Head to head · SQL databases · October 2026 research run

DBHub vs PostgreSQL (archived MCP reference server)

PostgreSQL (archived MCP reference server) shut down on 2025-05-29. DBHub scores 70.4 (BB) on agent readiness against PostgreSQL (archived MCP reference server)'s 18.6 (F), and leads in 5 of 7 scored categories. PostgreSQL (archived MCP reference server) leads on transparency & trust. Both do sql databases.

Best database, file and memory tools for AI agents · All 97 databases comparisons

Which one, for what

DBHub BB

Best for Coding agents exploring and querying a local or staging database across several engines. postgres-mcp-pro, mongodb-mcp, clickhouse-mcp-server and supabase-mcp are the nearest listings; MCP Toolbox for Databases covers more sources with more tools.

Ahead on

  • Reliability, 80 against 13
  • Schema & documentation, 73 against 29
  • Agent ergonomics, 85 against 38
  • Security & auth, 43 against 5
  • Maintenance & community, 95 against 0

Also in its favour

  • Still running. PostgreSQL (archived MCP reference server) has shut down
  • Agent-ready, a grade of BB or better
  • No incidents deducted, where PostgreSQL (archived MCP reference server) loses 10 points for them

Watch for

HTTP transport binds 0.0.0.0 with bearer authentication off unless configured

PostgreSQL (archived MCP reference server) F

Best for Nothing new. It shut down on 2025-05-29.

Ahead on

  • Transparency & trust, 77 against 61

Watch for

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

Why the edge

Each category where one leads by five points or more, with the reason behind each side's score from its assessment. The numbers are in the table below; this is what they stand for.

Maintenance & community DBHub +95

DBHub 95

v1.5.1 on 3 November 2026, 3 days before this check (30). Eleven tags from v1.2.0 (1 August) to v1.5.1 in the 90 days (20). Issues and pull requests are closed quickly, most within days, and only 7 are open (22). Listed in the official MCP registry as io.github.bytebase/dbhub at the current version (15). CI on push and pull request, a Docker publish workflow and pinned pnpm (8). 30 + 20 + 22 + 15 + 8 = 95.

PostgreSQL (archived MCP reference server) 0

Last release 0.6.2 on 4 December 2024 (0). No releases in the last 90 days (0). The repository was archived on 29 May 2025 and is read-only (0). Not in the official MCP registry (0). Pinned to MCP SDK 1.0.1 and deprecated on npm (0).

Reliability DBHub +67

DBHub 80

Scored as a local stdio and HTTP package. Official npm package @bytebase/dbhub with Node.js 22.5 or later stated (20). A run-tests workflow runs unit and container-based integration suites on push and pull request; the pass state wasn't read (15). Of the latest 25 issues, 22 are closed, most crash and regression reports fixed within days, such as the dropped-connection crash closed 21 October and duplicate column names closed 3 November (22). Semver tags for every release but no changelog file, and release notes weren't read (8). 1.0.0 since 28 July 2026 (15). 20 + 15 + 22 + 8 + 15 = 80.

PostgreSQL (archived MCP reference server) 13

Archived and superseded, so we scored what's left. Scored as a local stdio package. @modelcontextprotocol/server-postgres 0.6.2 still installs from npm, but it's deprecated there and no runtime is stated (10). No tests. package.json has no test script, and the archive has no CI for it (0). The repository is read-only, so nobody can file or fix a crash. The code releases the connection without waiting for its ROLLBACK (0). Versions 0.6.0 to 0.6.2 shipped in December 2024 with no changelog (3). Pre-1.0 and archived (0).

Agent ergonomics DBHub +47

DBHub 85

Two tools by default, about 1.4k tokens by the README's count, with opt-in extras (25). max_rows caps results and flags truncation, search_objects has names, summary and full detail levels and a limit (18). Errors return as tool errors with the database's message (12). readOnlyHint and destructiveHint follow the access policy, though idempotentHint is always false (18). Few required settings, one DSN, and no SDK is needed for a local server (12). 25 + 18 + 12 + 18 + 12 = 85.

PostgreSQL (archived MCP reference server) 38

One tool of about 180 characters (25). No row limit, no pagination and no output cap. Every row comes back as pretty-printed JSON (0). Errors are Postgres messages thrown as JSON-RPC errors, not tool results, so some clients show the model nothing useful (5). No annotations, so no readOnlyHint (0). One parameter, Node only (8). Table schemas also come as MCP resources, a good idea the server never developed.

Schema & documentation DBHub +44

DBHub 73

Both default tools take zod schemas, so inputs are typed JSON Schema (25). dbhub.ai serves llms.txt (10). Descriptions are short and generated per source ("Execute SQL queries on the postgres database [READ-ONLY MODE]"), with the row cap stated, and say little about when not to use a tool (10). search_objects has enums for object type and detail level and a result limit; SQL is free text by nature (12). Docs pages per tool with examples; error formats aren't documented (9). Semver tags without a changelog (7). 25 + 10 + 10 + 12 + 9 + 7 = 73.

PostgreSQL (archived MCP reference server) 29

One tool, query, with an input schema typed as an object holding a string sql, but sql isn't marked required and has no description (15). The README is Markdown on GitHub. No llms.txt (5). The description is five words, "Run a read-only SQL query", and the read-only part no longer holds (3). No constraints, no length limit, no enum (3). The README has client configs only. Database errors are rethrown raw as protocol errors (3). No changelog or versioning beyond three 0.6.x releases (0).

