Scorecard MCP
for LuumenAI

Read Scorecard evaluation projects, then run API changes as approved steps

Connect Scorecard MCP and your agent can look up how the SDK works before it touches anything. Search the documentation for the right method and parameters, then run JavaScript against the Scorecard API to manage projects, testsets, testcases, systems, metrics, runs, records, scores, and annotations. Luumen authenticates with OAuth via dynamic client registration.

The Scorecard MCP toolbox

2 tools: 1 read, 1 write. Reads answer instantly. Writes require approval by default. Everything is logged.

  • ReadSearch docsSearch SDK documentation to find methods, parameters, and usage examples for interacting with the API.
  • WriteExecuteRuns JavaScript code to interact with the Scorecard API. Approval by default

One prompt, start to finish

What a governed Scorecard MCP run looks like inside Luumen.

Questions

How does LuumenAI connect to Scorecard MCP?

Authorize once with OAuth 2.0. Luumen lists the scopes each action needs before you approve the connection, and credentials never appear in the chat.

Can LuumenAI change things in Scorecard MCP on its own?

Read actions answer immediately. Anything that writes — execute — is shown as a plan and requires approval by default, including the 1 action classified as destructive. Administrators configure that per tool, so you decide exactly which actions can ever run unattended.

Who gets access to the integration?

You decide. Actions are granted per agent, skill, and team, and per environment — production is not staging. Read access can be broad while writes stay narrow.

Is there an audit trail?

Every call to Scorecard MCP — read or write, approved or declined — is recorded with the actor, the input, and the result, and can be linked to the ticket or change record.

Put Scorecard MCP to work with Luumen

Connect in minutes. Every action scoped, approved, and audited from day one.