Salesloft MCP | OAuth 2.0 Salesloft connector for AI agents

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

CALL ANY TOOL

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

salesloft_account_stages_list

List account stages

Fetch the account pipeline stages configured in Salesloft -- useful context for interpreting or setting an account's company_stage_id. The records can be filtered, paged, and sorted.

Parameters

Name

Type

Required

Description

created_at_gt

string

Optional

Filter stages created after this ISO8601 timestamp (exclusive)

created_at_lt

string

Optional

Filter stages created before this ISO8601 timestamp (exclusive)

ids

string

Optional

Filter by specific account stage IDs. Comma-separated list of IDs.

include_paging_counts

boolean

Optional

Whether to include total count and page count in the response metadata

limit_paging_counts

boolean

Optional

Specifies whether the max limit of 10k records should be applied to pagination counts

name

string

Optional

Filter account stages by name.

page

integer

Optional

Page number for pagination, starting from 1

per_page

integer

Optional

Number of results per page in the range [1, 100]. Defaults to 25.

sort_by

string

Optional

Field to sort results by. Common values: name, created_at, updated_at. Defaults to updated_at.

sort_direction

string

Optional

Direction of sort: ASC or DESC. Defaults to DESC.

updated_at_gt

string

Optional

Filter stages updated after this ISO8601 timestamp (exclusive)

updated_at_lt

string

Optional

Filter stages updated before this ISO8601 timestamp (exclusive)

salesloft_account_upserts_create

Create account upserts

Create or update an account record in a single call: Salesloft looks up an existing account using the field named by upsert_key (matched against the value you supply for that same field in this request) and updates it if found, or creates a new account if not. Create and update behavior is otherwise the same as the individual create/update endpoints.

Parameters

Name

Type

Required

Description

upsert_key

string

Required

The field name Salesloft should use to look up an existing account. The value for that same field must also be included in this request. Accepted values: id, domain, crm_id.

account_tier_id

integer

Optional

ID of the Account Tier for this account

city

string

Optional

City where the account is located

company_stage_id

integer

Optional

ID of the CompanyStage assigned to this account

company_type

string

Optional

Type of company (e.g. prospect, customer, partner)

conversational_name

string

Optional

Conversational name of the company (e.g. Acme instead of Acme Corporation)

country

string

Optional

Country where the account is located

crm_id

string

Optional

CRM record ID for this account. Requires crm_id_type. Required if using crm_id as the upsert_key.

crm_id_type

string

Optional

The CRM that the provided crm_id is for. Must be: salesforce

custom_fields

object

Optional

Custom fields defined by the team. Only fields with values appear in the API.

description

string

Optional

Description of the account

do_not_contact

boolean

Optional

If true, the account will be marked as do not contact

domain

string

Optional

Domain of the account (e.g. acmecorp.com). Required if using domain as the upsert_key, and required when creating a new account.

founded

string

Optional

Date or year of founding

integer

Optional

The Salesloft ID of the account to match on. Required if using id as the upsert_key.

industry

string

Optional

Industry of the account

linkedin_url

string

Optional

LinkedIn page URL for the account

locale

string

Optional

Time locale for the account

name

string

Optional

Name of the account/company. Required when creating a new account.

owner_id

integer

Optional

ID of the user who owns this account

phone

string

Optional

Phone number for the account

postal_code

string

Optional

Postal/ZIP code of the account

revenue_range

string

Optional

Revenue range of the account

size

string

Optional

Number of employees at the account

state

string

Optional

State or region where the account is located

street

string

Optional

Street address of the account

tags

array

Optional

Updated tags applied to this person

title

string

Optional

Updated job title of the person

twitter_handle

string

Optional

Updated Twitter handle of the person (without @)

work_city

string

Optional

Updated work city of the person

work_country

string

Optional

Updated work country of the person

work_state

string

Optional

Updated work state or region of the person

salesloft_person_stages_list

List person stages

salesloft_successes_list

List successes

salesloft_tasks_create

Create tasks

salesloft_tasks_get

Get tasks

salesloft_users_get

Get users

salesloft_users_list

List users

Fetch multiple user records from Salesloft. Non-admin users will only see their own user or all on team depending on group visibility policy.

Parameters

Name

Type

Required

Description

active

boolean

Optional

Filter users by active status. Defaults to not applied.

calendar_connection_status

boolean

Optional

Filter users by calendar connection status. True returns only users with a connected calendar; false returns only users without.

emails

string

Optional

Filter users by exact email address match. Comma-separated list for multiple values.

group_id

string

Optional

Filter users by group ID. Comma-separated list. Use _is_null to filter users not in any group.

guid

string

Optional

Filter users by GUID. Comma-separated list for multiple values.

has_crm_user

boolean

Optional

Filter users by whether they have a CRM user mapped

ids

string

Optional

Filter by specific user IDs. Comma-separated list of IDs.

include_calendar_connection_status

boolean

Optional

Whether to include calendar connection status in the response. When true, adds a calendar_connection_status object to each user.

include_paging_counts

boolean

Optional

Whether to include total count and page count in the response metadata

last_login

string

Optional

Filter users based on last login time

managed_ar

boolean

Optional

Filter users based on whether they manage Automation Rules

manager_user_guid

string

Optional

Filter users by their manager's user GUID. Comma-separated list for multiple values.

page

integer

Optional

Page number for pagination, starting from 1

per_page

integer

Optional

Number of results per page in the range [1, 100]. Defaults to 25.

permissions

string

Optional

Filter users by specific permissions. Comma-separated list for multiple values.

role_id

string

Optional

Filter users by role ID. Comma-separated list for multiple values.

string

Optional

Space-separated keywords to search First Name, Last Name, or Email (case-insensitive substring match)

seat_package

string

Optional

Filter users by assigned license. Comma-separated list for multiple values.

sort_by

string

Optional

Field to sort results by. Accepted values: id, seat_package, email, name, group, last_login, role. Defaults to id.

sort_direction

string

Optional

Direction of sort: ASC or DESC. Defaults to DESC.

visible_only

boolean

Optional

When true, only shows users actionable based on team privacy settings. When false, shows all users including deactivated. Defaults to true.

work_country

string

Optional

Filter users by assigned work country. Comma-separated list for multiple values.

For more tools, view docs.

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.

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 });

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 }],
});

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.

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

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

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

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.

GTM and RevOps Teams

CRM AI agent

Reads the Granola transcript after every call, extracts next steps and updates the HubSpot record, drafts the follow-up in Gmail, and confirms in Slack, all on the rep's own delegated OAuth.

GTM and RevOps Teams

Deal intelligence agent

Pulls recent Gong calls, scores deal risk with an LLM, cross-references the record in Attio, and DMs each owner their at-risk deals in Slack. Every read is scoped to that rep's own access.

GTM and RevOps Teams

Sales call prep agent

Reads tomorrow's calls from Google Calendar, mines past Granola notes and Attio history for context, and delivers each rep a prep brief in Slack, scoped to the calls that rep actually owns.

GTM and RevOps Teams

Outbound prospecting agent

Searches Apollo for prospects matching your ICP, scores and ranks them, drafts personalized outreach in Gmail, and logs every send to Google Sheets. Mail goes out as the rep, not from a shared inbox.

Why Scalekit

Secure your agent's access. Connectors ship in minutes

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.

On this page

Tool and actions Framework Compatibility Starter Prompt Auth Lifecycle Try Other Agents Why Scalekit