Outreach

Live

OAUTH 2.0

SALES ENGAGEMENT

Every prospect, sequence, and outreach activity your team runs lives in Outreach. Outreach MCP gives your agent authenticated access to sales engagement data scoped to the user who authorized it.

  • Acts as the user: Access and write actions stay tied to the Outreach account that authorized the agent.
  • Credentials stay vaulted: AES-256, resolved at request time, never in LLM context.
  • Scoped before every call: User permissions enforced. 90-day audit trail.
Outreach
agent · Acme Q3
Run
Which sequences have reply rates above 10% this month and how many prospects are active in each?
S
outreach_sequences_list
83ms
Sales engagement agent
3 sequences above 10% reply rate. Cold Outbound v3 (14.2%, 480 active), Champion Change (11.8%, 120 active), Re-Engage 90d (10.4%, 320 active). All outperforming the 8% org benchmark.
Sources: 3 sequences, this month
outreachmcp
3 sequences
18:29
Message Claude...

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

CALL ANY TOOL
List sequences and prospects, retrieve activity history, create new prospects, and track open tasks.
outreach_sequences_list
List sequences
List Outreach sequences with owner and active status filters.
Parameters
Name
Type
Required
Description
owner_id
integer
Optional
Filter by owner user ID
enabled
boolean
Optional
Filter by enabled status
limit
integer
Optional
Max sequences
outreach_prospects_list
List prospects
outreach_prospect_get
Get prospect
outreach_prospect_create
Create prospect
outreach_tasks_list
List tasks
Build your Agent
Drop the toolkit in, point it at the user, and your sales engagement agent can use Outreach 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: ["outreach"], toolNames: ["outreach_sequences_list", "outreach_prospects_list", "outreach_prospect_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: ["outreach"], toolNames: ["outreach_sequences_list", "outreach_prospects_list", "outreach_prospect_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: ["outreach"], toolNames: ["outreach_sequences_list", "outreach_prospects_list", "outreach_prospect_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/outreach",
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 using Outreach.
Sequences & prospects
Copy the prompt
Copied
List all active sequences.
Copy the prompt
Copied
Which sequences have reply rate above 10%?
Copy the prompt
Copied
List prospects in [sequence name].
Copy the prompt
Copied
Get activity for prospect [email].
Action & creation
Copy the prompt
Copied
Create a prospect: [name], [email], account [id].
Copy the prompt
Copied
List open tasks assigned to me.
Copy the prompt
Copied
Find prospects with no activity in 14 days.
Copy the prompt
Copied
Get stats for [sequence name].
Reporting
Copy the prompt
Copied
Top 3 sequences by reply rate this month.
Copy the prompt
Copied
Prospect reply rate by owner.
Copy the prompt
Copied
Which accounts have most active prospects?
Copy the prompt
Copied
Tasks overdue today.
SEE HOW AUTH WORKS
Users authorize Outreach once. Their credentials stay vaulted, every call is checked, and every action is logged.
1
Authorize
Your user connects
Outreach
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
Outreach
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
Outreach
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
Outreach
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 agents and MCP connectors. Working code, live demos, fork what fits.
SALES
Outbound prospecting agent
Build targeted prospect lists with Apollo, enrich with firmographic data, and draft personalised outreach. Runs on a schedule.
SALES
Sales call prep agent
Pull Granola notes and Attio contact history to draft a pre-call brief before every sales meeting. Zero rep input.
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 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.
Outreach 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 Outreach 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 Outreach 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 Outreach?
Yes. Pass a tool name filter to listScopedTools so the sales engagement agent only sees the subset you authorize. Pre-API-call scope checks block out-of-policy actions before the request reaches Outreach.
What happens when a user revokes Outreach 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.
Can the agent enroll prospects into sequences owned by other reps?
Only if the authorizing user has the Outreach permissions to manage others' sequences. Admins and managers can enroll into team sequences; reps are limited to their own. Outreach role-based permissions carry over to every agent call.
Start in your coding agent
Up and running in one command
Install the Scalekit skill in your editor of choice. Connector, auth, tools, prompt, all wired up
Claude Code REPL
/plugin marketplace add scalekit-inc/claude-code-authstack
/plugin install agentkit@scalekit-auth-stack
Cursor Code REPL
# ~/.cursor/mcp.json
{
""mcpServers"": {
""outreach"": {
""url"": ""https://mcp.scalekit.com/outreach"",
""headers"": { ""Authorization"": ""Bearer $SCALEKIT_TOKEN"" }
}
}
}
Codex Code REPL
# ~/.codex/config.toml
[mcp_servers.outreach]
url = ""https://mcp.scalekit.com/outreach""
auth_env = ""SCALEKIT_TOKEN""
Copilot Code REPL
# .vscode/mcp.json
{
""servers"": {
""outreach"": {
""url"": ""https://mcp.scalekit.com/outreach"",
""type"": ""http""
}
}
}