Your tools already know this.

The problem

How it works

-- Step 1: Load full development context
context

-- Step 2: Record what you learned while working
save _memory/bugs @deleted-entity-check title: "read returns a deleted marker"
  fix: "Check if entity is deleted before reading .payload"
  date: "2026-02-11"

-- Step 3: Search previous development notes
search _memory "entity deletion handling" top 10

Memory categories

As you work, save what you learn to _memory/{category} folders. Each entry has a unique key — saving with the same key updates the existing record instead of creating a duplicate.

These are conventions, not constraints. You can create any sub-folder under _memory/. The context command auto-discovers and summarizes all of them. All _memory/ folders require your key — your development history is private by default.

Set up your agent

Add InfiniteOcean as a Claude connector (web or Desktop, same flow) and your agent gets 5 tools wired to your account — one click if you're signed in, one magic-link email if you're not.

No account yet? Sign up free — takes 10 seconds.

Settings → Connectors → Add custom connector

Name:     InfiniteOcean
URL:      https://api.infiniteocean.io/mcp/io
Advanced: (leave empty)

Click Connect → browser opens →
  signed in?  one-click Approve
  not yet?    enter email → click magic link → Approve
  agent key?  "paste an Ocean Key instead" fallback

{
  "mcpServers": {
    "infiniteocean": {
      "command": "npx",
      "args": ["-y", "mcp-remote", "https://api.infiniteocean.io/mcp/io"]
    }
  }
}

https://api.infiniteocean.io/mcp/io?key=YOUR_KEY

{
  "servers": {
    "ocean": {
      "type": "sse",
      "url": "https://api.infiniteocean.io/mcp/io?key=YOUR_KEY"
    }
  }
}

Ocean Key: `YOUR_KEY`

Endpoint: POST /exec
Header: X-Ocean-Key: YOUR_KEY
Body: {"query":"your drops command"}

Docs: /drops

curl -X POST https://api.infiniteocean.io/exec \
  -H "Content-Type: application/json" \
  -H "X-Ocean-Key: YOUR_KEY" \
  -d '{"query":"save _memory/decisions @first title: \"Chose IO\" reasoning: \"Simple\""}'

MCP connections get 5 tools: exec, get_context, remember, recall, broadcast. The exec tool does everything — see /drops for the full language. /mcp/io is the canonical endpoint; /mcp/ocean and /mcp/default are aliases (kept for back-compat).

Automatic skill injection

When an agent connects via MCP, it automatically receives behavioral instructions — no extra setup. Every agent knows how to use InfiniteOcean from the first message.

You can also write custom skills that teach agents project-specific behavior. The instructions are injected at connection time via the MCP instructions field.

// Write your project skill
save _mcp/YOUR_KEY @skill
  "This is a Next.js 14 app.
  Always use App Router, never Pages.
  Tests: vitest, not jest.
  Deploy: git push to main triggers CI.
  Database: Supabase, never raw SQL."

// Or via the payload parameter for longer text
query="save _mcp/YOUR_KEY @skill"
payload="Your full project skill text..."

Cross-folder reasoning

Your AI can pull related information from anywhere — link a decision to the bug it fixed, or a pattern to the files it applies to. Everything connects.

With universal fields, your agent just asks a question — and gets answers from every folder in one call.

{
  "identifiers": {
    "$has": {
      "type": "email",
      "value": "[email protected]"
    }
  }
}

{
  "dates": {
    "$gte": "2026-03-01",
    "$lt": "2026-04-01"
  }
}

{
  "locations": { "$near": {
    "lat": 55.68, "lon": 12.57,
    "radius_km": 5
  }}
}

{
  "amounts": {
    "$gte": 10000,
    "$unit": "USD"
  }
}

Connected agents get the query_primitives tool automatically. All filters combine with AND — "Alice's meetings in March near Copenhagen over $1000" is one query.

Live references

Agents can compose data from multiple sources without copying it. Place a $embed reference in any content — the server resolves it on read, keeping the original creator's ownership, billing, and counters intact.

Think YouTube embeds — the content stays with its creator, the embedder just places a reference. Views, revenue, and version updates all flow back to the source.

{
  "hero": {
    "$embed": {
      "route": "photos/nature",
      "key": "sunset-001"
    }
  }
}

{
  "chart": {
    "$embed": {
      "route": "charts/revenue",
      "key": "q4",
      "mode": "view"
    }
  }
}

Connected agents use the write tool with $embed references in content. The read tool resolves them automatically. Use resolve: true in the query tool for batch resolution.

Live context preview

This is a live context response right now:

Quick start

# 1. Get an Ocean Key (free, instant) — POST /drop on any route you pick
curl -X POST https://api.infiniteocean.io/drop \
  -H "Content-Type: application/json" \
  -d '{"route":"my-app/notes","key":"hello","payload":{"message":"hello world"}}'
# Response includes keypair.public AND keypair.private. Save both.
# public  → your X-Ocean-Key for future requests
# private → keep secret; never sent over the wire after this

# 2. Fetch your development context
context

# 3. Record something you learned
save _memory/decisions @first-decision 
  title: "Chose immutable data history"
  reasoning: "Every write is versioned, nothing lost"
  date: "2026-01-01"

# 4. Fetch context again — your note is there
context

# 5. Search your memories
search _memory "immutable" top 5

Send commands through one place. Learn Drops →