# ADCIRC Model Setup MCP Server (pypi · adcirc-mcp)

ADCIRC model configuration debugging, parameter lookup, and validation

- Trust score: 78/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-10-04

## Components

- pypi · `adcirc-mcp`: 78/100 (this document), [markdown](https://verifymcp.io/servers/oceanmodeling-adcirc-mcp/adcirc-mcp.md), [page](https://verifymcp.io/servers/oceanmodeling-adcirc-mcp/adcirc-mcp)

## Channel facts

- Registry: `pypi`
- Package: `adcirc-mcp`
- Version: `0.1.2`
- 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 2026-10-04.

- **Supply Chain Security**: 100/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - Runs hatchling.build at install time, a recognised build step with no custom scripting around it.
  - 0 of 28 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 100/100
  - Source repository is publicly reachable at the declared URL.
  - Cryptographically verified build provenance (signed, bound to oceanmodeling/ocean-mcp).
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 2 days ago).
  - Publishes a security disclosure policy (SECURITY.md).
- **Schema Quality & AI Usability**: 69/100
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 996 tokens (~99/item across 10 items; 10 tools + 0 resources), lean.
  - 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**: 71/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 0% of tool parameters carry a description.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 10 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 10 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **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

### How do I install the ADCIRC Model Setup MCP Server server?

ADCIRC Model Setup MCP Server runs locally as a PyPI package, launched with uvx adcirc-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add oceanmodeling-adcirc-mcp -- uvx adcirc-mcp
```

### Cursor

```json
{
  "mcpServers": {
    "oceanmodeling-adcirc-mcp": {
      "command": "uvx",
      "args": [
        "adcirc-mcp"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "oceanmodeling-adcirc-mcp": {
      "command": "uvx",
      "args": [
        "adcirc-mcp"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add oceanmodeling-adcirc-mcp -- uvx adcirc-mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "oceanmodeling-adcirc-mcp": {
      "type": "local",
      "command": [
        "uvx",
        "adcirc-mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add oceanmodeling-adcirc-mcp --command uvx --arg adcirc-mcp
```

### Hermes

```yaml
mcp_servers:
  oceanmodeling-adcirc-mcp:
    command: "uvx"
    args: ["adcirc-mcp"]
```

### Netclaw

```json
{
  "McpServers": {
    "oceanmodeling-adcirc-mcp": {
      "Transport": "stdio",
      "Command": "uvx",
      "Arguments": [
        "adcirc-mcp"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add oceanmodeling-adcirc-mcp -t stdio -c uvx -a adcirc-mcp
```

### Other

