Field-by-field comparison

Compare the evidence before choosing an MCP.

Each signal stays separate, missing facts remain visible, and the column order follows your selection.

MCPs in this comparison

Uncheck an MCP to remove it. Comparing two or three keeps each signal in its own row.

Open canonical comparison link

Comparable alternatives

Shown only when capability or industry context overlaps.

Side-by-side MCP evidence comparison
Evidence fieldMetabase MCPShortlist candidateGoogle MCP Toolbox for DatabasesMCP100 Recommended
Task fit
Best for
  • Let AI clients query and build against a user's own Metabase instance under existing permissions
  • Metabase users who need to let ai clients query and build against a user's own metabase instance under existing permissions.
  • Schema exploration and database-aware coding in development environments
  • Connecting one MCP layer to supported Google Cloud and third-party databases
  • Defining structured, parameterized database tools with integrated authentication and observability
Not ideal for
  • The endpoint is instance-specific: https://{your-metabase.example.com}/api/metabase-mcp. Query, SQL, write, and delivery scopes can expose or mutate sensitive analytics content; OAuth never grants more than the connecting user's Metabase permissions.
  • Unrestricted natural-language SQL against production data
  • Teams unwilling to operate and secure a local or hosted Toolbox process
Avoid when
  • The endpoint is instance-specific: https://{your-metabase.example.com}/api/metabase-mcp. Query, SQL, write, and delivery scopes can expose or mutate sensitive analytics content; OAuth never grants more than the connecting user's Metabase permissions.
  • The configured database user can modify production data or schema beyond the approved task
  • Sensitive query results cannot be sent to the AI client
  • Credentials would be committed in tools.yaml or MCP configuration
Provenance
Provenance details

First-party MCP

Metabase · Publisher source ↗

First-party MCP

Google · Publisher source ↗

Maintenance
Maintenance details

Repo: Not documented

Package: Not documented

Repo: Sep 24, 2026

Package: Not documented

Popularity evidence
GitHub starsNot documented

16,485

GitHub stars · checked 2026-09-24T04:14:16.258000Z

Shared repository stars

49,767

Shared repository stars (not MCP-specific) · checked 2026-10-20

Not documented
Client coverage
Client coverage detailsNot documented
Claude Code✓ Local stdio
Claude Desktop✓ Local stdio
Codex✓ Local stdio
VS Code✓ Local stdio
Cursor✓ Local stdio
OpenCode✓ Local stdio
Client coverage noteLocal stdio runs on your computer. Streamable HTTP connects to a remotely hosted MCP server.
Access and data
AuthenticationOAuth 2.0 through the Metabase instance's embedded OAuth server.Authentication depends on the database source and can include database username/password, Google Cloud IAM, or other source-specific mechanisms. Use a dedicated read-only identity and secret manager or protected environment variables.
CostThe built-in MCP has no separately documented fee. Metabase has free Open Source and paid hosted/commercial plans; certain AI/usage features have separate usage pricing.The Apache-licensed Toolbox and npm server have no documented MCP usage fee. Database services, Google Cloud resources, network transfer, observability backends, hosting, and the AI client may incur normal charges.
PermissionsThe MCP is scoped to the connecting user's Metabase permissions. Capability scopes include content read/write, query execution, SQL execution and delivery writes depending on authorization.Effective permissions come from each configured database identity and the enabled prebuilt or custom tools. Generic prebuilt sets can include schema discovery and execute_sql; custom tools can constrain statements, parameters, and accessible sources.
Data handlingNot documented in the reviewed sources. The reviewed Metabase MCP page does not provide an MCP-specific retention or training statement. Queries can expose data accessible through the user's Metabase permissions.The Toolbox process connects directly to configured databases and returns selected schemas, rows, query results, and errors to the MCP client. Credentials may be supplied through environment variables or configuration; integrated cloud authentication and OpenTelemetry are available.
Limitations
Tradeoffs
  • Official Metabase documentation establishes the built-in MCP server and distinguishes it from community implementations. Exact runtime tool inventory/context footprint remains instance/version dependent.
  • Prebuilt tools are quick to adopt but may expose generic execute_sql capability; custom tools require more design but provide a narrower contract.
  • The npx path is convenient but the publisher recommends binary or container installation for standard reliable deployments.
  • Supporting many database engines increases configuration flexibility and operational complexity.
Risk contextDepending on granted scopes, the MCP can run queries/SQL and create, edit or trash Metabase content, potentially exposing sensitive analytics or modifying shared dashboards/questions.Generic SQL tools can expose or mutate large amounts of data and retrieved database text can carry prompt-injection content. Prefer a non-production replica, read-only credentials, allow-listed custom parameterized tools, query limits, audit logs, and no secrets in config. This review does not claim MCP100 execution testing.
Evidence date
Editorial review2026-10-192026-07-24
Candidate evidence2026-10-202026-09-24T04:25:05.554391Z

Popularity, maintenance, fit, permissions, and client support are independent evidence fields.

Read the evidence method →