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

# Openlayer MCP

> Learn how to set up the Openlayer MCP server.

<img style={{ borderRadius: "0.5rem" }} width="700" src="https://mintcdn.com/openlayer-44/jN8MTVdaEnRVD4sY/images/documentation/mcp_hero.png?fit=max&auto=format&n=jN8MTVdaEnRVD4sY&q=85&s=482b8ca23f477afe8b2385470ac1911c" alt="MCP hero" data-path="images/documentation/mcp_hero.png" />

[MCP](https://github.com/modelcontextprotocol) (Model Context Protocol) is an open-source standard for how applications provide
context and tools to LLMs.

The **Openlayer MCP server** exposes many of Openlayer's features to LLMs. If you
use an IDE or desktop app with MCP support — like [Cursor](https://docs.cursor.com/context/model-context-protocol),
[VSCode](https://code.visualstudio.com/docs/copilot/chat/mcp-servers), [Claude Desktop](https://modelcontextprotocol.io/quickstart/user),
and others — you can now directly interact with your Openlayer workspace **without
leaving your editor**.

<img width="700" style={{ borderRadius: "0.5rem" }} src="https://openlayer-static-assets.s3.us-west-2.amazonaws.com/images/openlayer_mcp_cursor.gif" alt="Openlayer MCP in Cursor" />

## Set up

To get started with the Openlayer MCP server:

<Steps>
  <Step title="Install uv">
    Make sure you have `uv` installed in your machine. You can follow the
    [instructions here](https://docs.astral.sh/uv/getting-started/installation/) if you don’t have it yet.
  </Step>

  <Step title="Add Openlayer to your MCP configuration">
    Add the following snippet to your `mcp.json` configuration file.

    The location of this file depends on your editor. For example, for Cursor,
    this is `~/.cursor/mcp.json`. For VSCode, this is `~/.vscode/mcp.json`.

    ```json theme={null}
    {
        "mcpServers": {
            "openlayer": {
                "command": "uvx",
                "args": ["openlayer-mcp"],
                "env": {
                    "OPENLAYER_API_KEY": "YOUR_OPENLAYER_API_KEY_HERE"
                }
            }
        }
    }
    ```
  </Step>

  <Step title="Restart your application">
    Some applications require you to restart the application after adding the
    configuration.
  </Step>
</Steps>

## Usage

Once configured, you’ll be able to see and use the Openlayer MCP server inside your
application.

You can ask about:

* Projects in your Openlayer workspace.
* Recent test results.
* Inference pipelines.
* Commits, and more.