Skip to content

Integrations

Everything your agent needs to actually do something.

200+ built-in tools, 1,000+ MCP integrations, and a custom tool builder for everything else. Auth handled, permissions scoped per agent, observability included. Connect to the systems your team already runs - not the ones you wish you ran.

The integration layer your agents need - without the integration project.

1,000+
MCP integrations
200+
Built-in tools
1-click
OAuth setup
Per-agent
Permissions scoped

The tool surface

Built-in. MCP. Custom. Pick your altitude.

There are three ways an agent can take action. Use a pre-built tool that ships with AgentX. Plug in any of the 1,000+ MCP servers in the marketplace. Or write your own - with the in-platform custom tool builder when something doesn't exist yet.

01

Built-in Tools

Tools that ship with the platform. Document generation (PDF, Excel, Slides). Image and video generation. Lead capture and CRM forwarding. Scheduling and calendar. Email send. 200+ tools, zero setup. Toggle on per agent.

02

MCP Integrations

Pre-configured Model Context Protocol servers. Salesforce, HubSpot, Slack, GitHub, Notion, Stripe, PostgreSQL, Mailchimp, and 1,000+ more. One-click install. OAuth or API key auth. Updates and security patches managed by us.

03

Custom Tools

When something doesn't exist yet, write it. In-platform Python editor. Vibe-code via natural language ("build me a tool that verifies SAT CFDI tax IDs"). Test, version, deploy - all inside the same workspace.

Built-in

200+ tools that ship turned off until your agent needs them.

Every AgentX workspace has the full catalog available. Toggle a tool on for an agent and it's part of the agent's capability surface. Most are zero-config - a few need an API key for the underlying service.

See all 200+ built-in tools
  • All
  • Document
  • Media
  • Capture
  • Schedule
  • Communication
  • Productivity
  • PDF Generator

    High-quality PDF creation from agent output.

    Enable
  • Excel Generator

    Spreadsheets with formulas and formatting.

    Enable
  • Slides Generator

    Presentations from agent content.

    Enable
  • Image Generator

    Text-to-image generation.

    Enable
  • Video Generator

    Text-to-video generation.

    Enable
  • Office Generators

    DOCX, XLSX, PPTX bundle.

    Enable
  • Lead Capture

    Inbound lead form with CRM forwarding.

    Enable
  • Google Sheets

    Read/write sheets directly.

    Enable
  • Google Calendar

    Create, modify, delete events.

    Enable
  • Calendly

    Manage and display bookings.

    Enable
  • Mailchimp Send

    Marketing email send + lists.

    Enable
  • Web Tool

    Fetch and parse web pages.

    Enable

MCP marketplace

1,000+ integrations. One-click install. No glue code.

Model Context Protocol is the open standard for AI agent integrations. We host the largest curated MCP marketplace - every server tested, versioned, and updated. Install with one click. Auth via OAuth or API key. Permissions scoped per agent.

  • Featured
  • CRM
  • Communication
  • Cloud & DB
  • Productivity
  • E-commerce
  • Dev Tools
  • Marketing
  • Finance & Data
  • Salesforce
  • HubSpot
  • Slack
  • Mailchimp
  • PostgreSQL
  • MongoDB
  • Astra DB
  • Notion
  • Google Sheets
  • Stripe
  • GitHub
  • GitLab
  • Playwright
  • ActiveCampaign
  • AirTable
  • Alphavantage
  • Yahoo Finance
  • Google Calendar

Always up to date

Servers are managed centrally. Security patches, API updates, breaking change migrations - handled. You don't maintain integrations.

Auth managed

OAuth flows, API key vaults, token refresh - handled per workspace. Credentials never reach individual agents.

Open source

AgentX maintains an open-source MCP server collection on GitHub. Want a specific integration? Request it or build it.

Custom

When something doesn't exist yet, write it.

Most platforms make you wait for the integration team to ship support for the API you actually need. AgentX gives you the editor. Write Python directly - or describe what you want in natural language and let the platform write it for you. Test it in the same workspace. Version it. Share it across agents.

  • Write Python directly or describe what you need in plain English.
  • Test cases auto-generated, runnable from the editor.
  • Version-controlled and shareable across agents in a workspace.
  • Custom tools follow the same auth, permission, and audit model as built-ins.

Under the hood

Tool calls aren't magic. They're scoped, audited, and observable.

The interesting questions about an integration aren't “is it on the list” - they're “who can call it, what data does it see, and what happens when it fails.” Every tool call on AgentX, whether built-in, MCP, or custom, runs through the same auth and observability layer.

  1. Stage 1

    Agent decides

    Agent calls a tool. Permission check fires.

  2. Security · Stage 2

    Permission gate

    Workspace policy + per-agent allow-list.

  3. Security · Stage 3

    Auth layer

    OAuth/API key from workspace vault.

  4. Stage 4

    Tool execution

    Built-in, MCP, or custom function.

  5. Stage 5

    Response handling

    Return to agent + log to audit trail.

  6. Stage 6

    Trace event

    Recorded in observability layer.

Security perimeter spans stages 2–3.

Per-agent permissions

An agent can only call tools it's explicitly allowed to call. A customer support agent can't suddenly query your production database. Permissions defined at agent creation, modifiable per environment.

Auth at the workspace, not the agent

OAuth tokens and API keys live in a workspace vault - encrypted at rest, never exposed to the agent context. Tool calls happen on the agent's behalf, not with the agent's credentials.

Every call logged

Tool name, parameters, response, latency, cost. Searchable for 90 days (longer on Enterprise). Exportable. Audit-ready.

Fail-safe by default

Rate-limited tools queue with backoff. Failed tools route to fallback or human queue. No tool failure causes silent agent breakdown - every error is observable.

Built for real users

Integration security isn't a separate feature. It's how integrations work.

Every integration - built-in, MCP, or custom - runs under the same controls. There's no “secure mode” toggle. There's just the way the platform works.

Workspace credential vault

All API keys, OAuth tokens, and secrets encrypted at rest. Never visible in agent context. Never logged in plain text.

Secure execution sandbox

Custom Python tools run in isolated sandboxes. No filesystem access outside designated paths. No network calls outside whitelisted endpoints (configurable per workspace).

Tool-call audit trail

Every tool call logged with full context. SOC 2 audit ready. Export to your SIEM via OTel or syslog.

On-prem MCP support

Run MCP servers inside your perimeter. AgentX agents connect to on-prem servers without your data leaving your environment.

Get started

Plug it in. Build something real.

Free to start. Full integration catalog available on every tier. Custom tools on Solo Builder and up. Enterprise gets on-prem MCP support and dedicated integration support.

Free

$0

/ forever

Build and test your first agent.

Solo Builder

$49

/ month

Solo builders shipping production agents.

Professional/Business

$199 - $299

/ month

Agencies and service teams with white-label deployment.

Enterprise

Custom

scoped per process

On-prem, SSO, dedicated infrastructure.

Start Your AI Automation Journey Today

Sign up for AgentX and let AI handle your routine tasks - no credit card needed.