```json
{
  "mcpServers": {
    "oceanmodeling-adcirc-mcp": {
      "command": "uvx",
      "args": [
        "adcirc-mcp"
      ]
    }
  }
}
```

## 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.

### 2026-10-01 (score 78)

First indexed and scored.

## MCP tools (10)

### `adcirc_fetch_docs` (~67 tokens)

Fetch documentation from the ADCIRC wiki for a specific topic.

Retrieves the wiki page content as plain text.

Args:
    topic: Wiki page title or topic (e.g., 'Fort.15', 'NWS', 'Hot Start').

Input parameters:

- `topic` (string, required)

Output parameters:

- `result` (string)

### `adcirc_search_docs` (~75 tokens)

Search the ADCIRC wiki and return matching pages with summaries.

Args:
    query: Search terms (e.g., 'tidal forcing', 'hot start', 'wetting drying').
    limit: Maximum number of results to return (default 10).

Input parameters:

- `limit` (integer)
- `query` (string, required)

Output parameters:

- `result` (string)

### `adcirc_parse_fort15` (~94 tokens)

Parse an ADCIRC fort.15 control file into a structured summary.

Extracts run parameters, timestep, forcing configuration, tidal
constituents, output settings, and station locations.

Args:
    file_path: Path to the fort.15 file on disk.
    content: Raw text content of the fort.15 file (alternative to file_path).

Input parameters:

- `content`
- `file_path`

Output parameters:

- `result` (string)

### `adcirc_parse_fort14` (~98 tokens)

Parse an ADCIRC fort.14 mesh file header (NOT the full mesh).

Returns grid name, node count, element count, and boundary information.
Does NOT load node coordinates or element connectivity into memory.

Args:
    file_path: Path to the fort.14 file on disk.
    content: Raw text content (or header portion) of the fort.14 file.

Input parameters:

- `content`
- `file_path`

Output parameters:

- `result` (string)

### `adcirc_parse_fort13` (~77 tokens)

Parse an ADCIRC fort.13 nodal attributes file.

Returns attribute names, default values, and non-default node counts.

Args:
    file_path: Path to the fort.13 file on disk.
    content: Raw text content of the fort.13 file.

Input parameters:

- `content`
- `file_path`

Output parameters:

- `result` (string)

### `adcirc_parse_fort22` (~106 tokens)

Parse an ADCIRC fort.22 meteorological forcing file header.

Returns format type, time range, and spatial extent based on the NWS value.

Args:
    nws: NWS value from fort.15 (determines the file format).
    file_path: Path to the fort.22 file on disk.
    content: Raw text content of the fort.22 file.

Input parameters:

- `content`
- `file_path`
- `nws` (integer)

Output parameters:

- `result` (string)

### `adcirc_explain_parameter` (~102 tokens)

Look up any ADCIRC fort.15 parameter by name.

Returns description, valid values, typical range, common pitfalls,
and companion file requirements. Also covers NWS values, tidal
constituents, and nodal attributes.

Args:
    parameter: Parameter name (e.g., 'NWS', 'DTDP', 'TAU0', 'M2', 'mannings_n_at_sea_floor').

Input parameters:

- `parameter` (string, required)

Output parameters:

- `result` (string)

### `adcirc_list_parameters` (~98 tokens)

List all ADCIRC fort.15 parameters grouped by category.

Returns a cheat sheet of parameter names with brief descriptions.
Also lists tidal constituents and nodal attributes.

Args:
    category: Optional filter by category (e.g., 'time_stepping', 'forcing', 'friction', 'output', 'tidal', 'solver', 'wetting_drying', 'spatial', 'meteorological').

Input parameters:

- `category`

Output parameters:

- `result` (string)

### `adcirc_validate_config` (~197 tokens)

Validate an ADCIRC configuration with comprehensive checks.

Parses fort.15 and optionally cross-references with fort.14 and fort.13.
Checks CFL condition, parameter consistency, NWS/file matching,
DRAMP adequacy, station counts, and output frequency sanity.

Args:
    fort15_path: Path to the fort.15 file.
    fort15_content: Raw text of fort.15 (alternative to path).
    fort14_path: Optional path to fort.14 for cross-validation.
    fort13_path: Optional path to fort.13 for cross-validation.
    min_edge_length: Optional minimum mesh edge length in meters (for CFL check).
    max_depth: Optional maximum water depth in meters (for CFL check).

Input parameters:

- `fort13_path`
- `fort14_path`
- `fort15_content`
- `fort15_path`
- `max_depth`
- `min_edge_length`

Output parameters:

- `result` (string)

### `adcirc_diagnose_error` (~82 tokens)

Diagnose an ADCIRC run error from a log snippet or error description.

Matches against known ADCIRC failure patterns (CFL violation, hot-start
issues, NWS mismatch, boundary errors, etc.) and suggests fixes.

Args:
    error_text: Error message, log snippet, or description of the problem.

Input parameters:

- `error_text` (string, required)

Output parameters:

- `result` (string)

## Diagnostics

Captured diagnostic sections: Provenance, Install scripts, Dependencies. The full working is on the page: https://verifymcp.io/servers/oceanmodeling-adcirc-mcp/adcirc-mcp#diagnostics

## Score history

- 2026-10-04: 78
- 2026-10-03: 78
- 2026-10-02: 78
- 2026-10-01: 78

## Common questions

### What is the ADCIRC Model Setup MCP Server server?

ADCIRC Model Setup MCP Server is listed in the public MCP registry as io.github.oceanmodeling/adcirc-mcp. ADCIRC model configuration debugging, parameter lookup, and validation. This page covers its PyPI package (adcirc-mcp).

### Is the ADCIRC Model Setup MCP Server server safe to use?

ADCIRC Model Setup MCP Server scores 78 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 4 October 2026. Its build provenance is signed and verified. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the ADCIRC Model Setup MCP Server server expose?

ADCIRC Model Setup MCP Server exposes 10 tools: adcirc_fetch_docs, adcirc_search_docs, adcirc_parse_fort15, adcirc_parse_fort14, adcirc_parse_fort13, and 5 more. Their descriptions and schemas cost roughly 996 tokens of context every time the server is loaded.

### Is the ADCIRC Model Setup MCP Server server still maintained?

ADCIRC Model Setup MCP Server is still listed as active in the MCP registry. We last reached this channel on 4 October 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What licence is the ADCIRC Model Setup MCP Server server under?

ADCIRC Model Setup MCP Server declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

## Links

- PyPI project: https://pypi.org/project/adcirc-mcp/
- Socket report: https://socket.dev/pypi/package/adcirc-mcp
- Repository: https://github.com/oceanmodeling/ocean-mcp
- Changelog RSS feed: https://verifymcp.io/servers/oceanmodeling-adcirc-mcp/adcirc-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/oceanmodeling-adcirc-mcp/adcirc-mcp.json
- HTML version of this page: https://verifymcp.io/servers/oceanmodeling-adcirc-mcp/adcirc-mcp