DreamerOS

One key. Five checks.

One dros_ API key opens five checks over plain HTTPS. An API key is a private password that lets a program use your account. Send text, get a clear answer back. Every response carries an id you can keep as proof. No SDK required - curl, a command that sends a web request from your terminal, works.

Get your key

Sign in at app.dreameros.app and open the Connect page. Select Generate API key. Your key starts with dros_. The free plan includes 100 calls per check per day on the first three checks below. Checks that need a paid plan say so plainly in the response - nothing fails silently.

In every example below, replace dros_YOUR_KEY with your own key. Every path below starts with https://mcp.dreameros.app/api/v1.

Free plan

1. Check a message

POST /api/v1/daim/check

Checks one piece of text before or after a model sees it. It flags injected instructions, banned dash characters, and text whose depth does not match its size.

Copy-paste example
curl -X POST https://mcp.dreameros.app/api/v1/daim/check \
  -H "Authorization: Bearer dros_YOUR_KEY" \
  -H "Content-Type: application/json" \
  -d '{"phase": "pre", "text": "Summarize this contract in plain terms."}'
Response shape
{
  "pass": true,
  "flags": [],
  "em_dash_stripped": false,
  "injection_detected": false,
  "depth_match_score": 0.6,
  "phase": "pre",
  "governance_event_id": "dro_evt_...",
  "gateway_version": "1.0.0"
}

In plain words: pass is true when nothing risky was found, and flags lists anything that was.

phase is pre for text going in, post for text coming back.

Free plan

2. Confirm an answer

POST /api/v1/ifp/verify

Checks an answer against the question it claims to answer. It scores how faithful the answer is, how costly a wrong answer would be, and whether the answer finishes the job. The verdict is one word: go, hedge, or block.

Copy-paste example
curl -X POST https://mcp.dreameros.app/api/v1/ifp/verify \
  -H "Authorization: Bearer dros_YOUR_KEY" \
  -H "Content-Type: application/json" \
  -d '{"answer": "The refund window is 30 days from delivery.",
       "sources": ["https://example.com/refund-policy"],
       "intent": "confirm the refund window"}'
Response shape
{
  "pass": true,
  "fidelity": 0.9,
  "consequence": 0.95,
  "endgame": 0.85,
  "verdict": "go",
  "cited_sources": ["https://example.com/refund-policy"],
  "failing_axis": null,
  "don_t_kick_problem": false,
  "governance_event_id": "dro_evt_...",
  "gateway_version": "1.0.0"
}

In plain words: go means use the answer, hedge means double-check it, and block means do not rely on it.

Answers with named sources score better. A long answer with no sources loses points.

Free plan

3. Sharpen a prompt

POST /api/v1/ede/restructure

Takes a rough prompt and returns a cleaner one. It names the intent, the mood, and how deep the answer should go, so the model you call next does better work.

Copy-paste example
curl -X POST https://mcp.dreameros.app/api/v1/ede/restructure \
  -H "Authorization: Bearer dros_YOUR_KEY" \
  -H "Content-Type: application/json" \
  -d '{"prompt": "uh can you maybe look at why the build is red and also the login thing"}'
Response shape
{
  "intent": "risk_scan",
  "emotion_signal": "focused",
  "depth_hint": 3,
  "ambiguity": 0.4,
  "multi_question_split": true,
  "restructured_prompt": "1. Find why the build fails. 2. Check the login issue.",
  "mode": "day_to_day",
  "governance_event_id": "dro_evt_...",
  "gateway_version": "1.0.0"
}

In plain words: you get your prompt back, cleaned up and split into numbered parts, with a reading of what you meant.

restructured_prompt is null when your prompt was already clean. depth_hint runs 1 to 5.

Solo plan and up

4. Scan for filler

POST /api/v1/slop/check

Checks text or code for filler and low-effort patterns. Each finding names the signal, its severity, the line, and why it matters.

Copy-paste example
curl -X POST https://mcp.dreameros.app/api/v1/slop/check \
  -H "Authorization: Bearer dros_YOUR_KEY" \
  -H "Content-Type: application/json" \
  -d '{"text": "# leverage our synergy to streamline delivery",
       "language": "text", "mode": "advisory"}'
Response shape
{
  "findings": [
    {
      "signal_name": "banned_filler_word",
      "severity": "low",
      "line_hint": 1,
      "snippet": "# leverage our synergy to streamline delivery",
      "explanation": "Filler word in comment or docstring. Replace with precise language."
    }
  ],
  "total": 1,
  "advisory_summary": "1 finding(s): 1 low. Advisory only.",
  "would_block": false,
  "governance_event_id": "dro_evt_...",
  "gateway_version": "1.0.0"
}

In plain words: each finding is one weak spot. In advisory mode the check only advises.

Set language to python, javascript, and so on to scan code instead of prose.

Paid plans

5. Pressure-test a decision

POST /api/v1/verify-decision

Checks a decision statement before you act on it. You get a plain rating - GREEN, YELLOW, or RED - plus a recommendation and any conditions. The full written check rides along in raw, so you see exactly what was said.

Copy-paste example
curl -X POST https://mcp.dreameros.app/api/v1/verify-decision \
  -H "Authorization: Bearer dros_YOUR_KEY" \
  -H "Content-Type: application/json" \
  -d '{"statement": "Ship the new pricing page today without a review.",
       "scope": "full"}'
Response shape
{
  "risk_rating": "YELLOW",
  "recommendation": "Hold for one review pass.",
  "conditions": ["Confirm the listed prices match live billing."],
  "raw": "...the full written check...",
  "scope": "full",
  "governance_event_id": "dro_evt_...",
  "gateway_version": "1.0.0"
}

If the check itself cannot run, you get an honest error status - never a made-up rating.

Every response is a record

Each of the five checks returns a record id, the governance_event_id field. Keep it. It is the reference for that exact call. We also write the call to an append-only log on our side. If that log write fails, your check still returns its result. Answers in the app also carry signed receipts - you can check any receipt id at the receipt page, no account needed.

We run checks on ourselves too. See our own copy, checked on a schedule.

One key. Five checks. - copy, paste, run Get your key free