How to Use Bencher MCP

Bencher MCP is a hosted Model Context Protocol (MCP) server. It lets AI agents and assistants query benchmark data and submit benchmark results without needing the bencher CLI installed.

When the bencher CLI is available, it is still the recommended way to work with Bencher. bencher run handles benchmark harness adapters, iterations, and CI integration. Use Bencher MCP when the CLI is not installed or when your MCP client cannot run shell commands.

Connect

For example, connect from Claude Code:

claude mcp add --transport http bencher https://mcp.bencher.dev/mcp \
  --header "Authorization: Bearer $BENCHER_API_KEY"

Or use a generic MCP client configuration:

{
  "mcpServers": {
    "bencher": {
      "type": "http",
      "url": "https://mcp.bencher.dev/mcp",
      "headers": {
        "Authorization": "Bearer ${BENCHER_API_KEY}"
      }
    }
  }
}

Authentication

Bencher MCP accepts the same Authorization: Bearer credentials as the Bencher API: a project API key (bencher_run_*) or a user API key (bencher_user_*). Public projects can be read without any credential. OAuth is not yet supported, so MCP clients that only support OAuth for remote servers cannot connect yet.

A project API key is scoped to a single project, so it is the best choice for most agents. A user API key can access all of the user’s projects.

Tools

The tool surface mirrors what a project API key (bencher_run_*) can do: project-scoped reads and non-destructive writes. There are no delete or rename tools, and with a project API key alert updates are status only. Most tools take a project argument that accepts either a project slug or UUID.