Quickstart: test an AI agent

By the end of this page your agent’s real traces are streaming to Mirrors, you have a runnable environment built from them, and your agent is calling its tools instead of production.

Mirrors is available by request: accounts are enabled one at a time rather than self-serve. If you have not been set up yet, request access first. Signing in without a granted account leaves every step below answering 403.

How do I set up Mirrors, step by step?

Five steps: connect an MCP client so your AI does the driving, add the collector so real sessions start streaming, then build an environment and point your agent at it, and read your first result. Steps 3 to 5 can be run from your MCP client, the CLI, or the dashboard; they all hit the same backend.

Install the MCP

Mirrors hosts an MCP server that exposes the full product surface (build, explore, query, and eval environments), so any MCP client can drive it. Point your client at the hosted endpoint; sign-in happens in the browser on first use, no API key to paste.

https://api.runmirrors.com/mcp

claude mcp add --transport http mirrors https://api.runmirrors.com/mcp

Then run /mcp → mirrors → Authenticate via browser.

Add to ~/.cursor/mcp.json:

{
  "mcpServers": {
    "mirrors": {
      "url": "https://api.runmirrors.com/mcp"
    }
  }
}

Cursor shows Needs login on the server. Click it to sign in via the browser.

code --add-mcp '{"name":"mirrors","type":"http","url":"https://api.runmirrors.com/mcp"}'

VS Code prompts to trust the server, then opens the browser to sign in.

On chatgpt.com:

Settings → Apps & Connectors → Advanced → enable Developer mode
Create → name it Mirrors, MCP server URL https://api.runmirrors.com/mcp
Authentication: OAuth → Create, then connect

Sign-in opens in the browser. Needs a Plus/Pro/Business plan (web).

codex mcp add mirrors --url https://api.runmirrors.com/mcp
codex mcp login mirrors

login opens the browser to sign in; tokens refresh automatically.

On claude.ai or Claude Desktop:

Settings → Connectors → Add custom connector
Paste https://api.runmirrors.com/mcp
Click Add, then Connect

Connect opens the browser to sign in and approve. Works on free and paid plans.

Every other client (Zed, Warp, Goose, Cline, Windsurf, …), the one-click installs, and headless/CI setups with a workspace key are on the MCP server page.

Install the collector

The collector streams your agent’s real production traces to Mirrors, the raw material every environment is built from. First mint a workspace API key (mk_live_…) at runmirrors.com under Settings → API keys, then install the collector and initialize it before your agent runs. It auto-instruments LangChain/LangGraph, Anthropic, and OpenAI, ships traces in the background, and never raises into your app.

# pip install mirrorkit
import mirrorkit
mirrorkit.init(api_key="mk_live_...", project="my-agent")

// npm install mirrorkit
import * as mirrorkit from 'mirrorkit';
mirrorkit.init({ apiKey: 'mk_live_...', project: 'my-agent' });

// go get github.com/ai-singhal/mirrorkit-go
mirrorkit.Init(mirrorkit.Options{APIKey: "mk_live_...", Project: "my-agent"})

Run your agent normally and traces start streaming. Details per language: Python, TypeScript, Go.

Build your first environment

Turn the collected traces into an environment: a schema, a seeded database, and bound tools, a runnable copy of your agent’s world, scored per tool for fidelity. Ask your MCP client, or use the CLI:

Build a mirror from my "my-agent" project and call it my-agent.

pip install "mirrorkit[cli]"
mirrors login                                   # paste your mk_live_… key
mirrors build --project my-agent --name my-agent

You can also build from the dashboard under Set up. Prefer files over a live stream? mirrors build traces.jsonl --name my-agent ingests a trace log directly.

Point your agent at it

Your agent does not move. Give it the endpoint, and every tool call goes to the twin instead of production. Nothing about your framework, your SDK version, or how your loop is written matters here: it is three HTTP calls.

import os, httpx

MIRROR = "https://api.runmirrors.com/v1"
KEY = os.environ["MIRRORS_API_KEY"]

with httpx.Client(base_url=MIRROR, timeout=300,
                  headers={"Authorization": f"Bearer {KEY}"}) as c:
    # your tools, already in Anthropic's tools= shape ("openai" works too)
    tools = c.get("/envs/my-agent/tools", params={"format": "anthropic"}).json()["tools"]

    # an isolated world, seeded in plain English
    s = c.post("/envs/my-agent/sessions",
               json={"seed_instructions": "a customer with one refundable booking"}).json()
    auth = {"Authorization": f"Bearer {s['session_token']}"}

    # your agent loop goes here: every tool call it makes becomes one of these
    r = c.post(f"/sessions/{s['session_id']}/call",
               json={"name": "cancel_booking", "arguments": {"id": "BK-4471"}},
               headers=auth).json()
    print(r["content"])

    c.delete(f"/sessions/{s['session_id']}", headers=auth)

The first call to a cold mirror waits about two minutes while its container starts. POST /v1/envs/my-agent/wake warms it without blocking, which is what you want in a test suite’s setup. Full reference: tool plane.

Read what it did

Every session keeps a transcript of the calls made in it, in order, with arguments, latency, and how each tool was answered (provided real code, synthesized generated code, simulated a model). With your agent’s loop on your own machine, that ledger is our record of what it did.

curl https://api.runmirrors.com/v1/sessions/$SESSION_ID/transcript \
  -H "Authorization: Bearer $SESSION_TOKEN"

The dashboard’s Connect screen has the same thing with a console attached, so you can call a tool by hand and read exactly what your agent would read.

Next steps

How it works

Fidelity scoring, deterministic seeding, sessions, and business context.

MCP server

Every client, one-click installs, and headless setups.

CLI

The mirrors command: full parity with the web app.

Tool plane

The endpoints your agent calls: tools, sessions, transcripts.

Get started

Collect traces

Drive Mirrors

Account

Resources

Quickstart: test an AI agent

How do I set up Mirrors, step by step?

Next steps

How it works

MCP server

CLI

Tool plane

​How do I set up Mirrors, step by step?

​Next steps

How it works

MCP server

CLI

Tool plane

How do I set up Mirrors, step by step?

Next steps