Close MCP | OAuth Close connector for AI agents

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

CALL ANY TOOL

List leads and tasks, create opportunities, log calls and emails, and update pipeline.

close_leads_list

List leads

List Close leads with status, owner, and search filters.

Parameters

Name

Type

Required

Description

query

string

Optional

Search query

status_id

string

Optional

Lead status ID filter

limit

integer

Optional

Max leads

close_lead_get

Get lead

close_lead_create

Create lead

close_opportunity_create

Create opportunity

close_activity_create

Log activity

close_tasks_list

List tasks

Build your Agent

Drop the toolkit in, point it at the user, and your sales agent can use Close 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: ["close"], toolNames: ["close_leads_list", "close_lead_get", "close_lead_create"] },
  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: ["close"], toolNames: ["close_leads_list", "close_lead_get", "close_lead_create"] },
  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: ["close"], toolNames: ["close_leads_list", "close_lead_get", "close_lead_create"] },
  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/close",
    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 Close.

Search & recall

Copy the prompt

Copied

Find leads at [company name].

Copy the prompt

Copied

List leads with status [status].

Copy the prompt

Copied

Show opportunities owned by [user].

Copy the prompt

Copied

Which leads have no activity in 14+ days?

Action & updates

Copy the prompt

Copied

Create a lead: [company], [contacts].

Copy the prompt

Copied

Log a call on [lead]: [notes].

Copy the prompt

Copied

Update opportunity on [lead] to value [$amount].

Copy the prompt

Copied

Create a task: follow up with [lead] by [date].

Pipeline & reporting

Copy the prompt

Copied

Total pipeline value by owner this quarter.

Copy the prompt

Copied

Lead velocity by source last month.

Copy the prompt

Copied

Find leads with multiple opportunities.

Copy the prompt

Copied

Tasks overdue today across the team.

SEE HOW AUTH WORKS

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

Authorize

Your user connects

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

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

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

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

CRM AI agent

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

HubSpot

Salesforce

View agent

SALES

Deal intelligence agent

Combine Gong, Attio, and Slack signals to surface deal risks and next-best actions. Updated after every call.

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.

Lead updates lose rep attribution

A shared Close token looks fine in a demo. In production, every lead update and activity log looks like it came from a service account. Rep attribution breaks. Pipeline ownership breaks. Scalekit resolves the actual user's token so every Close action is attributed to the right rep.

// 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.

Close today. HubSpot, Salesforce, Attio 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

On this page

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

Frequently Asked Questions

Does the agent access Close 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 Close oauth 2.0 stored?

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

What happens when a user revokes Close access?

Can the agent see leads owned by other reps?

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

Copy Copied

/plugin marketplace add scalekit-inc/claude-code-authstack
/plugin install agentkit@scalekit-auth-stack

Cursor Code REPL

Copy Copied

# ~/.cursor/mcp.json
{
""mcpServers"": {
""close"": {
""url"": ""https://mcp.scalekit.com/close"",
""headers"": { ""Authorization"": ""Bearer $SCALEKIT_TOKEN"" }
}
}
}

Codex Code REPL

Copy Copied

# ~/.codex/config.toml
[mcp_servers.close]
url = ""https://mcp.scalekit.com/close""
auth_env = ""SCALEKIT_TOKEN""

Copilot Code REPL

Copy Copied

# .vscode/mcp.json
{
""servers"": {
""close"": {
""url"": ""https://mcp.scalekit.com/close"",
""type"": ""http""
}
}
}