Aerostack
Aerostack
Aerostack MCP for AI Agents

One MCP URL.
Any AI agent.
Full infrastructure.

Copy the Aerostack MCP into Claude Code, Cursor, OpenClaw, CrewAI, or any MCP-compatible agent. Your agent gets 16 tools to build functions, deploy MCPs, create bots, compose workspaces, and wire up workflows — without ever leaving the conversation.

mcp-config.json
{
  "mcpServers": {
    "aerostack": {
      "url": "https://mcp.aerostack.dev",
      "headers": {
        "Authorization": "Bearer your_api_key"
      }
    }
  }
}

That's it. Your agent now has full infrastructure access.

Get Your MCP KeyRead the Guide
Claude CodeCursorWindsurfOpenClawCrewAIAutoGPTLangChainAny MCP Client
//16 Tools

Everything your agent needs. Built in.

Your agent gets a complete infrastructure toolkit. No SDKs, no API docs, no boilerplate — just tool calls.

Discover & Plan
plan()

Analyze any integration request — find MCPs, detect gaps, get a credential checklist

capabilities()

Inspect any MCP or service — tools, auth requirements, schemas

guide()

Context-aware help on setup, credentials, node types, platform config

Build & Deploy
scaffold()

Describe what you want in plain English → get a ready-to-create config

create()

Create bots, workflows, functions, endpoints, webhooks — code auto-deployed to edge

deploy()

Push to live — register bot webhooks, activate workflows, push functions to 300+ cities

Integrate & Compose
setup_integration()

One call: create workspace, add MCPs, store encrypted secrets, verify health

generate_workflow()

Auto-discover tools in workspace, build trigger → source → transform → destination graph

build_spec()

Generate MCP server templates for any API — boilerplate, tool stubs, marketplace metadata

Test & Iterate
test()

Test-run any resource with a payload — get per-node execution logs back

validate()

Validate configs before deploying — catch disconnected nodes, missing fields, syntax errors

publish()

Ship to the Aerostack marketplace — auto-checked for quality, discoverable by other agents

//How It Works

From idea to production. One conversation.

Your agent handles every step — from discovery to deployment. No dashboards, no config files, no manual wiring.

01

Describe what you need

Tell your agent in natural language. "Connect my Notion to Slack." "Build a support bot." "Deploy a webhook that enriches leads."

02

Agent plans the architecture

Searches the marketplace, detects gaps, identifies missing integrations, and returns a structured execution plan with credential requirements.

03

Agent builds what's missing

No MCP for the API you need? Agent generates one from scratch — boilerplate, tool stubs, tests. Deploys custom functions to the edge.

04

Agent composes & deploys

Creates workspace, adds MCPs, stores encrypted secrets, generates workflow, validates, tests, and pushes to live — all in one conversation.

05

You get a production URL

One workspace URL with everything composed. Share with your team, connect to other agents, or embed in your product.

//Use Cases

What can agents actually build?

Real conversations. Real infrastructure. Your agent handles the entire lifecycle — from planning to deployment.

Instant Integrations
U

Connect my Notion workspace to Slack — post a summary of new pages every morning at 9am.

A

Let me plan this integration...

plan("Connect Notion to Slack, post new pages daily at 9am")
A

Found both MCPs. Setting up your workspace with encrypted credentials...

setup_integration({ name: "Notion → Slack", servers: [...], secrets: {...} })
A

Generating the workflow — cron trigger at 9am, read new Notion pages, summarize with LLM, post to Slack...

generate_workflow({ intent: "Read new Notion pages, summarize, post to Slack", schedule: "0 9 * * *" })
A

Deployed. Every morning at 9am, your Slack channel will get a summary of new Notion pages. Here's the workflow ID if you want to edit it later.

//Beyond MCP Config

Use in your code.

Already building with OpenAI, LangChain, or Vercel AI? Drop in our SDK — same workspace tools, native integration.

agent.ts
import { openai } from '@ai-sdk/openai';
import { generateText } from 'ai';
import { getTools } from '@aerostack/sdk-vercel-ai';

const { tools } = await getTools({
  workspace: 'my-workspace',
  token: 'mwt_...',
});

// Tools auto-execute — no manual handling needed
const { text } = await generateText({
  model: openai('gpt-4o'),
  tools,
  maxSteps: 5,
  prompt: 'Deploy mcp-stripe and create a payment webhook',
});

npm install

@aerostack/sdk-vercel-ai

npm install

@aerostack/sdk-langchain

npm install

@aerostack/sdk-openai

//Zero Gaps

No MCP? No problem. Agent builds it.

If an integration doesn't exist on the marketplace, your agent creates one on the fly. Build, deploy, and compose — all in the same conversation.

Post to Ocoya (social media)

auto-built

Agent generates MCP server → deploys → adds to workspace

Read from Airtable

on Hub

Agent finds mcp-airtable on Hub → installs → ready to use

Custom lead scoring logic

auto-built

Agent writes edge function → deploys → composes into workflow

Slack notifications

on Hub

Agent finds mcp-slack on Hub → installs with webhook URL

Internal company API

auto-built

Agent generates proxy MCP → wraps your API → encrypted secrets

Stripe payments

on Hub

Agent finds mcp-stripe on Hub → installs with API key

Marketplace has it?install()
Doesn't exist?build_spec() → create() → deploy()
Tool-Level PermissionsNew

Giving agents infrastructure access? Control exactly which tools they can use. Block destructive operations at the platform level.

Learn more

Give your agent
superpowers.

Get your API key, paste the MCP config, and your agent can build, deploy, and compose anything on Aerostack's infrastructure. Start free.

mcp-config.json
{
  "mcpServers": {
    "aerostack": {
      "url": "https://mcp.aerostack.dev",
      "headers": {
        "Authorization": "Bearer YOUR_API_KEY"
      }
    }
  }
}
Get Your API Key — FreeFull Documentation