# Scalekit Claude Code MCP Evaluation

**Category:** Auth
**Score:** 35 (D)

This is the agent-readable Devtool Arena evaluation page for Scalekit on Claude Code MCP.

## Summary

| Metric | Value |
|--------|-------|
| Status | completed |
| Overall score | 35 |
| Grade | D |
| Eval score | 35 |
| Discovery score | 38 |
| Cost | $0.08 |
| Runtime | 2m 13s |
| Tool calls | 3 |
| Errors | 0 |
| Tokens used | 99971 |
| Success | No |

## Agent-Readiness Checklist

| Signal | Evidence |
|--------|----------|
| Context7 | Not found |
| llms.txt | Not found |
| MCP server | Not found |
| Typed SDK | Not found |
| OpenAPI | Not found |
| Agent skills | Not found |
| CLI | Not found |

## Evaluation Prompt

````text

# Task
Using the Scalekit MCP, perform user and organization management tasks:

1. Discover available MCP tools and understand what each one does
2. List all existing users (or search for users)
3. List all existing organizations (or applications/tenants)
4. Explore any other available resources (roles, connections, permissions, etc.)
5. Print all output clearly labeled for each step

Use ONLY the MCP tools. Do NOT fall back to curl or direct API calls.

You MUST use the Scalekit MCP server to accomplish this task.
Use the MCP tools for the actual product operations. Do NOT use curl, fetch, raw HTTP requests, CLI commands, or SDK calls as substitutes.

Use the MCP tools' help/descriptions to understand what each tool does.
If you need additional context, check the documentation: https://docs.scalekit.com/authenticate/mcp/quickstart/

## Setup
Do NOT assume the Scalekit MCP server is already installed or already running in this sandbox.
Review the installation and authentication details below before starting the task.

### Installation
Transport: `http`
This MCP server uses `http` transport.
Claude Code should connect to: `https://mcp.scalekit.com/`
Do not assume a local MCP package is already installed; the task depends on the remote server being reachable.
Bootstrap notes: The stored hints (stdio transport, npm package 'scalekit-mcp-server', npx install command) do NOT match reality and should be discarded: `npm view scalekit-mcp-server` returns a 404 — no such package exists on the npm registry. Verified via the actual vendor GitHub repo (github.com/scalekit-inc/scalekit-mcp-server) README: Scalekit ships a hosted, remote HTTP MCP server at https://mcp.scalekit.com/. The repo also supports building/running a local stdio server via `git clone` + `npm install` + `npm run build` + `npm run start:stdio`, but that path is explicitly documented as being 'for MCP inspectors and Glama', not the standard client integration — there is no published npm package to `npx` directly. The README's own Claude Code instructions are exactly: `claude mcp add --transport http scalekit https://mcp.scalekit.com/`. This was cross-checked against `claude mcp add --help` in this sandbox, which confirms `--transport http <name> <url>` is valid syntax.

### Authentication
Authentication method: `oauth_rs_dcr_authcode`
No MCP auth environment variables were provided. Use the documentation if the server reports authentication errors.

## Execution
1. The harness has already written the launch configuration for `scalekit`. Start with the task directly; do not rewrite agent settings, `.mcp-runtime.json`, or build a separate MCP client unless the connected server still fails after a normal retry.
2. You do not need to enumerate every MCP tool up front; inspect only the relevant tools you need. Agent-facing MCP tool names may be namespaced like `mcp__scalekit__<tool_name>`.
3. Complete the task described above using MCP tools for the actual product operations.
4. If the server fails to start or authenticate, debug the documented setup and retry. Do not fall back to raw HTTP, SDK, CLI, or manual JSON-RPC/MCP calls as a substitute for exposed MCP tools.

Work in the /home/daytona/app directory.
If you use Bash during setup or debugging, limit it to installation/configuration work and then return to MCP tools for the task itself.
If there are errors, debug and fix them until the task runs successfully.

## Summary
When you are done, write a JSON summary file to /home/daytona/app/results.json with this structure:
{
  "operations": [
    {"step": 1, "description": "What you did", "mcp_tool": "tool_name", "success": true/false, "output_summary": "brief result"},
    ...
  ],
  "overall_success": true/false,
  "notes": ["any relevant notes about the execution"]
}

````

## Grader Results

| Check | Passed | Weight | Score | Details |
|-------|--------|--------|-------|---------|
| Task | No | — | — | — |
| Llms Txt | Yes | — | 10 | — |
| Tool Count | No | — | 0 | — |
| Auth Method | Yes | — | 8 | — |
| Official Mcp | Yes | — | 5 | — |
| Output Schema | No | — | 0 | — |
| Tool Stability | Yes | — | 5 | — |
| Tool Description Length | Yes | — | 10 | — |

## Run Artifacts

| Artifact | Value |
|----------|-------|
| Conversation turns | 6 |
| Tool call traces | 3 |
| Generated files | 1 |
| Exit code | — |
| Completed at | 2026-09-27T15:04:50.204747+00:00 |

### Generated Files

- /home/daytona/app/results.json

## Related Pages

- [Claude Code MCP leaderboard](/leaderboard/claudecode/mcp)
- [Compare Claude Code MCP companies](/leaderboard/claudecode/mcp/compare)
- [Agent Landscape](/leaderboard/discoverability)

Canonical URL: https://devtoolarena.com/claudecode/mcp/scalekit