Getting Started

Quick Start Guide

Connect Claude or any AI agent to all 15 currently-available PolyDB data models (Transaction coming soon) in under 5 minutes.

Two Ways to Use PolyDB MCP

Direct tool calls

Call any of the 59 tools by name — best for agents or code that already knows which operation it needs. Examples: store_document, query_sql, search_vectors.

Agent-native code mode

Skip loading the full tool catalog into your prompt. Call search_schema to discover tools at runtime by provider or keyword, then execute_workflow to run a batched multi-step pipeline — with outputs piped between steps via $ref(). Dramatically fewer prompt tokens for autonomous agents.

Both patterns work against the same server — mix them freely.

Sign Up & Get Your API Key

Start with the Micro plan — $9.99 for 50 credits, 30 days

Step A Go to beta.polydb.dev/signup and create your account.
Step B From the dashboard, open API Keys and create a new key.
Step C Copy your key — it looks like polydb_mcp_... and is shown once.

Note Your API key grants access to all 15 currently-available data models (Transaction coming soon) under your account's plan limits. Keep it secret — treat it like a password.

Connect via MCP

Works with Claude Desktop, Claude Code, Cursor, Continue, and any MCP client

Claude Code (terminal)

$ claude mcp add polydb \
    --transport http \
    https://beta.polydb.dev/mcp \
    --header "X-PolyDB-Token: YOUR_KEY"

Claude Desktop (claude_desktop_config.json)

{
  "mcpServers": {
    "polydb": {
      "transport": "http",
      "url": "https://beta.polydb.dev/mcp",
      "headers": {
        "X-PolyDB-Token": "YOUR_KEY"
      }
    }
  }
}

Config location: ~/Library/Application Support/Claude/claude_desktop_config.json (macOS)

Tip After connecting, ask Claude: "Use the search_schema tool to show me what's available in my PolyDB." This gives you a full map of all your collections and data models.

First Operations

Copy-paste ready examples for each data model

Store a Document

# Via Claude (MCP) — tell Claude:
"Store a document in the 'notes' collection:
  { title: 'My first note', body: 'Hello PolyDB', tags: ['test'] }"

# Claude will call the store_document MCP tool automatically.

REST data plane — coming soon. Use MCP today.

Retrieve a Document

# Via Claude (MCP):
"Find all documents in 'notes' where tags contains 'test'"

REST data plane — coming soon. Use MCP today.

Store a Key-Value Pair

# Via Claude (MCP):
"Set key 'session:user_123' to 'active' with a 3600 second TTL"

REST data plane — coming soon. Use MCP today.

Store & Search Vectors

# Via Claude (MCP) — Claude generates the embedding automatically:
"Add this text to the 'docs' vector collection with semantic search enabled:
  'PolyDB supports 16 data models including SQL and vector search.'"

# Then search:
"Search the 'docs' vector collection for content similar to
  'database with multiple storage models'"

Connection Methods

Three ways to use PolyDB — choose what fits your workflow.

Method 01

MCP (Recommended)

For Claude Desktop, Claude Code, Cursor, Continue. Zero setup — connect once, all 15 currently-available models (Transaction coming soon) available as natural language.

                            claude mcp add polydb \

                              --transport http \

                              https://beta.polydb.dev/mcp \

                              --header "X-PolyDB-Token: KEY"

59 tools available

Method 02

REST API

Direct HTTP access for languages without an MCP client — bring your own HTTP tooling, no SDK required.

                            curl https://beta.polydb.dev/api/... \

                              -H "X-PolyDB-Token: YOUR_KEY"

Coming soon — MCP is the data plane today

Method 03

Python SDK

Native Python client with async support. Until the cloud SDK ships, use the OSS polydb package locally or hit MCP / REST from any HTTP client.

# Python SDK details coming soon

Coming soon

Working with multiple databases

Each tenant can hold multiple named databases. All 55 dataplane tools accept an optional database parameter so a single API key can target different databases per call.

Resolution order: database argument > X-PolyDB-Database header > tenant default > "polydb".

Create and manage databases from the Databases page in the dashboard or via GET/POST/DELETE /api/databases. Then pass the name as database='analytics' on any tool call.

Next Steps

MCP Reference →

Complete tool reference for all 59 MCP tools. Find the right tool for every query pattern.

16 Providers →

Deep-dive into each data model — Vector, Graph, Time-Series, Spatial, and more.

Examples →

Real-world patterns: AI memory, RAG pipelines, event streams, geospatial queries.

Dashboard →

Browse your collections, manage API keys, and monitor usage in the web dashboard.