Bitscale Ai

What is Bitscale Ai?

Bitscale Ai is an MCP server that connects a BitScale workspace to Claude Desktop, enabling users to manage and run data enrichment grids directly through Claude’s interface. It is intended for users who want to query their BitScale grids, run enrichment jobs, and inspect workspace details without leaving the chat.

How to use Bitscale Ai?

Install uv (one‑time), then add the bitscale MCP server entry to your Claude Desktop configuration file (claude_desktop_config.json) with your BITSCALE_API_KEY. Restart Claude Desktop. Alternatively, add the server via the claude mcp add command for Claude Code.

Key features of Bitscale Ai

• List all grids with search and pagination, including column definitions.
• Get full schema, settings, and data sources for any grid.
• Retrieve a ready‑to‑use curl command and API contract for a grid.
• Run grids synchronously (results in ≤120 s) or asynchronously (get a request_id).
• Poll the status of an async or timed‑out grid run.
• Rotate the workspace API key (irreversible, invalidates current key).
• View workspace plan, credit balances, search limits, and member counts.

Use cases of Bitscale Ai

• Discover and inspect all BitScale grids available in a workspace.
• Run a lead‑enrichment grid by providing company name and website.
• Check the execution status of a long‑running grid enrichment.
• Obtain the exact API contract and curl command for a grid before running it.
• Rotate a compromised API key directly from the chat.

FAQ from Bitscale Ai

What tools does Bitscale Ai provide?

The server exposes seven tools: get_workspace_details, list_grids, get_grid_details, get_grid_curl, run_grid, get_run_status, and rotate_api_key.

How do I run a BitScale grid?

First call get_grid_curl with the grid ID to discover the required input labels. Then call run_grid with the grid ID and an inputs map of human‑readable labels to values. Results are returned synchronously within 120 seconds; for longer runs, use async mode and poll with get_run_status.

What is the difference between input labels and output column UUIDs?

inputs use human‑readable labels (e.g., "company_name") derived from the grid’s BitScale API data source. output_columns use UUIDs from get_grid_details to filter which enriched columns appear. The response outputs are keyed by UUID, each containing a name (display name) and value.

What is the rate limit for the BitScale API?

The default rate limit is 5 requests per second per workspace. All requests hit the https://api.bitscale.ai/api/v1 base endpoint.

How can I check the status of an async grid run?

Call get_run_status every 2–5 seconds with the request_id returned by run_grid (async mode) until the status becomes completed.