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

MCP server for interacting with Oracle databases

- Trust score: 61/100 (medium)
- Change this week: +11
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- npm · `@marcelo-ochoa/server-oracle`: 61/100 (this document), [markdown](https://verifymcp.io/servers/marcelo-ochoa-oracle/marcelo-ochoa-server-oracle.md), [page](https://verifymcp.io/servers/marcelo-ochoa-oracle/marcelo-ochoa-server-oracle)

## Channel facts

- Registry: `npm`
- Package: `@marcelo-ochoa/server-oracle`
- Version: `1.0.7`
- 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**: 87/100
  - No malware found by supply-chain analysis.
  - Only part of the dependency tree could be resolved (96 of 100), 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 (96 of 100), 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**: 58/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (fair).
  - Context-footprint check failed: tool/resource definitions use about 1270 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**: 0/100
  - Stability not yet verified: not enough scan history yet (needs a 30-day window).
- **Tool Coverage**: 97/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 92% of tool parameters carry a description.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

**Unverified: 1 category.** A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.

## Install

### Claude

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

### Codex

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

### opencode

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

### OpenClaw

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

### Hermes

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

### Other

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

## 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 61, +37)

- [security regression] Provenance: unverified → fail
- [security improvement] Install scripts: unverified → pass
- [security improvement] Known CVEs: unverified → partial
- [security improvement] Malware scan: unverified → pass
- [security] Stability: Stability not yet verified: not enough scan history yet (needs a 30-day window).
- [functional regression] Tool coverage: 100 → unverified
- [functional regression] Schema quality: 100 → unverified
- [functional improvement] License: unverified → pass
- [functional improvement] Schema quality: unverified → fair
- [functional improvement] Maintenance: unverified → pass
- [functional improvement] MCP protocol: unverified → pass
- [functional improvement] Dependency health: unverified → partial
- [functional] Licence: MIT

### 2026-07-31 (score 24, 0)

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

### 2026-07-30 (score 24, −26)

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

### 2026-07-27 (score 50)

First indexed and scored.

## MCP tools (5)

### `orcl-query` (~348 tokens)

This tool executes SQL queries in a READY ONLY session connected to an Oracle database. If no active connection exists, it uses MCP server registration argument and environment variables ORACLE_USER and ORACLE_PASSWORD.

You should:

Execute the provided SQL query.

Return the results in Json 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

### `orcl-explain` (~253 tokens)

Generate and display the execution plan for a given SQL query using Oracle's EXPLAIN PLAN command. This tool helps you understand how Oracle will execute your query, including information about table access methods, join operations, indexes used, estimated costs, and cardinality estimates.

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 Oracle will process the query, including operation types, object names, costs, bytes, and cardinality estimates.

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

### `orcl-stats` (~261 tokens)

Get comprehensive statistics for a specific Oracle database object (table, index, or view). This tool retrieves detailed information including row counts, block statistics, segment size, index information, column statistics, partition details, and other metadata that can help optimize queries and understand data distribution.

Args:

name: The name of the database object 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 object statistics including row counts, block usage, size information, indexes, partitions, and column details with histograms and data distribution metrics.

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...)
- `name` (string, required): SQL Object to get stats

### `orcl-connect` (~160 tokens)

Provides an interface to connect to a specified database. If a database connection is already active, prompt the user for confirmation before switching to the new connection.


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 Oracle connect string (e.g. host.docker.internal:1521/freepdb1
- `password` (string, required): The Oracle password (e.g. tiger
- `user` (string, required): The Oracle user (e.g. scott

### `orcl-awr` (~248 tokens)

Generate an Automatic Workload Repository (AWR) report or AWR SQL report for Oracle database performance analysis. AWR reports provide comprehensive performance metrics including database statistics, wait events, top SQL statements, system resources, and performance recommendations.

If no sql_id is provided, generates a full AWR database report with:
\- Database instance information and configuration
\- Load profile and instance efficiency metrics
\- Top wait events and time model statistics
\- SQL statistics ordered by various metrics (elapsed time, CPU time, executions, etc.)
\- Segment statistics and I/O statistics
\- Memory and SGA statistics
\- System and session statistics

If a sql_id is provided, generates an AWR SQL report focused on that specific SQL statement with:
\- SQL text and execution statistics
\- Execution plans and plan history
\- Bind variable information
\- Wait events specific to the SQL
\- Performance metrics over time

Args:

sql_id (optional): The SQL ID for generating an AWR SQL report. If omitted, generates a full AWR database report.

Returns:

Comprehensive performance report in text or HTML format with actionable insights for database tuning and optimization.

Input parameters:

- `sql_id` (string)

## Diagnostics

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

## Score history

- 2026-08-03: 61
- 2026-08-02: 61
- 2026-08-01: 24
- 2026-07-31: 24
- 2026-07-30: 24
- 2026-07-28: 50
- 2026-07-27: 50

## Links

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