> ## Documentation Index
> Fetch the complete documentation index at: https://docs.zenable.io/llms.txt
> Use this file to discover all available pages before exploring further.

# MCP Server

> The Zenable MCP Server lets you manage requirements and guardrails, without ever leaving your IDE

## Overview

The Zenable MCP (Model Context Protocol) Server lets your AI coding assistant check and improve code against your organization's requirements, and manage those requirements, guardrails, and scopes without leaving the IDE.

The same tools are available in the in-app chat assistant, so a conversation that starts in chat can continue from your IDE and vice versa.

<Note>
  **Your code is safe**: We never retain or train on your code, regardless of tier. [Read our FAQ](https://zenable.io/faq?utm_source=docs\&utm_medium=mcp-server\&utm_content=faq)
</Note>

To install the MCP server, see [MCP Server Installation](/integrations/mcp/getting-started).

## MCP Tools

### `search_marketplace_requirements`

Retrieve requirements from the Zenable marketplace that are enabled for
your environment.

### `search_tenant_requirements`

Retrieve the requirements from your tenant. Supports filtering by
lifecycle status, so you can narrow to draft, beta, stable, deprecated,
archived, or declined requirements.

### `search_guardrails`

Locate the policy-as-code guardrails enforcing a requirement. Useful
for inspecting the current rule, or grabbing an id to regenerate or
roll back.

### `list_scopes`

List the scopes, both built-in and tenant-defined, that decide *where*
a requirement applies. Call this before creating a new requirement or
scope.

### `create_proposed_tenant_requirement`

Author a new requirement and submit it as a draft proposal. As a safety
measure, a user must separately approve the requirement before it
becomes effective in your tenant.

### `create_scope`

Define a new reusable scope when nothing in `list_scopes` matches the
surface you want to govern.

### `regenerate_guardrail`

Ask Zenable to produce an improved iteration of a guardrail using
specific feedback such as false positives, missing coverage, or style.

### `reinstate_prior_guardrail_iteration`

Roll a guardrail back to a prior iteration (i.e. version).