One write path for connected, searchable context.

01 · Connect your data

Turn incoming data into queryable graph context.

RushDB infers property types as data arrives. Nested payloads become linked records immediately. Flat sources can be analyzed for reviewable relationship patterns after import.

• Accept real payloads

  Use nested JSON, arrays of records, or CSV-shaped imports instead of forcing every source through a hand-built staging model.

• Keep structure queryable

  Nested objects become records connected by default parent-child relationships, so the source structure survives the import.

• Evolve flat imports safely

  When separate flat sources need joins, suggested patterns stay reviewable before they become durable graph relationships.

Import nested records in one call.

from rushdb import RushDB

db = RushDB('RUSHDB_API_KEY')

db.records.import_json({
    'label': 'COMPANY',
    'data': {
        'name': 'Acme Corp',
        'DEPARTMENT': [
            {'name': 'Engineering', 'headcount': 42},
            {'name': 'Design', 'headcount': 12},
        ],
    },
})

03 · Managed embeddings

Keep searchable text indexed as records change.

Define an embedding index for the label and string property you want to retrieve by meaning. Use managed embeddings for the shortest path or external vectors for model control.

• Index only useful text

  Choose the specific property that should be recalled by meaning, such as an agent output, document body, or product description.

• Backfill stays attached

  Managed indexes can generate vectors for existing records and keep updated values searchable as records change.

• Model control remains possible

  External indexes let teams supply their own vectors when compliance, local inference, or domain models matter.

Create an index, then search with plain text.

from rushdb import RushDB

db = RushDB('RUSHDB_API_KEY')

db.ai.indexes.create({'label': 'MEMORY', 'propertyName': 'output'})

recall = db.ai.search({
    'labels': ['MEMORY'],
    'propertyName': 'output',
    'query': 'What pricing decision affected revenue?',
    'limit': 10,
})

05 · Unified query API

Query records. Inspect the graph. Use one shape.

RushDB applies the same SearchQuery-shaped request model across records and graph introspection. Applications and agents can filter stored data, discover labels, inspect relationships, read property metadata, and fetch distinct values or ranges before constructing the next query.

• Build adaptive UIs

  Fetch labels, property metadata, and distinct values or ranges to build filters that match the data actually present.

• Support analytics inline

  Use select expressions, groupBy, time buckets, and derived metrics for dashboard-style answers without exporting to another analytics store.

• Reduce agent query drift

  The same request shape teaches agents how to discover structure and then query records without switching mental models.

One intent, five perspectives.

from rushdb import RushDB

db = RushDB('RUSHDB_API_KEY')

# One intent, defined once
query = {
    'labels': ['ORDER'],
    'where': {'status': 'paid', 'CUSTOMER': {'tier': 'enterprise'}},
}

records = db.records.find(query)              # 1. matching entities
labels = db.labels.find(query)                # 2. entity types in this slice
properties = db.properties.find(query)        # 3. fields in this slice
relationships = db.relationships.find(query)  # 4. graph links in this slice
# 5. canonical values for one property in this slice:
#    POST /properties/:propertyId/values with the same query body

07 · MCP server

Give agents a direct path to structured memory.

The RushDB MCP server exposes database operations as tools for MCP-compatible clients. Agents can discover structure before they build queries.

• Hosted or local connection

  Connect ChatGPT, Claude.ai, and other web assistants to the hosted OAuth endpoint at mcp.rushdb.com/mcp — one URL, sign in, no install. Desktop and coding clients run the local npx server.

• Database operations as tools

  Agents can browse structure, query records, manage relationships, run bulk operations, export data, and use transactions.

• Discovery before execution

  The documented workflow starts with schema, classifies intent, loads the query spec when needed, and then builds the tool call.

Connect hosted with OAuth, or run the local server.

# Local MCP server (desktop and coding clients):
RUSHDB_API_KEY=your-key npx -y @rushdb/mcp-server