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

clickhouseSupabase MCP

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

Comparable alternatives

Azure MCP ServerMCP100 RecommendedChrome DevTools MCPMCP100 RecommendedContext7 MCPMCP100 RecommendedGrafana Cloud MCPMCP100 RecommendedGoogle MCP Toolbox for DatabasesMCP100 RecommendedPlaywright MCPMCP100 Recommended

Shown only when capability or industry context overlaps.

Side-by-side MCP evidence comparison
Evidence field	clickhouseMCP100 Recommended	Supabase MCPMCP100 Recommended
Task fit
Best for	High-volume analytical database exploration and query workflows for ClickHouse deployments.	Inspecting one Supabase project's schema, logs, advisors, and docs Development environments using project-scoped read-only access Teams that understand database and deployment consequences
Not ideal for	Teams outside the publisher ecosystem or without least-privilege credentials	Production database administration by an unattended agent Users needing only public Supabase documentation Organizations unable to grant Supabase OAuth access to an MCP client
Avoid when	The connected identity is broader than the task requires Tool calls cannot be reviewed before consequential mutations	The server would be left organization-wide rather than project-scoped Write-capable SQL, migrations, functions, branches, or storage changes cannot be human-approved Production secrets or customer records could be returned to the model
Provenance
Provenance details	First-party MCP ecosystem:clickhouse · Publisher source ↗	First-party MCP Supabase · Publisher source ↗
Maintenance
Maintenance details	Repo: Sep 21, 2026 Package: Not documented	Repo: Sep 24, 2026 Package: Sep 21, 2026
Popularity evidence
GitHub stars	878 GitHub stars · checked 2026-09-24T04:14:39.535000Z	2,919 GitHub stars · checked 2026-09-24T04:16:20.864000Z
Package downloads / 30 days	248,614 package downloads / 30 days · checked 2026-09-24T04:17:50.251000Z	406,869 package downloads / 30 days · checked 2026-09-24T04:17:50.300000Z
Client coverage
Client coverage details	Claude Code✓ Local stdio Claude Desktop✓ Local stdio Codex✓ Local stdio VS Code✓ Local stdio Cursor✓ Local stdio OpenCode✓ Local stdio	Claude Code✓ Streamable HTTP Claude Desktop✓ Streamable HTTP Codex✓ Streamable HTTP VS Code✓ Streamable HTTP Cursor✓ Streamable HTTP OpenCode✓ Streamable HTTP
Client coverage note	Local stdio runs on your computer. Streamable HTTP connects to a remotely hosted MCP server.
Access and data
Authentication	The official server uses configured ClickHouse connection credentials and supports secure deployment settings.	Hosted MCP uses browser OAuth and grants organization access to the MCP client. Project scope, read-only mode, and feature groups are encoded in URL query parameters. Enterprise-managed authentication is GA for eligible Team and Enterprise organizations. Access remains scoped to each user's existing Supabase role and permissions.
Cost	The MCP integration has no separately verified MCP100 price conclusion. Publisher subscriptions, API usage, compute, storage, and AI-client charges may apply.	The MCP server is open source; normal Supabase plan, database, branch, Edge Function, storage, and usage charges apply. Branching and some storage operations require a paid plan.
Permissions	The configured ClickHouse user's grants and RBAC define the authoritative accessible schemas and queries. MCP-side general writes require CLICKHOUSE_ALLOW_WRITE_ACCESS, and DROP, TRUNCATE, DELETE, and similar destructive operations require the additional CLICKHOUSE_ALLOW_DROP control.	Without project_ref the hosted server can access all projects in the authorized organization. With project_ref it is limited to one project. read_only=true uses a read-only Postgres user for SQL and disables listed mutation tools. Feature groups can further narrow exposed tools.
Data handling	Authorized service data and tool results pass through the MCP server to the connected AI client. Review the publisher and client data policies before using sensitive data & databases information.	Enabled tools may return schemas, table data from executed queries, logs, security/performance advisors, project metadata, publishable keys, types, and Edge Function source. Hosted mode sends tool requests through Supabase's MCP service.
Limitations
Tradeoffs	Queries can expose large or sensitive datasets and consume cluster capacity even when writes are disabled.	Project scoping removes account-level tools but materially reduces blast radius. Read-only mode disables mutations but also removes migration, deployment, branch, and storage configuration workflows. Branching and some storage capabilities require paid plans; the server is pre-1.0 and may change.
Risk context	MCP-side write and destructive opt-ins are safety controls, not the primary security boundary. Queries can expose large or sensitive datasets and consume cluster capacity. Use a narrowly privileged ClickHouse identity, least-privilege grants/RBAC, narrowly enabled tools, and explicit confirmation for mutations even when destructive controls are disabled.	Unscoped or write-enabled access can affect every project in an organization, execute SQL, apply migrations, deploy functions, or manage branches. Always set project_ref and read_only=true first, minimize feature groups, and avoid production data.
Evidence date
Editorial review	2026-07-30	2026-09-05
Candidate evidence	2026-09-24T04:25:05.554391Z	2026-09-24T04:25:05.554391Z

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

Read the evidence method →