Airops MCP

CALL ANY TOOL

API key scoped per user. Every workflow run attributed to the authorizing team member.

airops_workflow_run

Run workflow

Execute an Airops AI workflow with custom inputs and retrieve structured outputs, following the team's brand and content guidelines.

Parameters

Name

Type

Required

Description

workflow_id

string

Required

Airops workflow identifier

inputs

object

Required

Key-value pairs of workflow input variables

async_mode

boolean

Optional

Run asynchronously and poll for results

airops_brand_kit_get

Get brand kit

airops_templates_list

List templates

airops_output_get

Get workflow output

airops_documents_create

Create document

Build your Agent

Drop the toolkit in, point it at the authorized team member, and your agent can run Airops workflows and access brand kits 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: ["airopsmcp"], toolNames: ["airops_workflow_run", "airops_brand_kit_get", "airops_templates_list"] },
  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: ["airopsmcp"], toolNames: ["airops_workflow_run", "airops_brand_kit_get", "airops_templates_list"] },
  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: ["airopsmcp"], toolNames: ["airops_workflow_run", "airops_brand_kit_get", "airops_templates_list"] },
  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/airopsmcp",
    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 content agent to start running Airops workflows and accessing brand assets.

Search & recall

Copy the prompt

Copied

List all content templates available in my workspace.

Copy the prompt

Copied

Get our brand voice guidelines and approved terminology.

Copy the prompt

Copied

Show the last 5 workflow runs and their output status.

Action & create

Copy the prompt

Copied

Run the [workflow name] workflow with these inputs: [inputs].

Copy the prompt

Copied

Generate a blog post draft for [topic] using our brand voice template.

Copy the prompt

Copied

Create social media captions for [campaign] following our brand guidelines.

SEE HOW AUTH WORKS

Team members authorize Airops once. Their API key stays vaulted, every workflow run is scoped to their workspace permissions, and every action is logged.

1

Authorize

Your user connects

Airops 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

Airops 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

Airops 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

Airops 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

Same per-user auth pattern across other content and AI workflow connectors.

No items found.

Why Scalekit

Secure your agent's access. Connectors ship in minutes

One vault for every content connector. Airops today, Notion and Google Docs tomorrow.

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.

Airops 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 use a shared Airops key or per-user keys?

Per-user keys. Each team member provisions their own Airops API key and Scalekit vaults it under their identity. Workflow runs are attributed to that user, not a shared team credential.

Where is the Airops API key stored?

In Scalekit's AES-256 vault, namespaced per tenant. Keys resolve at request time and never appear in prompts, logs, or LLM completions.

Can I restrict which Airops workflows the agent can execute?

Yes. Use listScopedTools with a tool name filter to allow only specific workflow types, for example, email drafting but not social media publishing, for a given user.

What happens when a user's Airops key is revoked?

The next tool call fails closed for that user with a clear error. Other users in the workspace continue unaffected. Revocation is logged with a timestamp.

Can one agent run Airops workflows for multiple users?

Yes. Scalekit resolves the credential for each user identifier at call time. A single agent deployment serves all users in a tenant, each with their own scoped Airops access.

Tools your content agent reaches for on Airops, scoped per team member.