Upstream MCP connector for AI agents

Tools your productivity agent reaches for on Upstream, scoped per user.

CALL ANY TOOL

Inbox automation end to end: read and triage threads, compose and generate drafts, manage splits, labels, rules, channels, and contacts. The token stays vaulted per user.

upstreammcp_list_channels

List channels

List all channels the user belongs to. channels are team shared spaces for organizing threads. returns channel ids, names, colors, member counts, and unread counts. use get-channel-threads to browse threads within a channel.

Parameters

Name

Type

Required

Description

—

No parameters required

upstreammcp_get_channel_threads

Get channel threads

upstreammcp_search_inbox

Search inbox

upstreammcp_create_channel

Create channel

upstreammcp_update_inbox_split

Update inbox split

upstreammcp_delete_inbox_split

Delete inbox split

upstreammcp_list_contacts

List contacts

upstreammcp_get_inbox_split_threads

Get inbox split threads

upstreammcp_create_inbox_split

Create inbox split

upstreammcp_update_rule

Update rule

upstreammcp_delete_rule

Delete rule

upstreammcp_list_draft_threads

List draft threads

upstreammcp_get_label_threads

Get label threads

upstreammcp_create_label

Create label

upstreammcp_update_settings

Update settings

upstreammcp_list_inbox_splits

List inbox splits

upstreammcp_get_self

Get self

upstreammcp_create_rule

Create rule

upstreammcp_list_labels

List labels

upstreammcp_list_org_members

List org members

upstreammcp_list_rules

List rules

upstreammcp_list_scheduled_threads

List scheduled threads

upstreammcp_list_sent_threads

List sent threads

upstreammcp_list_snoozed_threads

List snoozed threads

upstreammcp_list_spam_threads

List spam threads

upstreammcp_list_starred_threads

List starred threads

upstreammcp_list_trashed_threads

List trashed threads

upstreammcp_compose_thread

Compose thread

upstreammcp_done_thread

Done thread

upstreammcp_generate_draft

Generate draft

For more tools, view docs.

Build your Agent

Drop the toolkit in, point it at the user, and your agent can triage threads and draft replies 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: ["upstreammcp"], toolNames: ["upstreammcp_list_inbox_splits", "upstreammcp_get_inbox_split_threads", "upstreammcp_compose_thread"] },
  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: ["upstreammcp"], toolNames: ["upstreammcp_list_inbox_splits", "upstreammcp_get_inbox_split_threads", "upstreammcp_compose_thread"] },
  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: ["upstreammcp"], toolNames: ["upstreammcp_list_inbox_splits", "upstreammcp_get_inbox_split_threads", "upstreammcp_compose_thread"] },
  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/upstreammcp",
    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 running Upstream inbox automation from your workflows.

Triage

Copy the prompt

Copied

What is in my primary split that I have not replied to?

Copy the prompt

Copied

List threads labeled [label] from the last 7 days.

Copy the prompt

Copied

Mark thread [thread_id] as done and tell me what it was about.

Drafting

Copy the prompt

Copied

Generate a draft reply for thread [thread_id] and show it to me first.

Copy the prompt

Copied

Compose a new thread to [email] about the renewal date.

Copy the prompt

Copied

List my unsent drafts.

Automation rules

Copy the prompt

Copied

Create a rule that labels vendor invoices and moves them out of primary.

Copy the prompt

Copied

List existing rules and what each one matches.

Copy the prompt

Copied

Create a split for threads mentioning [keyword].

SEE HOW AUTH WORKS

Your users connect once. Their Upstream MCP credentials stay vaulted, every call is scope-checked, and every action is logged.

Authorize

Your user connects

Upstream 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

Store

Their

Upstream 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

Resolve

When your agent calls a

Upstream 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

Audit

Every

Upstream 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.

OPS

Email-to-calendar scheduling agent

Read scheduling intent out of Gmail threads, resolve mutual free time, and create the Google Calendar event.

Gmail

Google Calendar

View agent

ENGINEERING

Engineering standup agent

Pull commits from GitHub and GitLab, track Jira issue movement, and post a per-engineer standup brief to Slack.

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.

Upstream MCP 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 Upstream MCP 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 Upstream MCP bearer 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 Upstream MCP?

Yes. Pass a tool name filter to listScopedTools so the productivity agent only sees the subset you authorize. Pre-API-call scope checks block out-of-policy actions before the request reaches Upstream MCP.

What happens when a user revokes Upstream MCP 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 send email without me seeing it first?

Only if you expose the send tools. Draft generation is a separate tool from compose and send, so an assistant can be limited to reading and drafting. Every send is scope-checked before the Upstream call and logged against the authorizing user.

On this page

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