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.
Integrations
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.
The tool surface
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.
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.
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.
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
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.
High-quality PDF creation from agent output.
EnableSpreadsheets with formulas and formatting.
EnablePresentations from agent content.
EnableText-to-image generation.
EnableText-to-video generation.
EnableDOCX, XLSX, PPTX bundle.
EnableInbound lead form with CRM forwarding.
EnableRead/write sheets directly.
EnableCreate, modify, delete events.
EnableManage and display bookings.
EnableMarketing email send + lists.
EnableFetch and parse web pages.
EnableMCP marketplace
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.
Servers are managed centrally. Security patches, API updates, breaking change migrations - handled. You don't maintain integrations.
OAuth flows, API key vaults, token refresh - handled per workspace. Credentials never reach individual agents.
AgentX maintains an open-source MCP server collection on GitHub. Want a specific integration? Request it or build it.
Custom
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.
Under the hood
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.
Stage 1
Agent calls a tool. Permission check fires.
Security · Stage 2
Workspace policy + per-agent allow-list.
Security · Stage 3
OAuth/API key from workspace vault.
Stage 4
Built-in, MCP, or custom function.
Stage 5
Return to agent + log to audit trail.
Stage 6
Recorded in observability layer.
Security perimeter spans stages 2–3.
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.
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.
Tool name, parameters, response, latency, cost. Searchable for 90 days (longer on Enterprise). Exportable. Audit-ready.
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
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.
All API keys, OAuth tokens, and secrets encrypted at rest. Never visible in agent context. Never logged in plain text.
Custom Python tools run in isolated sandboxes. No filesystem access outside designated paths. No network calls outside whitelisted endpoints (configurable per workspace).
Every tool call logged with full context. SOC 2 audit ready. Export to your SIEM via OTel or syslog.
Run MCP servers inside your perimeter. AgentX agents connect to on-prem servers without your data leaving your environment.
Get started
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.
$199 - $299
/ month
Agencies and service teams with white-label deployment.
Sign up for AgentX and let AI handle your routine tasks - no credit card needed.