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

# MCP servers

> Connect Model Context Protocol servers so the LLM judge can check your agent's answers against live data, and scenarios can be built from it.

The **MCP** page connects Model Context Protocol (MCP) servers to Arklex Platform. Once a server is connected and an Owner approves its read-only tools, custom metrics can call them during evaluations, and the scenario assistant can use them as a source. For example, the judge can look up an order's real status and check whether the agent reported it correctly.

***

## Add a server

Go to **MCP** in the sidebar and click **Add Server**. Fill in the **Add MCP Server** dialog:

**Display name** `string` *required*

A name for the server, for example "Orders API (production)". Names must be unique in your organization.

**Transport** `string` *required*

**Streamable HTTP**, the only supported transport. Servers that offer only stdio or the older HTTP+SSE transport can't be connected.

**Server URL** `string` *required*

The server's MCP endpoint, which often ends in `/mcp`, for example `https://example.com/mcp`. On cloud, it must be reachable from the public internet, because private and `localhost` addresses are blocked. Self-hosted deployments allow them by default. See the note under [Endpoint URL](https://docs-platform.arklex.ai/agents.md#connect-a-new-agent).

**Auth header** `object`

One header name and value for authentication. The name defaults to `Authorization`. If your server doesn't accept `Authorization`, use the header it expects, such as `X-API-Key`. The value is encrypted at rest and shows as `****` after you save.

Click **Test connection** to check the server and list its tools, then click **Add and Connect**.

You can't edit a server after you add it. To change its URL or credentials, delete the server and add it again.

***

## Read the server list

The summary at the top shows **Reachable servers** and **Enabled tools**. The table lists each server:

| Column | Description |
| - | - |
| **Server** | The server name. The last error, if any, appears below it. |
| **Health** | **Reachable**, **Error**, or **Not checked**, from the last connection test. |
| **Tools** | How many of the server's tools are enabled, out of the total. |
| **Last checked** | When the server was last tested. |
| **Enabled** | Turn the server on or off. |
| **Actions** | **Test** the connection again, or delete the server. |

***

## Manage tools

Click a server to open its details. The **Tools** tab lists every tool the server offers. Click **Re-run tools/list** to refresh the list.

For each tool, you can see:

* An **Enabled** switch. Only enabled tools can be used.
* A safety label: **Read-only**, **Write-capable**, or **Unknown safety**.
* A **Judges and scenario generation may call** switch, which approves the tool for evaluation judges and the scenario assistant. Only Owners can turn it on, and only for **Read-only** tools, so neither can change data in your systems.

Tools that the server marks as read-only are enabled automatically. If a tool's definition changes on the server, Arklex removes its approval, and an Owner must approve it again.

### Test a tool

Owners can run a tool by hand to check what it returns. Click **Test this tool**, fill in the **Arguments** (or click **Edit as JSON**), and click **Run tool**. The server and the tool must both be enabled.

> [!WARNING]
>
> **Run tool** really calls the tool, even a **Write-capable** one, so it can change data in your systems.

***

## Use tools in evaluations and scenarios

To use an approved tool in evaluations, add it to a custom metric. See [Check facts with MCP tools](https://docs-platform.arklex.ai/metrics.md#check-facts-with-mcp-tools).

To build scenarios from live records, pick approved tools as a source when the assistant asks which knowledge to use. See [Build with the assistant](https://docs-platform.arklex.ai/scenarios.md#build-with-the-assistant).

During the evaluation, the judge calls the tool and scores the agent against the results. In the conversation view, you can see the **Evidence used for this score**. When you re-evaluate, choose whether to reuse the saved tool results or fetch new ones. See [Re-evaluate](https://docs-platform.arklex.ai/evaluations.md#re-evaluate).

***

## Roles

| Action | Owner | Member |
| - | - | - |
| Add, test, enable, and delete servers | Yes | Yes |
| Enable and disable tools | Yes | Yes |
| Use approved tools in custom metrics and scenario sources | Yes | Yes |
| Approve tools for judges and scenario generation | Yes | No |
| Run a tool with **Test this tool** | Yes | No |

***

## Limits

* Connection tests time out after 10 seconds, and tool calls time out after 30 seconds.
* Each metric can make up to 5 tool calls per turn and 20 per conversation on turn scope, or 5 in total on conversation scope.
* Arklex lists up to 500 tools per server.
* On cloud, server URLs must be public.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.