More power for your AI agents

Serverless data
and email built
for agents.

MonkeyDB records and MonkeyMAIL inboxes share one organization, one scoped key system, one TypeScript SDK, and one MCP endpoint.

2 products
Database + email
1 MCP server
Scoped agent tools
Org-bound
Tenant-scoped data
live TypeScript client
Database surface

Serverless database for agents

const monkey = new MonkeyHubClient({ apiKey })
const memories = monkey.db("prod").collection({
  name: "memories",
  key: "agentId",
  indexes: [{ field: "status" }]
})

await memories.save({
  agentId: "agent_7",
  status: "active",
  score: 0.98
})
Org-scoped records
5 field indexes
TTL + backups
Pricing Tiers

Start free. Scale with your agents.

One base subscription includes explicit MonkeyDB operation and MonkeyMAIL recipient quotas.

Start free

MonkeyHUB Free

$0/mo
10,000 DB ops
3,000 mail recipients

Build agents with MonkeyDB and native MonkeyMAIL inboxes.

  • 10,000 DB operations / month
  • 3,000 mail recipients / month
  • 5 inboxes · built-in mail domain
Start building
Most popular

MonkeyHUB Pro

$20/mo
1,000,000 DB ops
50,000 mail recipients

Run production database and mail workloads under one organization.

  • 1,000,000 DB operations / month
  • 50,000 mail recipients / month
  • 100 inboxes · 3 custom domains
Choose Pro
Scale

MonkeyHUB Ultra

$200/mo
25,000,000 DB ops
1,000,000 mail recipients

Scale high-volume agent data and email with the largest included quotas.

  • 25,000,000 DB operations / month
  • 1,000,000 mail recipients / month
  • 5,000 inboxes · 25 custom domains
Choose Ultra
V1 Releases

What ships in MonkeyHUB v1

MonkeyHUB V1
MONKEYMAIL

Native Agent Inboxes

Give agents exact email addresses with durable sending, receiving, and threaded replies.

MonkeyMAIL stores inbound text, HTML, Markdown, authentication verdicts, and attachments. Agents can send, read, and reply through MCP while owners observe the same conversation through a sandboxed console viewer.

HUMAN OVERSIGHT

Durable Mail Safety

Approval inboxes, suppression, reputation gauges, and org-scoped pauses protect every queue.

Accepted sends remain durable through SES pressure and safety pauses. Suppressed recipients are removed before metering, and approval inboxes return pending_approval until the signed-in owner approves or rejects them.

NEW INTEGRATION

Model Context Protocol

Expose your databases directly to AI agents via standard MCP endpoints.

Connect any MCP-compatible agent to MonkeyDB. Generated SKILL.md, OpenAPI, and llms.txt endpoints expose the same request shapes used by REST and MCP.

AUTOMATED BACKUPS

Verified Backups

Snapshot nightly or on demand, then download or restore in one call.

Every gzip JSONL snapshot carries its collection schema, record count, and SHA-256 checksum. The console, SDK, REST API, and MCP can create snapshots and restore them into a new collection while preserving timestamps.

SECURITY

Tenant-Safe Isolation

Org-partitioned keys bind every storage operation to authenticated tenant context.

Every storage path is automatically bounded by organization, database, and collection. The API derives that boundary from the authenticated request context, never from caller-supplied tenant data.

BILLING CORE

Hourly DB Usage Rollups

Hourly usage rollups power quota checks and the console usage summary.

The API records successful database operations by organization and calendar hour. Free-tier organizations over their monthly included quota receive a standard 402 response.

01 / PLATFORM STRUCTURE

Field-Indexed Collections

MonkeyDB turns plain objects into organization-scoped collections with field-based indexes and deterministic query shapes.

Architecture

Collection Schema

Each collection declares a record key, an optional sort field, and up to five indexes using your own domain names.

Click to inspect

Your Fields, End to End

Key and sort declarations stay stable while indexes can be added idempotently as your access patterns grow.

{
  key: "agentId",
  sort: "memoryId",
  indexes: [
    { field: "status", sort: "createdAt" }
  ]
}
Click to return
Architecture

Field-Based Indexing

Declare custom indexes when you ensure a collection. Records missing an indexed field still save normally.

Click to inspect

Indexed Queries

Queries use the same field names as your records, including range operators on a declared sort field.

await memories.query({
  where: {
    status: "active",
    createdAt: { gte: "2026-04-01" }
  },
  limit: 50
})
Click to return
02 / DATA SECURITY

Tenant-Bound Storage

Tenant safety is built in. Queries are bounded programmatically by org context, keeping separate customer workspaces completely invisible from one another.

Tenant Isolation

Tenant-Safe Boundaries

Every record and index lookup includes the organization resolved from the authenticated credential.

Click to inspect

Scoped Storage

MonkeyDB binds every collection and index lookup to the authenticated organization before it reaches storage.

// Resolved request context:
{
  orgId: "org_abc123",
  actor: { type: "human", id: "usr_7" },
  plan: "pro"
}
Click to return
Tenant Isolation

Actor Credentials

Authenticate API requests with owner-session tokens or scoped agent API keys bound directly to an organization.

Click to inspect

Context Resolution

The API resolves every Bearer credential into tenant context and checks its database permission before executing an operation.

Authorization: Bearer mk_live_xyz...

// Returns:
X-Request-ID: req_abc
Content-Type: application/json
Click to return
03 / CREDENTIALS

Secure Credentials & Access

Manage owner keys, database-scoped keys, and agent approval requests. API keys cannot authenticate organization or billing screens.

Security

Secure API Access

Provision and revoke full-access, database read-only, or database read/write keys from the owner console.

Click to inspect

Key Structure

API keys use the mk_live_ prefix plus 32 base62 characters. Only a short display prefix and hash are retained after the raw key is shown once.

// Owner-session console endpoint
POST /api/settings/keys
{
  "db": "app",
  "mode": "rw"
}

// Permission: db:app:rw
Click to return
Security

Agent Approval Flows

Agent signup requests stay pending until the organization owner approves or denies them.

Click to inspect

Approval Pipeline

An agent identifies the owner's email; approval is scoped to that owner's organization. Callback delivery uses a one-time key claim instead of the raw credential.

{
  "requester": {
    "email": "agent@domain.com",
    "type": "agent"
  },
  "status": "pending",
  "expiresAt": 1798761600
}
Click to return
04 / OPERATIONS

Backups & Hourly Rollups

Verified nightly and on-demand backups with portable downloads, one-call restore, and hourly usage summaries.

Backups

JSONL Collection Backups

Nightly and on-demand snapshots are verified, downloadable, and restorable from the console, API, SDK, or MCP.

Click to inspect

Portable Restore

Each KMS-encrypted gzip JSONL snapshot includes schema, count, and SHA-256 metadata. Restore into a new collection while preserving original update timestamps.

Collection: prod/memories
Date: 2026-05-19

Format:
{"data":{"agentId":"agent_7","status":"active"},"updatedAt":1779148800000}
Click to return
Backups

Hourly Op Rollups

Usage counts roll up hourly for transparent quota checks and billing.

Click to inspect

Billing Middleware

The quota enforcer reads calendar-month rollups. Free-tier requests over the included quota receive a 402 response.

{
  "product": "db",
  "hour": "2026-05-19T12",
  "counters": { "ops": 1420 },
  "plan": "free"
}
Click to return