaulted, every cadence action runs under their identity, and every step is logged.

1

Authorize

Your user connects

Salesloft

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

Salesloft

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

Salesloft

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

Salesloft

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 engagement and CRM connectors.

No items found.

Why Scalekit

Secure your agent's access. Connectors ship in minutes

One vault for every sales engagement tool. Salesloft today, Outreach and Apollo tomorrow.

01.

Shared tokens break per-user analytics

A shared token looks fine in a demo. In production every call looks like a service account. Scalekit resolves the real user credential so attribution, audit, and scope stay accurate.

// shared token
 audit → bot_service_account
 user_filter → broken

 // scalekit
 audit → user_abc
 scope → enforced ✓

02.

Authentication is not authorization

03.

Multi-tenancy is architectural

04.

Salesloft today. Others 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 Salesloft as the rep or a shared service account?

As the rep. Each sales rep authorizes once via OAuth and Scalekit resolves their credential at request time. Logged calls and emails appear under that rep's Salesloft identity, not a bot account, critical for accurate activity attribution and manager visibility.

Where is the Salesloft OAuth token stored?

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

Can I prevent the agent from sending emails or making calls autonomously?

Yes. Use listScopedTools to allow cadence step queries and prospect lookup without granting execution permissions. You control exactly which actions the agent can take, reads can be enabled without writes per user.

What happens when a rep revokes Salesloft access?

The connection is invalidated on the next tool call for that rep. Subsequent requests fail closed. Other reps in the team remain unaffected. The event is logged for audit.

Can the agent combine Salesloft with Salesforce or HubSpot in one workflow?

Yes. A single agent can query Salesloft for cadence status and sync results back to Salesforce or HubSpot in the same workflow. Each connector resolves under the same rep identity with its own vaulted credential.

Salesloft

Tools your sales agent reaches for on Salesloft, scoped per rep.