Metorial Products | The Platform for the AI Workforce

Product

Portals

Metorial Portals lets employees connect AI agents to the integrations and skills your company already uses. People sign in with company SSO and connect through one Magic MCP URL. Admins decide who gets access to what.

Browse
A catalog of approved tools and skills
Employees open Metorial Portals to find the integrations and skills your company approved, in one familiar place, with no setup to figure out.
Connect
One link to start working
People connect their agent through a single Magic MCP URL and sign in with the company login they already have, with no tokens to manage.
Govern
Each person sees only what they should
Access groups and policies decide which tools and skills appear for each person, and people can request more when they need it.

Product

Magic MCP

Discover more Book a demo

Magic MCP is a single URL you paste into your AI client. Sign in with the login you already use, and your agent reaches every integration and tool you allow it to use.

A single Magic MCP URL connecting an AI agent to the integrations a person is allowed to use.

One URL
Paste one link into any agent
Drop a single Magic MCP URL into any MCP-compatible client. Nothing to install and no integration to wire up tool by tool.
Every tool
1000+ integrations, plus your own
The same link reaches a growing catalog of verified integrations and the custom or remote MCP servers only your team has, kept current for you.
Your access
Only what you allow, never more
Sign in with the identity you already use and stay tokenless. Behind the link, every call runs on the real user and reaches only the tools they’re allowed.

Product

Skills

Discover more Book a demo

A skill is a reusable workflow that teaches an agent how your team does a task, written by the people who actually do the work. Write it once, attach the tools it needs, and share it across your organization.

The Skills editor showing a team writing a shared skill with steps and connected tools.

Write
Captured by the people who do the work
Experts write a skill in a collaborative editor, the way they’d brief a new teammate. No code or setup required.
Connect
Comes with the tools it needs
Each skill carries the integrations it relies on through one connection, so an agent gets the workflow and the tools together.
Share
Sharing made easy
Publish once and skills appear in the agent clients your teams already use, staying in sync with no reinstalling.

Product

Integrations

Discover more Book a demo

Start from 1000+ verified integrations or add your own, and give every one a governed path to your agents under existing SSO and access policies.

The Metorial integrations catalog showing verified providers, tools, and access controls.

Connect
Any tool, ours or yours
Start with 1000+ verified integrations or add the internal systems and private APIs only your team has as custom, remote, or Docker-based providers.
Reach
One link for every approved tool
Agents reach the integrations they’re allowed to use through a single connection, with no connector project per tool.
Govern
Scoped and traceable by default
Access follows the groups and policies you already manage, down to individual tools and actions, and every call stays on the record.

Product

Tracing

Discover more Book a demo

Metorial keeps a complete, searchable record of everything your agents, team, and machines do. See exactly what happened and trust AI in production.

The Tracing console showing agent sessions, tool calls, and a full trace timeline.

Capture
Recorded automatically
Every session, message, and tool call is recorded the moment it happens, with nothing for your team to set up.
Attribute
Which agent, on whose behalf
Every action ties back to the exact agent that took it and the real person behind it. Nothing happens anonymously.
Review
Search and replay anything
Monitor activity as it happens, then search past interactions and replay full sessions to answer questions from security and leadership.

Product

Protoguard

Discover more Book a demo

Protoguard is Metorial’s security layer for AI agents. It reviews incoming messages and tool requests before an agent acts, catches prompt injection, watches for provider schema changes, and blocks anything outside your policies before it reaches your systems.

The Protoguard console showing message reviews, policy checks, and blocked requests.

Review
Check every message and request
Protoguard scans incoming messages for prompt injection and checks each tool request against your filters and policies before an agent acts.
Monitor
Watch for risky changes and activity
Monitors track provider schema changes and suspicious behavior, turning flagged activity into alerts with the context your security team needs.
Block
Stop and contain anything unsafe
Requests outside your rules are blocked before they reach connected systems, and what does run stays contained on isolated infrastructure.

Product

CLI

Discover more Book a demo

Let agents use the CLI for native integration work. Skip unnecessary tool schema overhead.

Connect
Set up an integration in minutes
Install the CLI, sign in, and connect a provider, then list its tools and inspect each one, all from the terminal.
Call
Run tools as commands
Agents use commands, flags, and help text they already understand, with no large tool schema to load before they can act.
Automate
The same workflow anywhere
Run integration work locally, in scripts, and in CI, so it fits the automation your team already has.

Product

Access Control

Discover more Book a demo

Sign in with company SSO, set policies per user and group, and let agents act on real identity across Portals and Magic MCP.

The Metorial access console showing users, groups, access policies, and connected identity providers.

Who
People, groups, and agents
People sign in with your existing identity, and groups, service accounts, and each agent are governed the same way. Non-human access is never an exception.
What
Agents, tools, and providers
Decide which agents can act and which tools, actions, and providers each one can reach. Allow a provider while still blocking specific tools.
How
Set once, enforced everywhere
Policies follow the real user behind every agent, cap what any single agent can do, and can be revoked the moment someone leaves.

Product

Callbacks

Discover more Book a demo

Your agents usually wait to be asked. Callbacks let them act the moment something happens.

The Callbacks console showing registered triggers, where updates are sent, and recent event deliveries.

Register
Choose what to listen for
Pick the event that matters, like a new message, a new ticket, or a tool call finishing, across your integrations and Metorial itself.
Listen
Metorial watches for it
Metorial detects the event the moment it happens, so nothing has to keep polling for changes.
React
Your agent acts right away
As soon as the event fires, your agent or systems get the update and respond, instead of waiting to be prompted.

A catalog of approved tools and skills

One link to start working

Each person sees only what they should

Paste one link into any agent

1000+ integrations, plus your own

Only what you allow, never more

Captured by the people who do the work

Comes with the tools it needs

Sharing made easy

Any tool, ours or yours

One link for every approved tool

Scoped and traceable by default

Recorded automatically

Which agent, on whose behalf

Search and replay anything

Check every message and request

Watch for risky changes and activity

Stop and contain anything unsafe

Set up an integration in minutes

Run tools as commands

The same workflow anywhere

People, groups, and agents

Agents, tools, and providers

Set once, enforced everywhere

Choose what to listen for

Metorial watches for it

Your agent acts right away

Ready to build your AI workforce on Metorial?