Introducing the ORION-DBs MCP Server

Navigating Open Research Information Resources on BigQuery with LLMs

Abstract

ORION-DBs provides access to multiple open research information resources, but their heterogeneous schemas make exploration and querying difficult. This post presents orion-mcp, an MCP server that lets LLMs like Claude explore schemas, draft SQL, estimate costs, and run queries, providing a practical entry point for users less familiar with open research information resources and BigQuery.

About

Working with ORION-DBs can be tricky: providers use different schemas and pre-processing routines, making cross-database comparisons hard and writing queries against complex schemas a steep learning curve. To give a sense of scale: ORION-DBs currently spans six different BigQuery projects from different providers, 52 datasets with various tables, and over 14 000 GB of data.

orion-mcp is a Model Context Protocol server that addresses this by connecting ORION-DBs to AI apps like Claude Desktop. Once installed, you can ask questions about the available data sources or have the LLM draft and run SQL queries against them.

The tool builds directly on the comprehensive schema documentation that ORION-DBs providers maintain, making that work directly useful when chatting with an LLM. It is at an early stage, so feedback is welcome!

What it does

Explore schemas

These tools work without a BigQuery account, using pre-fetched schemas the ORION-DBs website when orion-mcp is started:

• orion_list_datasets — list all available ORION-DBs datasets
• orion_list_tables — list tables in a specific dataset
• orion_get_db_schema — inspect the full schema of a table

Query BigQuery

Once you know what you want to query, the LLM writes and executes SQL. To avoid surprise costs, a dry-run cost estimate is always shown before any query runs. SELECT * queries are blocked to prevent unnecessary large scans.

• orion_estimate_query_cost — estimate bytes scanned and cost before running
• orion_run_bq_query — execute the confirmed query

Use case

This screencast demonstrates a typical session.

First, I ask whether OpenAlex is available and which version is the most recent. Then, I ask Claude to compare the version provided by MultiObs with the version provided by SUB Göttingen. Having gained this overview, I ask Claude to retrieve the number of diamond open access articles from first authors from Germany between 2021 and 2025. Throughout, Claude provides me with the estimated query costs and presents the SQL for the queries.

You may wish to be more explicit about how the results are presented. Often, a dynamic chart is unnecessary.

Installation

Full instructions are in the GitHub repo README.

In summary, the server runs in a Docker container connected to Claude Desktop via its MCP config file. Authentication uses Google’s Application Default Credentials, so your local gcloud credentials are used directly — no service account keys needed. A Google Cloud account includes 1 TB of free queries per month.

Requirements: Docker and the Google Cloud CLI (gcloud). The server is implemented in R using {mcptools} and {ellmer}.

Responsible use

LLMs make mistakes. Always verify that queries return the results you intended before using them in any analysis. If you plan to use this in a publication, check the outlet’s policy on AI-assisted work and document your process accordingly. Please acknowledge resources used.