# Fix list: PostgreSQL (archived MCP reference server) From Anchor Terminal's listing at https://www.anchorterminal.com/tools/postgres-reference-server-archived, the October 2026 research run, assessed 1 October 2026. Grade F, 18.6 out of 100. This is everything the published grade says the listing lacks, the biggest possible gain to the total first. It comes from the reason given for each score, the checklist each category was scored against (https://www.anchorterminal.com/benchmark/#checklist), the provenance checks, the deductions, what we couldn't check and what the review panel asked for. A fix counts at the next check, once it's public. For a coding agent working on PostgreSQL (archived MCP reference server): work through the items below in the product, its docs and its public pages. Each category gives the reason for its score, with the points each checklist item earned, and the checklist itself, so the gap is the items that earned less than their points. Change the product, not the wording, and keep a note of what you changed and where it's published. ## 1. Reliability, 13 out of 100, up to 17.4 more on the total Why it scored 13: Archived and superseded, so we scored what's left.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). The checklist (https://www.anchorterminal.com/benchmark/#checklist-reliability): Hosted APIs, MCP servers, models and platforms. - 20, a public status page with component history (Statuspage, Instatus, BetterStack or the vendor's own). - 0 to 30, the incident record for the last 90 days on that page. 30 for a clean record or trivial incidents only, 20 for minor incidents only, 10 for one major outage (an hour or more of a core API down, or errors across the board), 0 for several. 5 when there's no history we could read, and the note says so. - 15, rate limits documented with numbers. - 15, documented 429 or overload handling (Retry-After, backoff guidance), and idempotency keys or safe-retry guidance where writes are involved. - 10, an SLA published for any paid tier. - 10, the surface agents use is generally available, not beta or preview. Local packages, SDKs, frameworks and stdio MCP servers. - 20, installs from an official package with supported runtimes stated. - 25, a public CI and test suite, passing on the default branch. - 0 to 25, open crash or regression issues relative to activity (25 for few and handled, 0 for many, old and unanswered). - 15, semver discipline and breaking changes called out in a changelog. - 15, version 1.0 or later, or declared stable. Protocols are read from their reference implementations, the public facilitators or servers, spec stability and test vectors. ## 2. Security & auth, 5 out of 100, up to 16.6 more on the total Why it scored 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). The checklist (https://www.anchorterminal.com/benchmark/#checklist-security): - 0 to 30, the credential model. 30 for OAuth 2.1 with scopes, or scoped and revocable keys with rotation. 20 for plain revocable API keys. 10 for one all-powerful key. 10 off when a secret can travel in a URL query string as a documented option. - 0 to 20, read-only or least-privilege modes, and confirmation or approval for destructive actions. - 0 to 15, prompt-injection posture where the tool returns untrusted content (documented mitigations or guidance). A tool that returns no untrusted content gets 10. - 0 to 15, audit logs or per-call visibility for the operator. - 0 to 20, a security programme. security.txt or a disclosure policy, a bug bounty, SOC 2 or ISO 27001, advisories handled in public. Models are read for retention, whether API data trains models (and whether that's off by default), zero-retention options and certifications. Frameworks for telemetry defaults, approval hooks, guardrails and sandboxing. ## 3. Schema & documentation, 29 out of 100, up to 11.5 more on the total Why it scored 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). The checklist (https://www.anchorterminal.com/benchmark/#checklist-schema): APIs and MCP servers. - 25, a machine-readable contract (a public OpenAPI file or similar; for MCP, typed JSON Schema inputs on every tool). - 10, llms.txt or Markdown docs served for agents. - 0 to 20, descriptions that say what a tool is for, when to use it and when not to, read from the tool definitions in the source or the API reference. - 0 to 15, typed inputs with enums, constraints and required fields, and no free-form JSON blobs. - 0 to 15, examples and documented error responses. - 15, versioning and a public changelog. Models are read from the API reference, the OpenAPI file, llms.txt, the structured-output and tool-use docs and the model cards. Frameworks from docs a model can follow, typed interfaces, examples and the API reference. ## 4. Agent ergonomics, 38 out of 100, up to 10.1 more on the total Why it scored 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. The checklist (https://www.anchorterminal.com/benchmark/#checklist-ergonomics): - 0 to 25, context cost. For MCP, the number and size of the tool definitions (25 for ten or fewer compact tools, 15 for 11 to 30, 5 for more than 30, plus up to 10 back for toolsets, dynamic loading or read-only subsets). For APIs, whether responses can be sized (field selection, limits, summaries). - 20, pagination, filtering and output-size controls. - 20, actionable, documented error responses, codes and messages an agent can recover from. - 20, idempotency or safe retries, and for MCP the `readOnlyHint` and `destructiveHint` annotations. - 15, sensible defaults, few required parameters, and official SDKs in at least two languages. Models are read for tool use, structured output, prompt caching, context length, batch and SDKs. Frameworks for how much code and how many defaults a tool-calling agent with MCP needs. ## 5. Maintenance & community, 0 out of 100, up to 8.8 more on the total Why it scored 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). The checklist (https://www.anchorterminal.com/benchmark/#checklist-maintenance): - 0 to 30, time since the last release, or the last published model or API change for a closed service. 