MCP Server (Beta)

The Databar MCP Server implements the Model Context Protocol (MCP), allowing AI assistants like Claude to interact with Databar’s API using natural language. Instead of writing API calls manually, you can say “find the email for John Smith at Google” and your AI assistant will automatically discover the right enrichment, run it, and return the results.

What you can do

The MCP server exposes 18 tools covering the full Databar API:

Enrichments

Search, inspect, and run enrichments — single or bulk

Waterfalls

Run multi-provider waterfalls that try sources sequentially

Tables

Create tables, manage columns, and configure table enrichments

Row Operations

Insert, update, upsert, and read rows with full CRUD support

Quick start

npm (recommended)
From source

Install globally from npm:

npm install -g databar-mcp-server

Or run directly with npx (no install needed):

npx databar-mcp-server

Then add to your Claude Desktop config (~/Library/Application Support/Claude/claude_desktop_config.json on macOS):

{
  "mcpServers": {
    "databar": {
      "command": "npx",
      "args": ["-y", "databar-mcp-server"],
      "env": {
        "DATABAR_API_KEY": "your-api-key-here"
      }
    }
  }
}

git clone https://github.com/databar-ai/databar-mcp-server.git
cd databar-mcp-server
npm install && npm run build

Then add to your Claude Desktop config (~/Library/Application Support/Claude/claude_desktop_config.json on macOS):

{
  "mcpServers": {
    "databar": {
      "command": "node",
      "args": ["/path/to/databar-mcp-server/dist/index.js"],
      "env": {
        "DATABAR_API_KEY": "your-api-key-here"
      }
    }
  }
}

Restart Claude Desktop, then ask: “What Databar tools do you have access to?”

Available tools

Enrichments

Tool	Description
`search_enrichments`	Search enrichments by keyword or category
`get_enrichment_details`	Get parameters, pricing, and response fields
`run_enrichment`	Run a single enrichment with auto-polling and caching
`run_bulk_enrichment`	Run an enrichment on multiple inputs at once

Waterfalls

Tool	Description
`search_waterfalls`	Search available waterfall enrichments
`run_waterfall`	Run a waterfall (tries providers sequentially)
`run_bulk_waterfall`	Run a waterfall on multiple inputs at once

Tables

Tool	Description
`create_table`	Create a new empty table
`list_tables`	List all tables in your workspace
`get_table_columns`	Get column schema for a table
`get_table_rows`	Get rows with pagination
`get_table_enrichments`	List enrichments configured on a table
`add_table_enrichment`	Add an enrichment with column mapping
`run_table_enrichment`	Trigger an enrichment on all rows

Row operations

Tool	Description
`create_rows`	Insert up to 100 rows with deduplication options
`patch_rows`	Update fields on existing rows by ID
`upsert_rows`	Insert or update rows by matching key

Account

Tool	Description
`get_user_balance`	Check credit balance and account info

Configuration

All settings are configurable via environment variables in your Claude Desktop config:

Variable	Default	Description
`DATABAR_API_KEY`	(required)	Your Databar API key
`DATABAR_BASE_URL`	`https://api.databar.ai/v1`	API base URL
`CACHE_TTL_HOURS`	`24`	How long to cache results
`MAX_POLL_ATTEMPTS`	`150`	Max polling attempts for async tasks
`POLL_INTERVAL_MS`	`2000`	Polling interval in milliseconds
`DATABAR_SAFE_MODE`	`true`	Check credit balance before each enrichment
`DATABAR_MAX_COST`	`10`	Max credits per single request
`DATABAR_MIN_BALANCE`	`1`	Minimum balance threshold before blocking
`DATABAR_AUDIT_LOG`	(none)	File path to write audit logs
`DATABAR_MAX_RESULT_LENGTH`	`50000`	Truncate results longer than this

Safe mode vs unsafe mode

By default, the server runs in safe mode — it checks your credit balance before each enrichment to prevent accidental overspending. If you find this slows down bulk operations, you can disable it:

{
  "env": {
    "DATABAR_API_KEY": "your-key",
    "DATABAR_SAFE_MODE": "false"
  }
}

In unsafe mode, the server skips balance checks. You’ll see a warning at startup and before bulk operations, but spending will not be blocked.

Example prompts

Here are some things you can ask Claude once the MCP server is connected:

“Get me David Abaev’s LinkedIn profile”
“Verify the email david@databar.ai”
“Find the email for John Smith at Google using a waterfall”
“Enrich these 10 domains with company data”
“List my tables and show the columns for the first one”
“Create 5 rows in my leads table with name, email, and company”
“How many credits do I have left?”

Results are cached for 24 hours by default. Cached lookups don’t consume credits. Use skip_cache: true to force a fresh lookup.

Task data is stored for 1 hour after completion. If you need the results later, make sure to save them promptly.

npm package

Install with npm or npx

GitHub

View source, report issues, or contribute

Overview

Agent Skills

What you can do

Enrichments

Waterfalls

Tables

Row Operations

Quick start

Available tools

Enrichments

Waterfalls

Tables

Row operations

Account

Configuration

Safe mode vs unsafe mode

Example prompts

Links

npm package

GitHub

Overview

Agent Skills

​What you can do

Enrichments

Waterfalls

Tables

Row Operations

​Quick start

​Available tools

​Enrichments

​Waterfalls

​Tables

​Row operations

​Account

​Configuration

​Safe mode vs unsafe mode

​Example prompts

​Links

npm package

GitHub

What you can do

Quick start

Available tools

Enrichments

Waterfalls

Tables

Row operations

Account

Configuration

Safe mode vs unsafe mode

Example prompts

Links