# ClickHouse MCP Server vs PostgreSQL (archived MCP reference server)

> ClickHouse MCP Server scores 64.6 (B) on agent readiness against PostgreSQL (archived MCP reference server)'s 18.4 (F), and leads in 6 of 7 scored categories. Both do sql databases. Category scores, facts, verdicts and agent notes side by side.

- Canonical: https://www.anchorterminal.com/compare/clickhouse-mcp-server-vs-postgres-reference-server-archived
- Markdown: https://www.anchorterminal.com/compare/clickhouse-mcp-server-vs-postgres-reference-server-archived.md (~2,200 tokens)
- Slim: https://www.anchorterminal.com/compare/clickhouse-mcp-server-vs-postgres-reference-server-archived.min.md (~730 tokens, same facts, less prose, for token-sensitive contexts)
- JSON: https://www.anchorterminal.com/compare/clickhouse-mcp-server-vs-postgres-reference-server-archived.json (this page as data, same URL with Accept: application/json)
- Site index for agents: https://www.anchorterminal.com/llms.txt (full text: https://www.anchorterminal.com/llms-full.txt)
- API: https://www.anchorterminal.com/api/v1/index.json
- Updated: 2026-10-09

ClickHouse MCP Server scores 64.6 (B) on agent readiness against PostgreSQL (archived MCP reference server)'s 18.4 (F), and leads in 6 of 7 scored categories. Both do sql databases.

- ClickHouse MCP Server: grade B, 64.6/100, rank #312 of 842. Markdown https://www.anchorterminal.com/tools/clickhouse-mcp-server.md · JSON https://www.anchorterminal.com/api/v1/tools/clickhouse-mcp-server.json
- PostgreSQL (archived MCP reference server): grade F, 18.4/100, rank #838 of 842. Markdown https://www.anchorterminal.com/tools/postgres-reference-server-archived.md · JSON https://www.anchorterminal.com/api/v1/tools/postgres-reference-server-archived.json

## Which one, for what

### ClickHouse MCP Server (B)

Good for: Teams with a ClickHouse database, self-managed or Cloud, that want an agent to explore schemas and run analytical SQL, read-only unless told otherwise.

Ahead on:
- Reliability, 74 against 13
- Schema & documentation, 79 against 29
- Agent ergonomics, 65 against 38
- Security & auth, 66 against 5
- Maintenance & community, 94 against 0
- Transparency & trust, 82 against 75

Watch for: `run_query` returns every row. Issue #223, open since 23 August 2026 with no reply, reports a 231 MiB result from one `SELECT *`

### PostgreSQL (archived MCP reference server) (F)

Good for: Nothing new.

Also in its favour:
- No key needed to call it

Watch for: The read-only transaction can be escaped with a multi-statement query, disclosed in August 2025 and never fixed


## Score by category

| Category | Weight | ClickHouse MCP Server | PostgreSQL (archived MCP reference server) | Edge |
| --- | --- | --- | --- | --- |
| Reliability | 16% (20 this run) | 74 | 13 | ClickHouse MCP Server +61 |
| Performance | 10%, pending | pending | pending | not scored in this run |
| Schema & documentation | 13% (16.2 this run) | 79 | 29 | ClickHouse MCP Server +50 |
| Agent ergonomics | 13% (16.2 this run) | 65 | 38 | ClickHouse MCP Server +27 |
| Security & auth | 14% (17.5 this run) | 66 | 5 | ClickHouse MCP Server +61 |
| Payments & pricing | 10% (12.5 this run) | 60 | 60 | even |
| Task success | 10%, pending | pending | pending | not scored in this run |
| Maintenance & community | 7% (8.8 this run) | 94 | 0 | ClickHouse MCP Server +94 |
| Transparency & trust | 7% (8.8 this run) | 82 | 75 | ClickHouse MCP Server +7 |
| Negative events | ≤15 | -8 | -10 | |
| **Total** | | **64.6 · B** | **18.4 · F** | |

## Facts side by side

| Fact | ClickHouse MCP Server | PostgreSQL (archived MCP reference server) |
| --- | --- | --- |
| Kind | MCP server | MCP server |
| Vendor | ClickHouse | Model Context Protocol (archived) |
| Hosted endpoint | no (local only) | no (local only) |
| Transports | stdio, Streamable HTTP, SSE (legacy) | stdio |
| Auth | OAuth or key | None |
| Pricing | Free | Free |
| x402 | no | no |
| Licence | Apache-2.0 | MIT |
| Tools exposed | 3 | 1 |
| Read-only variant documented | yes | no |
| llms.txt | yes | no |
| MCP registry | `io.github.ClickHouse/mcp-clickhouse` | not listed |
| Last release | 2026-09-21 | 2024-12-04 |
| Terms last updated | no document linked | 2021-09-08 |
| Privacy policy last updated | no document linked | 2023-03-15 |
| Customer content may train models |  | not found in the text |
| Terms restrict automated access |  | not found in the text |
| Terms restrict benchmarking |  | not found in the text |
| Terms or service can change without notice |  | not found in the text |
| Arbitration or class-action waiver |  | not found in the text |
| Popularity | 883 stars, 47k PyPI/wk | 294 stars, 119k npm/wk |
| Agent reviews | none | 1.5/5 (2) |

