Gmail

Live

OAUTH 2.0

EMAIL

Communication

Inboxes are where context lives and deals die in silence. Your agent can search threads, draft replies, and read attachments, scoped to the inbox the user authorized.

  • Acts as the user: Email access and send actions stay tied to the Gmail 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.
Gmail
agent · Acme Q3
Run
Find all unread emails from enterprise customers this week and summarize them.
S
gmail_fetch_mails
81ms
Inbox agent
4 unread enterprise emails this week: Acme (renewal intent, needs pricing deck), Globex (integration question, reply needed), Initech (contract redline attached), Umbrella (upsell interest flagged).
Sources: 4 emails, Oct 28 to Nov 1
gmailmcp
4 emails
18:29
Message Claude...

Tools your inbox agent reaches for on Gmail, scoped per user.

CALL ANY TOOL
Read emails, send replies, search messages, and manage labels. Same toolkit, every framework, no auth plumbing.
gmail_fetch_mails
Fetch emails
Fetch messages from any label or inbox with optional search query and pagination.
Parameters
Name
Type
Required
Description
query
string
Optional
Gmail search query (e.g. is:unread from:acme.com)
label_ids
array
Optional
Array of label IDs to filter by
max_results
integer
Optional
Max messages to return (default 10)
page_token
string
Optional
Pagination token for next page
gmail_get_message
Get message
gmail_send_message
Send email
gmail_search_messages
Search messages
gmail_labels_list
List labels
gmail_label_message
Apply label
Build your Agent
Drop the toolkit in, point it at the user, and your agent can read, search, and send Gmail messages 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: ["gmail"], toolNames: ["gmail_fetch_mails", "gmail_search_messages", "gmail_send_message"] },
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: ["gmail"], toolNames: ["gmail_fetch_mails", "gmail_search_messages", "gmail_send_message"] },
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: ["gmail"], toolNames: ["gmail_fetch_mails", "gmail_search_messages", "gmail_send_message"] },
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/gmail",
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 reading and acting on Gmail.
Search & recall
Copy the prompt
Copied
Find all unread emails from [domain] this week.
Copy the prompt
Copied
Search for emails about [topic] from [person].
Copy the prompt
Copied
List all emails with attachments received today.
Copy the prompt
Copied
Find the last email thread with [person name].
Action & replies
Copy the prompt
Copied
Send an email to [address] with subject [subject]: [body].
Copy the prompt
Copied
Reply to the latest email from [person]: [reply text].
Copy the prompt
Copied
Mark all emails from [sender] as read.
Copy the prompt
Copied
Archive all emails older than 30 days in [label].
Triage & organization
Copy the prompt
Copied
Summarize all unread emails from the last 24 hours.
Copy the prompt
Copied
List emails that need a reply and have been waiting more than 2 days.
Copy the prompt
Copied
Find all emails with invoices or billing in the subject.
Copy the prompt
Copied
What did [person] email me about last week?
SEE HOW AUTH WORKS
Users authorize Gmail once. Their Google credentials stay vaulted, every call is checked, and every action is logged.
1
Authorize
Your user connects
Gmail
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
Gmail
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
Gmail
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
Gmail
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 inbox agents and MCP connectors. Working code, live demos, fork what fits.
OPS
Email-to-calendar scheduling agent
Parse scheduling intent from Gmail threads and create Google Calendar events with the right attendees and timezone.
GTM
Salesforce customer insights agent
Surface Salesforce account activity, NPS signals, and renewal flags into Slack threads for the account team.
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.
Replies sent from the wrong identity
A shared Gmail token looks fine in a demo. In production, every email read or sent looks like it came from a service account. Audit logs break. Per-user scoping breaks. Scalekit resolves the credential of the actual user who triggered the agent, never a shared bot.
// shared bot token
token = "sk_gmail-mcp_shared_xxx"
audit → bot_service_account
user_filter → broken

// scalekit · per-user
token = resolve(user_id)
audit → user_abc
scope → enforced ✓
02.
Authentication is not authorization
03.
Multi-tenancy is architectural
04.
Gmail today. Outlook, Slack, Teams 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 Gmail 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 Gmail 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 Gmail?
Yes. Pass a tool name filter to listScopedTools so the inbox agent only sees the subset you authorize. Pre-API-call scope checks block out-of-policy actions before the request reaches Gmail.
What happens when a user revokes Gmail 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.
Does sending an email show as the user or a bot?
As the user. Outbound emails come from the authorizing user's address with proper From, Reply-To, and DKIM. Audit logs attribute the send to that user, not a service account.
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"": {
""gmail"": {
""url"": ""https://mcp.scalekit.com/gmail"",
""headers"": { ""Authorization"": ""Bearer $SCALEKIT_TOKEN"" }
}
}
}
Codex Code REPL
# ~/.codex/config.toml
[mcp_servers.gmail]
url = ""https://mcp.scalekit.com/gmail""
auth_env = ""SCALEKIT_TOKEN""
Copilot Code REPL
# .vscode/mcp.json
{
""servers"": {
""gmail"": {
""url"": ""https://mcp.scalekit.com/gmail"",
""type"": ""http""
}
}
}