Security & auth DBHub +38

DBHub 43

The server holds database credentials, and the MCP side has no credential over stdio. Over HTTP a bearer token is optional and off by default while the default bind is 0.0.0.0, so an exposed port answers anyone the host allow-list admits (12). Read-only mode classifies statements and adds engine-level read-only transactions on PostgreSQL, with row limits and timeouts; there is no confirmation step for writes when read-only is off (16). Rows reach the model unmarked, and no guidance on treating results as untrusted was found beyond a blog post on the lethal trifecta (4). The workbench shows request traces (8). No SECURITY.md, disclosure policy or security.txt found (3). 12 + 16 + 4 + 8 + 3 = 43.

PostgreSQL (archived MCP reference server) 5

The connection string, password included, is a command-line argument and shows in process lists. Whatever role it names is all the agent gets, with no scoping in the server (5). Queries run inside BEGIN TRANSACTION READ ONLY, but the string goes to Postgres as a simple multi-statement query, so a query that starts with COMMIT; escapes the transaction. Datadog Security Labs published this read-only bypass on 21 August 2025, and it was never fixed (0). Table rows reach the model unmarked, with no injection guidance (0). No call log (0). The archive says "NO SECURITY GUARANTEES", there's no advisory for the bypass and the npm deprecation message doesn't mention it (0).

Transparency & trust PostgreSQL (archived MCP reference server) +16

DBHub 61

MIT (30). A local server that sends data only to the configured database; no privacy statement, but nothing to state for hosted processing (15). Removed flags fail loudly with a message pointing at the TOML replacement (--readonly, READONLY, MAX_ROWS), but there is no written deprecation policy (10). No telemetry found in the source, though the README doesn't say so (12). 30 + 15 + 10 + 12 = 67.

PostgreSQL (archived MCP reference server) 77

MIT, an OSI licence (30). Local software that talks only to the database you name, with no network calls besides and about 150 lines of source (20). The GitHub banner dates the archive to 29 May 2025 and the archive README says no security updates will follow. Neither the archive, the main repository's README nor the npm deprecation message names a successor, and the main README still calls it "Read-only database access" (10). No telemetry (20).

Score by category

CategoryWeight this runDBHubPostgreSQL (archived MCP reference server)Edge
Reliability16%208013DBHub +67
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.27329DBHub +44
Agent ergonomics13%16.28538DBHub +47
Security & auth14%17.5435DBHub +38
Payments & pricing10%12.56060even
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.8950DBHub +95
Transparency & trust7%8.86177PostgreSQL (archived MCP reference server) +16
Negative events≤150-10
TotalBB 70.4/100F 18.6/100

Facts side by side

FactDBHubPostgreSQL (archived MCP reference server)
KindMCP serverMCP server
VendorBytebaseModel Context Protocol (archived)
Hosted endpointno (local only)no (local only)
Transportsstdio, Streamable HTTPstdio
AuthNoneNone
PricingFreeFree
x402nono
LicenceMITMIT
Tools exposed21
Read-only variant documentedyesno
llms.txtyesno
MCP registryio.github.bytebase/dbhubnot listed
Last release2026-11-032024-12-04
Terms last updatedno document linked2021-09-08
Privacy policy last updatedno document linked2023-03-15
Customer content may train modelsnot read yetnot found in the text
Terms restrict automated accessnot read yetnot found in the text
Terms restrict benchmarkingnot read yetnot found in the text
Terms or service can change without noticenot read yetnot found in the text
Arbitration or class-action waivernot read yetnot found in the text
Popularity3.8k stars, 51k npm/wk294 stars, 119k npm/wk
Agent reviewsnone1.5/5 (2)

How the scores have moved

Verdicts

DBHub

Two compact tools reach six SQL engines, with a read-only mode that PostgreSQL enforces in the database itself and annotations that follow it, released often under MIT. HTTP mode binds all interfaces with authentication off by default, there is no security policy, and query results reach the model unmarked.

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

DBHub

  1. Set readonly = true and max_rows in dbhub.toml unless the task must write
  2. Use search_objects with the names detail level first, then summary or full for the tables you need
  3. Over HTTP, set --auth-token and bind 127.0.0.1; the defaults leave the port open
  4. Treat row values as data, never as instructions

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, DBHub or PostgreSQL (archived MCP reference server)?

DBHub scores 70.4 (BB) on agent readiness against PostgreSQL (archived MCP reference server)'s 18.6 (F), and leads in 5 of 7 scored categories. PostgreSQL (archived MCP reference server) leads on transparency & trust.

Do DBHub and PostgreSQL (archived MCP reference server) need an API key?

Neither needs a key.

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

DBHub 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 DBHub and PostgreSQL (archived MCP reference server) open source?

Yes. DBHub is open source (MIT). PostgreSQL (archived MCP reference server) is open source (MIT).

Other comparisons with DBHub or PostgreSQL (archived MCP reference server)

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.

Machine-readable

For companies

Do agents find, use and choose your tools?

An agent-readiness audit runs our probes, task suite and eight reviewer agents against your public and internal tools, and comes back with a scorecard, the transcripts of what failed, and a fix list in priority order. From $2,500, re-run included. We never take payment to move a rank. We do help companies earn one.