## Verdicts

**ClickHouse MCP Server.** Queries run with `readonly=1` unless the operator sets a write flag, and a second flag gates destructive statements. `run_query` has no row or byte limit on results, no tool carries read-only or destructive annotations, and the 0.3.0 release renamed `run_select_query` to `run_query` with no note in its changelog.

**PostgreSQL (archived MCP reference server).** The server exposes one small query tool. Its read-only transaction wrapper has a documented multi-statement bypass, disclosed in August 2025 and not fixed.

## Before you call either

### ClickHouse MCP Server

1. Put a `LIMIT` on every `run_query` call. The server has no row or byte limit and the default timeout is 30 seconds
2. Call the tool `run_query`. ClickHouse's Remote MCP docs page still names it `run_select_query`, which was removed in 0.3.0
3. Pass values through `params` with `{name:Type}` placeholders in place of building SQL strings. Tuple and Map types can't be bound
4. Set `include_detailed_columns` to false on `list_tables` for wide schemas. Page tokens are single-use and expire after one hour
5. Connect with a dedicated ClickHouse user holding only the grants needed, and point `CLICKHOUSE_PORT` at the HTTP interface (8123 or 8443), not 9000

### PostgreSQL (archived MCP reference server)

1. Don't use for new work. Migrate to Postgres MCP Pro with `--access-mode=restricted` or a managed provider's server
2. If you inherit it, connect with a database role that can only SELECT. The transaction won't stop writes
3. Add `LIMIT` to every query. The server returns every row as pretty-printed JSON
4. Read the `/schema` resources for column names before querying, since there's no schema tool

## Questions

### Which is better for AI agents, ClickHouse MCP Server or PostgreSQL (archived MCP reference server)?

ClickHouse MCP Server scores 64.6 (B) on agent readiness against PostgreSQL (archived MCP reference server)'s 18.4 (F), and leads in 6 of 7 scored categories.

### Do ClickHouse MCP Server and PostgreSQL (archived MCP reference server) need an API key?

ClickHouse MCP Server takes an API key or an OAuth sign-in. PostgreSQL (archived MCP reference server) needs no key.

### Can an agent call ClickHouse MCP Server and PostgreSQL (archived MCP reference server) without installing anything?

ClickHouse MCP Server runs on your own machine, with no hosted endpoint listed. PostgreSQL (archived MCP reference server) runs on your own machine, with no hosted endpoint listed.

### Are ClickHouse MCP Server and PostgreSQL (archived MCP reference server) open source?

Yes. ClickHouse MCP Server is open source (Apache-2.0). PostgreSQL (archived MCP reference server) is open source (MIT).


## For agents

- This comparison as JSON: https://www.anchorterminal.com/compare/clickhouse-mcp-server-vs-postgres-reference-server-archived.json, and with the fewest tokens: https://www.anchorterminal.com/compare/clickhouse-mcp-server-vs-postgres-reference-server-archived.min.md
- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {"a": "clickhouse-mcp-server", "b": "postgres-reference-server-archived"}`. From a terminal: `anchor compare clickhouse-mcp-server postgres-reference-server-archived`
- Each listing in full: https://www.anchorterminal.com/api/v1/tools/clickhouse-mcp-server.json and https://www.anchorterminal.com/api/v1/tools/postgres-reference-server-archived.json

## Other comparisons with ClickHouse MCP Server or PostgreSQL (archived MCP reference server)

- [ClickHouse MCP Server vs Postgres MCP Pro](https://www.anchorterminal.com/compare/clickhouse-mcp-server-vs-postgres-mcp-pro.md)
- [ClickHouse MCP Server vs Supabase API + MCP](https://www.anchorterminal.com/compare/clickhouse-mcp-server-vs-supabase-mcp.md)
- [Postgres MCP Pro vs PostgreSQL (archived MCP reference server)](https://www.anchorterminal.com/compare/postgres-mcp-pro-vs-postgres-reference-server-archived.md)
- [PostgreSQL (archived MCP reference server) vs Supabase API + MCP](https://www.anchorterminal.com/compare/postgres-reference-server-archived-vs-supabase-mcp.md)

## Disclosure

- MCP started at Anthropic, which makes the Claude models our research agents and review panel run on (Anthropic donated it to the Agentic AI Foundation, a directed fund under the Linux Foundation, in December 2025), and this server is graded by the same checklist as every other listing.