# io.github.marcelo-ochoa/postgres (npm · @marcelo-ochoa/server-postgres)

MCP server for interacting with PostgreSQL databases

- Trust score: 49/100 (low)
- Change this week: +17
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- npm · `@marcelo-ochoa/server-postgres`: 49/100 (this document), [markdown](https://verifymcp.io/servers/marcelo-ochoa-postgres/marcelo-ochoa-server-postgres.md), [page](https://verifymcp.io/servers/marcelo-ochoa-postgres/marcelo-ochoa-server-postgres)

## Channel facts

- Registry: `npm`
- Package: `@marcelo-ochoa/server-postgres`
- Version: `1.0.8`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-08-03.

- **Supply Chain Security**: 37/100
  - Malware scan not yet available for this package.
  - Only part of the dependency tree could be resolved (109 of 113), so this covers what we could see, not the whole tree.
  - No install/post-install scripts declared.
  - Only part of the dependency tree could be resolved (109 of 113), so this covers what we could see, not the whole tree.
- **Provenance & Transparency**: 45/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 144 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 54/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (poor).
  - Context-footprint check failed: tool/resource definitions use about 1273 tokens (~254/item across 5 items; 5 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 23/100
  - Stability observed for 7 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### Claude

```bash
claude mcp add marcelo-ochoa-postgres -- npx -y @marcelo-ochoa/server-postgres
```

### Codex

```bash
codex mcp add marcelo-ochoa-postgres -- npx -y @marcelo-ochoa/server-postgres
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "marcelo-ochoa-postgres": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "@marcelo-ochoa/server-postgres"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add marcelo-ochoa-postgres --command npx --arg -y --arg @marcelo-ochoa/server-postgres
```

### Hermes

```yaml
mcp_servers:
  marcelo-ochoa-postgres:
    command: "npx"
    args: ["-y", "@marcelo-ochoa/server-postgres"]
```

