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

# Connect Claude Code to Corunner MCP

> Configure Corunner Engineering Memory MCP in Claude Code.

Add Corunner as a hosted HTTP MCP server from the repository where you want to use it.

## Add Corunner for the current project

Run:

```bash theme={null}
claude mcp add --transport http corunner https://api.corunner.ai/mcp
claude mcp list
```

This makes the server available in the current project context.

## Add Corunner for every project

Use user scope:

```bash theme={null}
claude mcp add --transport http --scope user corunner https://api.corunner.ai/mcp
```

## Complete OAuth

Inside Claude Code, run `/mcp`, select **corunner**, and complete the browser sign-in and consent flow. Choose the Corunner workspace and approve only the scopes you need.

## Verify the connection

Run `claude mcp list` and confirm that `corunner` is available. Ask Claude Code to retrieve context for a file in the current repository. Include the canonical Git remote when prompted or in your task.

<Warning>
  Keep the OAuth grant user-specific. Do not place bearer tokens in project files, shell scripts, or committed configuration.
</Warning>

For current command options and OAuth behavior, see the [Claude Code MCP guide](https://code.claude.com/docs/en/mcp).