30 within 30 days, 20 within 90, 10 within 180, 0 older. - 20, at least three releases or dated changelog entries in the last 90 days. - 0 to 25, responsiveness. Issues and pull requests answered on GitHub (the open issues and how recent the replies are). For closed services, a public changelog and a support or community channel that answers, 0 to 15. - 15, presence in the official MCP registry under a verified namespace (MCP servers), or current official SDKs (APIs and models). - 10, package health, current dependencies and CI. Models are read for deprecation notice periods and model churn rather than release counts. ## 6. Payments & pricing, 60 out of 100, up to 5 more on the total Why it scored 60: Free, self-hosted, nothing to buy, so 20 + 20 + 20. No payment protocol (0). The rubric is mechanical here, and it says nothing in favour of using it. The checklist (https://www.anchorterminal.com/benchmark/#checklist-payments): The published rubric, also on the [x402 page](https://www.anchorterminal.com/x402/). - 40, a machine payment protocol (x402, MPP or L402) on the tool's own endpoints. 10 to 30 when it covers only some endpoints or only goes through a third party, and the note says which. - 20, per-call or per-unit pricing published without a login. 10 for public plan-only pricing, 0 for "contact sales" or prices behind a login. - 20, a free tier or trial that doesn't need a card. - 20, autonomous onboarding, meaning an agent can get access without a person signing up in a browser (keyless use, x402, a programmatic key API). Payment platforms and agent wallets rarely charge for their own API over a machine protocol, so the first line has steps for them, and the highest one that applies counts. 40 when x402, MPP or L402 runs on all their own endpoints, 30 when it runs on part of their own API, 25 when their merchants can accept one, 20 for running a facilitator, 15 for paying as a buyer, and 0 when the only protocol is their own. Merchant acceptance sits above a facilitator because the platform's own customers can charge agents through it, while a facilitator settles for sellers who wire up the protocol themselves. The counter-argument (a facilitator does more for the protocol as a whole) has a point. Each note says which step applied. Open-source software you run yourself is scored on its hosted or paid option if it has one. A free, self-hosted package with nothing to buy gets 20, 20 and 20 for the last three lines, and 0 to 40 for the first only if it ships a payment protocol. ## 7. Transparency & trust, 77 out of 100, up to 2 more on the total Made of editorial 80, provenance 74. Why it scored 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). The checklist (https://www.anchorterminal.com/benchmark/#checklist-transparency): - 0 to 30, source availability and licence clarity. 30 for open source under an OSI licence, 15 for closed with clear terms, 0 for unclear terms. - 0 to 30, data handling and retention statements that agree with each other (privacy policy, DPA, retention periods, subprocessors). - 0 to 20, a deprecation policy or notices with dates. - 0 to 20, telemetry disclosed with an opt-out (local software), or subprocessors and data locations disclosed (hosted). The other half of Transparency and trust is the provenance score, computed from checked facts (below). The category score is the mean of the two. Provenance checks not met in full (half of this category, computed from checked facts): - Domain age: modelcontextprotocol.io, registered 2024-11-18 (1 year) (3 of 15) - Status page: not found (0 of 10) ## Deductions Each comes off the total. A fixed and documented problem counts for less at the next check. - -8: 2026-09-30, the read-only bypass Datadog Security Labs published on 21 August 2025 (SQL injection that escapes the read-only transaction and runs arbitrary SQL) is still unfixed, with no advisory, and the package drew 118,589 npm downloads in the week to 30 September 2026. We date it by that week, not by the disclosure, because the exposure is current. Every new install still gets the hole, and the fix that would let the deduction decay never came (https://securitylabs.datadoghq.com/articles/mcp-vulnerability-case-study-SQL-injection-in-the-postgresql-mcp-server/; https://api.npmjs.org/downloads/point/2026-09-24:2026-09-30/@modelcontextprotocol/server-postgres). - -2: the tool description ("Run a read-only SQL query") and the main repository's README ("Read-only database access") still promise a guarantee the code doesn't keep, a misleading claim since the August 2025 disclosure (https://github.com/modelcontextprotocol/servers-archived/blob/main/src/postgres/index.ts; https://github.com/modelcontextprotocol/servers#archived). ## What we couldn't check What we couldn't read counted as absent. Publishing it on a page a plain HTTP fetch can read (not only in a browser) lets the next check count it. - unchecked: whether the mcp/postgres Docker image is still published on Docker Hub - unchecked: the date npm deprecated the package, since the registry record carries the message but no date - We read the Datadog write-up's date and title but the page body didn't load. The bypass mechanism in our notes comes from reading the server source ## Weaknesses - The read-only transaction can be escaped with a multi-statement query, disclosed in August 2025 and never fixed - Archived on 29 May 2025 with no security guarantees, and pinned to MCP SDK 1.0.1 - Connection string and password passed on the command line, visible in process lists - No row limit, pagination or tool annotations - The npm deprecation message names no successor, so installs keep coming ## What costs an agent a turn today The notes we give agents before they call it. Each one is a workaround an agent shouldn't need. - Don't use for new work. Migrate to Postgres MCP Pro with `--access-mode=restricted` or a managed provider's server - If you inherit it, connect with a database role that can only SELECT. The transaction won't stop writes - Add `LIMIT` to every query. The server returns every row as pretty-printed JSON - Read the `/schema` resources for column names before querying, since there's no schema tool ## What the review panel asked for - a truthful description - a schema tool - advisory for the bypass ## When it's done Send what changed and where it's published as a dispute (https://www.anchorterminal.com/builders/#disputes, or `POST https://www.anchorterminal.com/api/v1/contact` with `"kind": "dispute"`). Disputes are answered in public, and the listing is checked again by the same checklist. Paying for an audit or a listing claim changes nothing here.