M
MCP Directory CURATED DIRECTORY
911 MCP servers indexed
中文
← Back to directory
B

BigQuery MCP Server

Community
Secure, read-only access to BigQuery for LLMs.
How to install ↓ Compare GitHub source repository ↗
Category
Database #15 of 58
Stars
★ 148 Popular
Transport
stdio (local process)
Runtime
Node.js 14+
Credentials
API key / credential required
License
MIT
Last commit
62FMRS · C

This server provides secure read-only access to BigQuery, ideal for teams that want to use AI for data queries while enforcing strict controls on sensitive data. It defaults to read-only and offers field-level restrictions, adding a layer of safety. However, users must be aware that data is sent to LLM providers and that field restrictions are not a firewall.

Strongest · Security and permissions 16/20 Weakest · Reliability 8/20

Reliability
8/20
Security and permissions
16/20
Maintenance
10/20
Documentation
15/20
Setup experience
13/20
Why each score
Reliability 8/20
The README and source suggest the server performs MCP handshake and tool listing, but no executable CI workflow or committed tests are provided to verify key paths. The source code details were not reviewed, so end-to-end reliability is uncertain. Deductions for lack of execution evidence and unresolved error handling.
Security and permissions 16/20
The server is designed as read-only with dry-run validation and field restrictions documented. No red flags for malware or credential theft were found in the available evidence. However, the security model is cooperative and may not be a hard firewall. Overall, least privilege and data boundaries appear reasonably addressed, but source inspection was limited.
Maintenance 10/20
The repository has 145 stars and 3 open issues, with recent commits. License is MIT, but no security response channel is evident. Maintenance is active but governance and versioning have gaps.
Documentation 15/20
The README provides detailed setup, authentication, configuration, and limitation sections, along with a dedicated protection doc. However, troubleshooting guidance and full API reference are missing. Documentation is solid but not exhaustive.
Setup experience 13/20
Installation steps are clear with npx and local build examples, and client config snippets are provided. But it requires Google Cloud credentials and a BigQuery environment, which may add complexity. As no execution was performed, setup robustness is inferred.

Static review · not runListed 2026-08-07

Read the FMRS scoring method →

Fit and risk

What it can accessConnects to a database

Best for

  • Developers and analysts who want to query BigQuery quickly via AI assistants
  • Organizations that need to prevent AI agents from modifying data
  • Environments with sensitive data that require field-level access restrictions

Not for

  • Scenarios requiring write, update, or delete operations
  • Users who need unrestricted access to all columns
  • Strict security environments that cannot tolerate data leaving the network (since results are sent to LLM providers)

Required permissions

  • BigQuery read permissions (e.g., roles/bigquery.user or roles/bigquery.dataViewer)
  • For service account auth, access to the service account key file
  • For advanced features, permission to list datasets and tables, and run dry-run queries

Risks and side effects

  • Data exfiltration: query results are sent to LLM providers (Anthropic, OpenAI) and may leave your network
  • Despite field restrictions, AI agents may attempt to infer data through crafted queries
  • Misconfiguration may weaken restrictions, e.g., incorrectly setting preventedFields or maximum bytes billed

Setup

Before you start

Runtime：Node.js 14+

  1. Ensure you have Node.js 14+ and a Google Cloud project with BigQuery enabled.
  2. Authenticate with gcloud auth application-default login.
  3. Add the server to your MCP client config, e.g., for Claude Desktop or Claude Code, use:

{
"mcpServers": {
"bigquery": {
"command": "npx",
"args": ["-y", "@ergut/mcp-bigquery-server", "--project-id", "your-project-id"]
}
}
}

  1. Restart your client and start chatting.
claude_desktop_config.json 
{
  "mcpServers": {
    "bigquery": {
      "command": "npx",
      "args": [
        "-y",
        "@ergut/mcp-bigquery-server",
        "--project-id",
        "your-project-id"
      ]
    }
  }
}

Shown for Claude Desktop. Other clients may use a different file or key (VS Code uses "servers") — the configurator below converts it.

.vscode/mcp.json
{
  "servers": {
    "bigquery": {
      "command": "npx",
      "args": [
        "-y",
        "@ergut/mcp-bigquery-server",
        "--project-id",
        "your-project-id"
      ]
    }
  }
}

Goes in your project's .vscode/mcp.json (VS Code uses a "servers" key).

Terminal
claude mcp add bigquery -- npx -y @ergut/mcp-bigquery-server --project-id your-project-id

Run it in a terminal; replace any <…> placeholders with your own values first.

Generate and validate client config

Check that it works

Add the server config to claude_desktop_config. or .mcp., restart the client, then ask Claude something like "What tables are in my BigQuery datasets?" — real table names in the answer confirm the connection works.

Troubleshooting

  1. Check MCP client config and ensure `npx` is available
  2. Verify Google Cloud authentication: run `gcloud auth application-default login`
  3. Ensure BigQuery API is enabled and the project ID is correct
  4. If using a service account, check the key file path
  5. For Protected Mode, validate config.json exists and is correctly formatted

Things to try

Once connected, you can ask your AI assistant things like:

  • What were our top 10 customers last month?
  • List the tables and views in my BigQuery datasets and label each resource type.
  • Count the records in the patients table for the last 30 days without exposing any personal fields.
  • Which columns in my warehouse look like they contain sensitive data?

Use cases

Ask business questions in natural language, e.g., 'What were our top 10 customers last month?'
Explore dataset schemas to identify tables and views.
Analyze data without writing complex SQL, while keeping sensitive data protected.

Supported clients

Claude Desktop
Claude Code

Listed from the project's documentation, not tested by this site.

Overview

BigQuery MCP Server is a Model Context Protocol (MCP) server that provides secure, read-only access to BigQuery datasets. It acts as a translator between AI assistants and your data warehouse, allowing you to query data in natural language. The server only allows SELECT statements; every query is validated by BigQuery's dry-run planner, so INSERT, UPDATE, DELETE, DROP, TRUNCATE, EXPORT DATA, and MERGE are all rejected. It supports configurable query byte limits, field-level access restrictions, and automatic discovery of sensitive columns (e.g., names, emails, SSNs) to prevent AI agents from reading PII, PHI, or financial data.

Similar servers

Compare with other MCP servers

Source revision a298b53cd21d Data synced 2026-10-12 Read the FMRS scoring method