AI Governance

Overview

Formal governs how people and AI agents use MCP servers, skills, and LLM providers. The AI Tools section of the groups these pages:

Page	Use it to
Catalog	Keep the approved MCP servers and skills, and choose who can use each one
Shadow AI	Review MCP servers and skills that people use but that aren’t in the Catalog
Access Requests	Approve or reject employee requests for MCP servers and policy exceptions
Guardrails	Choose what happens to MCP servers and skills outside the Catalog
Assessment	Score LLM conversations for alignment and risk
Usage, Models, MCPs, Skills, Applications, and Providers	See AI activity, usage, and policy hits

Insights adds AI-generated security findings about LLM traffic.

How the Pieces Fit

Capture AI traffic. Formal sees AI activity that flows through the Formal Endpoint or a .
Discover. Shadow AI and the usage pages show which MCP servers, skills, models, and AI clients people use.
Decide. Add approved items to the Catalog with access controls. Set Guardrails for everything else.
Handle exceptions. Employees request access from the employee Catalog. Admins decide in Access Requests.
Investigate. Review Insights, Logs, and the usage pages for risky activity.

Capture AI Traffic

Each page reads logs, so it only shows traffic that Formal proxies:

Traffic	How to capture it	Pages that use it
LLM requests from laptops and servers	Formal Endpoint with Transparent Mode and a network rule that intercepts `llm` traffic	Usage, Models, Applications, Providers, Skills, Shadow AI skills
LLM requests from applications	An LLM Resource on a Connector	Models, Applications, Providers, Skills
MCP servers in the Catalog	The MCP gateway on a Connector	MCPs
MCP servers outside the Catalog	Formal Endpoint with Transparent Mode and a network rule that intercepts `mcp` traffic	Shadow AI MCP servers

This network rule intercepts LLM and MCP traffic from known AI agents on macOS:

{
  "condition": {
    "pre_tcp": process.is_agent || process.has_agent_ancestor,
    "pre_tls": true,
    "post_tls": technology in ["mcp", "llm"]
  }
}

Verify: Use an AI agent on a device that runs the Endpoint. Then open Logs, select the Endpoint source, and filter on resource.technology:llm.

The Catalog

The Catalog lists the MCP servers and skills your organization approves. Click Add MCP to add a server from a template or a custom endpoint. See MCP Gateway for the steps. Click Add Skill to add a skill from its SKILL.md. Adding items requires the Resource permission. Changing access requires the Policies permission.

Access Controls

Open an MCP server or a skill and go to Access Controls. Under Who can use this MCP? or Who can use this skill?, choose:

Everyone: Every user can use it.
Specific Users: Only the selected users and groups can use it.
No One: Nobody can use it. Formal keeps the item in the Catalog as blocked.

For an MCP server, you can also answer Which tools can they use? with All Tools or Specific Tools. Formal enforces restrictions with a generated . It stores Message shown when access is denied as the policy’s reason, which appears in Logs. Blocked users currently see Formal’s standard block message instead. An item open to Everyone, with All Tools for an MCP server, needs no policy, so Formal deletes it. You can find these policies on the Policies page, tagged as described in Policy Tags. Edit access from the Catalog rather than in the policy code.

The Employee Catalog

Employees use the employee Catalog at catalog.formal.ai. There they can:

Browse the MCP servers and skills available to them
Follow setup steps for their MCP clients
Link upstream accounts and approve MCP clients during sign-in
Request access to MCP servers, or exceptions to policies that blocked them
Review their governed AI activity and their requests

Control who can use the employee Catalog with the Catalog application in Permissions. See Grant access to the Catalog.

Next Steps

Shadow AI

Review unmanaged MCP servers and skills

Guardrails

Block MCP servers and skills outside the Catalog

Access Requests

Approve employee requests

AI Usage

See which AI tools people use

Getting Started

Example Use Cases

Configuring Formal

Integrations

Configuration

AI Governance

Overview

How the Pieces Fit

Capture AI Traffic

The Catalog

Access Controls

The Employee Catalog

Next Steps

Shadow AI

Guardrails

Access Requests

AI Usage

​Overview

​How the Pieces Fit

​Capture AI Traffic

​The Catalog

​Access Controls

​The Employee Catalog

​Next Steps

Shadow AI

Guardrails

Access Requests

AI Usage

Overview

How the Pieces Fit

Capture AI Traffic

The Catalog

Access Controls

The Employee Catalog

Next Steps