Skip to main content

​
MCP Server

The 2027.dev MCP server lets you query eval reports, request new evals, and track results directly from your AI coding tools.
No npm install needed. The MCP server uses HTTP Streamable transport — just add the URL and your API key to your MCP client config.

​
Setup

​
Get your API key

  1. Go to 2027.dev/evals and sign in
  2. Navigate to Settings → API Keys
  3. Create a new key and copy it (starts with evals_)

​
Claude Code (one command)

Run this in your terminal — replace evals_YOUR_API_KEY with your actual key: 
claude mcp add 2027-evals --transport http https://2027.dev/evals/api/mcp --header "Authorization: Bearer evals_YOUR_API_KEY"
That’s it. Run claude mcp list to verify the server is connected.
Alternatively, add to your Claude Code MCP config (~/.claude/claude_desktop_config.json):
{
  "mcpServers": {
    "2027-evals": {
      "url": "https://2027.dev/evals/api/mcp",
      "headers": {
        "Authorization": "Bearer evals_YOUR_API_KEY"
      }
    }
  }
}

​
Cursor

Add to your Cursor MCP settings (.cursor/mcp.json): 
{
  "mcpServers": {
    "2027-evals": {
      "url": "https://2027.dev/evals/api/mcp",
      "headers": {
        "Authorization": "Bearer evals_YOUR_API_KEY"
      }
    }
  }
}

​
Any MCP client

The server uses HTTP Streamable transport at: 
POST https://2027.dev/evals/api/mcp
Authorization: Bearer evals_YOUR_API_KEY

​
Available tools

ToolDescription
list_reportsList eval reports with filtering and pagination
get_reportFull report details — scores, dimensions, recommendations
get_session_traceAgent conversation replay with tool calls
get_friction_pointsExtract friction points from a report
compare_reportsSide-by-side comparison of multiple reports
get_trendsScore history over time
list_promptsAvailable eval prompts for your org
request_evalTrigger a new evaluation run
list_eval_requestsTrack eval request status

​
Example usage

Once connected, you can ask your AI assistant things like:
  • “Show me my latest eval reports”
  • “What friction points did the last eval find?”
  • “Compare the last two reports for my product”
  • “Request a new eval for my docs”
  • “Show me the session trace for report xyz”