### Other

```json
{
  "mcpServers": {
    "marcelo-ochoa-postgres": {
      "command": "npx",
      "args": [
        "-y",
        "@marcelo-ochoa/server-postgres"
      ]
    }
  }
}
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-08-02 (score 49, +25)

- [security regression] Provenance: unverified → fail
- [security improvement] Install scripts: unverified → pass
- [security improvement] Known CVEs: unverified → partial
- [functional improvement] Schema quality: unverified → poor
- [functional improvement] MCP protocol: unverified → pass
- [functional improvement] Maintenance: unverified → pass
- [functional improvement] Stability: unverified → 0.20
- [functional improvement] Dependency health: unverified → partial
- [functional improvement] License: unverified → pass
- [functional] Licence: MIT

### 2026-08-01 (score 24, +19)

- [functional improvement] Tool coverage: unverified → 100
- [functional improvement] Schema quality: unverified → 100

### 2026-07-31 (score 5, −27)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-30 (score 32, +24)

- [functional regression] Dependency health: partial → unverified
- [functional improvement] Schema quality: unverified → 100
- [functional improvement] Tool coverage: unverified → 100

### 2026-07-28 (score 8, −24)

- [functional regression] Tool coverage: 100 → unverified
- [functional regression] Schema quality: 100 → unverified
- [functional improvement] Dependency health: unverified → partial

### 2026-07-27 (score 32)

First indexed and scored.

## MCP tools (5)

### `pg-query` (~346 tokens)

This tool executes SQL queries in a READ ONLY session connected to a PostgreSQL database. If no active connection exists, it uses MCP server registration argument and environment variables PG_USER and PG_PASSWORD.

You should:

Execute the provided SQL query.

Return the results in Toon format.

Args:

sql: The SQL query to execute.


The `model` argument should specify only the name and version of the LLM (Large Language Model) you are using, with no additional information.
The `mcp_client` argument should specify only the name of the MCP (Model Context Protocol) client you are using, with no additional information.

Returns:

Json-formatted query results.
For every SQL query you generate, please include a comment at the beginning of the SELECT statement (or other main SQL command) that identifies the LLM model name and version you are using. Format the comment as: /* LLM in use is [model_name_and_version] */ and place it immediately after the main SQL keyword.
For example:

SELECT /* LLM in use is claude-sonnet-4 */ column1, column2 FROM table_name;

Please apply this format consistently to all SQL queries you generate, using your actual model name and version in the comment

Input parameters:

- `mcp_client` (string, required): Specify the name and version of the MCP client implementation being used (e.g. Copilot, Claude, Cline...)
- `model` (string, required): The name (and version) of the language model being used by the MCP client to process requests (e.g. gpt-4.1, claude-sonnet-4, llama4...)
- `sql` (string, required): The SQL query to execute

### `pg-stats` (~238 tokens)

Get comprehensive statistics for a specific PostgreSQL table. This tool retrieves detailed information including row counts, table size, index information, column statistics, and other metadata that can help optimize queries and understand data distribution.

Args:

name: The name of the table to get statistics for.


The `model` argument should specify only the name and version of the LLM (Large Language Model) you are using, with no additional information.
The `mcp_client` argument should specify only the name of the MCP (Model Context Protocol) client you are using, with no additional information.

Returns:

Json-formatted table statistics including row counts, size information, indexes, and column details.

Input parameters:

- `mcp_client` (string): Specify the name and version of the MCP client implementation being used (e.g. Copilot, Claude, Cline...)
- `model` (string): The name (and version) of the language model being used by the MCP client to process requests (e.g. gpt-4.1, claude-sonnet-4, llama4...)
- `name` (string, required): The name of the table to get statistics for

### `pg-explain` (~242 tokens)

Generate and display the execution plan for a given SQL query using PostgreSQL's EXPLAIN command. This tool helps you understand how PostgreSQL will execute your query, including information about table scans, joins, indexes used, and estimated costs.

Args:

sql: The SQL query to explain.


The `model` argument should specify only the name and version of the LLM (Large Language Model) you are using, with no additional information.
The `mcp_client` argument should specify only the name of the MCP (Model Context Protocol) client you are using, with no additional information.

Returns:

Detailed execution plan showing how PostgreSQL will process the query, including costs, row estimates, and access methods.

Input parameters:

- `mcp_client` (string, required): Specify the name and version of the MCP client implementation being used (e.g. Copilot, Claude, Cline...)
- `model` (string, required): The name (and version) of the language model being used by the MCP client to process requests (e.g. gpt-4.1, claude-sonnet-4, llama4...)
- `sql` (string, required): The SQL query to explain

### `pg-connect` (~323 tokens)

Provides an interface to connect to a specified PostgreSQL database. If a database connection is already active, the tool will close the existing connection before establishing a new one.

This tool accepts three required parameters:

connectionString: The PostgreSQL connection string without embedded credentials (e.g., postgresql://host:port/dbname or host:port/dbname). To enable encryption (SSL), append ?sslmode=require to the connection string.
user: The PostgreSQL username
password: The PostgreSQL password

The credentials are stored in environment variables PG_USER and PG_PASSWORD for the session.

The `model` argument should only be used to specify the name and version of the LLM (Large Language Model) you are using, with no additional information.
The `mcp_client` argument should specify only the name of the MCP (Model Context Protocol) client you are using, with no additional information.

Input parameters:

- `connectionString` (string, required): The PostgreSQL connection string (e.g. postgresql://host:port/dbname or host:port/dbname)
- `mcp_client` (string): Specify the name and version of the MCP client implementation being used (e.g. Copilot, Claude, Cline...)
- `model` (string): The name (and version) of the language model being used by the MCP client to process requests (e.g. gpt-4.1, claude-sonnet-4, llama4...)
- `password` (string, required): The PostgreSQL password
- `user` (string, required): The PostgreSQL user (e.g. postgres)

### `pg-awr` (~124 tokens)

Generate a PostgreSQL performance report similar to Oracle AWR. Includes database statistics, top queries (requires pg_stat_statements extension), table/index statistics, connection info, and optimization recommendations.

Input parameters:

- `mcp_client` (string): Specify the name and version of the MCP client implementation being used (e.g. Copilot, Claude, Cline...)
- `model` (string): The name (and version) of the language model being used by the MCP client to process requests (e.g. gpt-4.1, claude-sonnet-4, llama4...)

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/marcelo-ochoa-postgres/marcelo-ochoa-server-postgres#diagnostics

## Score history

- 2026-08-03: 49
- 2026-08-02: 49
- 2026-08-01: 24
- 2026-07-31: 5
- 2026-07-30: 32
- 2026-07-28: 8
- 2026-07-27: 32

## Links

- npm package: https://www.npmjs.com/package/@marcelo-ochoa/server-postgres
- Socket report: https://socket.dev/npm/package/@marcelo-ochoa/server-postgres
- Repository: https://github.com/marcelo-ochoa/servers
- Changelog RSS feed: https://verifymcp.io/servers/marcelo-ochoa-postgres/marcelo-ochoa-server-postgres/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/marcelo-ochoa-postgres/marcelo-ochoa-server-postgres/changelog.json
- HTML version of this page: https://verifymcp.io/servers/marcelo-ochoa-postgres/marcelo-ochoa-server-postgres