Close MCP

Live

OAUTH 2.0

CRM & SALES

Communication

Close is a CRM and sales platform. The Close MCP server provides a standardized interface that allows any compatible AI model or agent to access Close CRM...

  • Acts as the user: Every tool call runs as the authorizing user. Access and audit trail stay intact.
  • Credentials stay vaulted: AES-256 encrypted, resolved at request time, never stored in LLM context.
  • Scoped before every call: Per-user permissions enforced automatically. 90-day audit trail included.
Close MCP
agent · Acme Q3
Run
Activity Search in Close MCP
S
closemcp_activity_search
85ms
Close MCP agent
Search for activities. results are returned ordered by date descending. examples: - to list activities on a lead, use t.
Sources: Close MCP
closemcpmcp
1 tool call
18:29
Message Claude...

Close MCP tools for AI agents

CALL ANY TOOL
12 tools covering aggregation, activity, apply.
closemcp_activity_search
Search for activities. results are returned ordered by date
Search for activities. results are returned ordered by date descending. examples: - to list activities on a lead, use the lead_ids filter. - to list conversations, filter for calls and meetings.
Parameters
Name
Type
Required
Description
activity_at
string
Optional
Filter activities by the date/time the activity occurred.
activity_types
string
Optional
Filter by activity types. Valid values include activity.call, activity.email, activity.note, activity.meeting, activity.sms, activity.custom_activity, and others.
agent_config_ids
string
Optional
Filter by voice agent config IDs. Matches Call, Email, and SMS activities that carry an agent_config_id; other activity types are filtered out implicitly because the field is not indexed for them.
contact_ids
string
Optional
Filter by contact IDs. Only activities associated with these contacts will be returned.
cursor
string
Optional
Pagination cursor. Provide only when more results are requested from a previous response.
lead_ids
string
Optional
Filter by lead IDs. Only activities on these leads will be returned.
closemcp_aggregation
Perform an aggregation to answer questions like: - how many
closemcp_apply_voice_agent_update
Apply a previously proposed voice agent update. this tool p
closemcp_close_product_knowledge_search
Search close product documentation and knowledge base for re
closemcp_create_address
Add a new address to an existing lead (company).
closemcp_create_call_task
Schedule a call task on a lead, assigned to either a user or
closemcp_create_comment
Add a comment to a commentable object (note, call, opportuni
Python · LlamaIndex
from langchain_mcp_adapters.client import MultiServerMCPClient
from scalekit import ScalekitClient

client = ScalekitClient(env_url=ENV_URL, client_id=CLIENT_ID, client_secret=SECRET)
token = client.agent.get_token(user_id="user_id", connector="closemcp")

mcp = MultiServerMCPClient({
"closemcp": {
"url": "https://mcp.scalekit.com/closemcp",
"headers": {"Authorization": "Bearer " + token}
}
})
tools = await mcp.get_tools()
import OpenAI from "openai";
import { ScalekitClient } from "@scalekit-sdk/node";

const client = new ScalekitClient({ envUrl, clientId, clientSecret });
const token = await client.agent.getToken({ userId: "user_id", connector: "closemcp" });

const openai = new OpenAI();
// Connect to MCP at https://mcp.scalekit.com/closemcp
// Pass: Authorization: Bearer + token
import Anthropic from "@anthropic-ai/sdk";
import { ScalekitClient } from "@scalekit-sdk/node";

const client = new ScalekitClient({ envUrl, clientId, clientSecret });
const token = await client.agent.getToken({ userId: "user_id", connector: "closemcp" });

const anthropic = new Anthropic();
// Connect to MCP at https://mcp.scalekit.com/closemcp
// Pass: Authorization: Bearer + token
from google.adk.agents import LlmAgent
from scalekit import ScalekitClient

client = ScalekitClient(env_url=ENV_URL, client_id=CLIENT_ID, client_secret=SECRET)
token = client.agent.get_token(user_id="user_id", connector="closemcp")
# Connect to MCP at https://mcp.scalekit.com/closemcp
# Pass: Authorization: Bearer + token
Try these prompts
Paste any prompt into your agent to get started.
Get started
Copy the prompt
Copied
Update an existing task?
Copy the prompt
Copied
Perform a natural language search for leads or contacts?
Advanced
Copy the prompt
Copied
Schedule a voice agent to call a lead’s contact?
Copy the prompt
Copied
Return active users (memberships) which are part of the current org?
SEE HOW AUTH WORKS
User authorises once. Every agent call after uses their token with scope enforcement.
1
Authorize
Your user connects
Close MCP
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
Close MCP
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
Close MCP
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
Close MCP
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
See the same per-user auth pattern across other connectors.
ENGINEERING
Slack workflow agent (LangGraph)
LangGraph agent that drives multi-step Slack workflows: triggers, approvals, and follow-up actions per user identity.
OPS
Email-to-calendar scheduling agent
Parse scheduling intent from Gmail threads and create Google Calendar events with the right attendees and timezone.
Why Scalekit
Secure your agent's access. Connectors ship in minutes
Other connector libraries treat auth as a demo afterthought.
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.
// shared token
audit → bot_service_account

// scalekit
audit → user_abc ✓
02.
Authentication is not authorization
03.
Multi-tenancy is architectural
04.
One connector today. Ten 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 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 token 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 Close?
Yes. Pass a tool name filter to listScopedTools so the messaging agent only sees the subset you authorize. Pre-API-call scope checks block out-of-policy actions before the request reaches Close.

What happens when a user revokes Close 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 see leads owned by other reps?
Only if the authorizing user's Close role allows it. Admins see all leads; reps see their own plus shared views. Search, aggregation, and voice agent updates all inherit that scope.

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"": {
""closemcp"": {
""url"": ""https://mcp.scalekit.com/closemcp"",
""headers"": { ""Authorization"": ""Bearer $SCALEKIT_TOKEN"" }
}
}
}
Codex Code REPL
# ~/.codex/config.toml
[mcp_servers.closemcp]
url = ""https://mcp.scalekit.com/closemcp""
auth_env = ""SCALEKIT_TOKEN""
Copilot Code REPL
# .vscode/mcp.json
{
""servers"": {
""closemcp"": {
""url"": ""https://mcp.scalekit.com/closemcp"",
""type"": ""http""
}
}
}