Skip to main content
Glama
CROCODILE-CESM

regional-ocean-debugger-mcp

regional-ocean-debugger-mcp

MCP server for debugging regional ocean (MOM6 + CESM) model runs.

Combines practical log analysis tools with a searchable knowledge base of expert interview transcripts, giving an LLM agent both the ability to inspect model output files and access to domain-expert guidance.

Tools

Tool

Purpose

read_run_log(case_dir, component, lines)

Read recent CESM/MOM6 run log lines

find_errors(case_dir)

Scan all logs for FATAL/NaN/CFL/etc.

classify_error(error_text)

Match error against known MOM6 failure modes

read_mom6_params(case_dir, filter)

Read MOM_input + MOM_override

diff_params(case_dir_a, case_dir_b)

Compare MOM_input between two cases

check_cfl(case_dir)

Evaluate CFL stability from MOM_input timestep settings

suggest_timestep(resolution_deg)

Recommend DT and DT_THERM for a given resolution

read_diag_table(case_dir)

Parse enabled MOM6 diagnostics

suggest_diagnostics(symptoms)

Suggest useful diagnostics for a given problem

query_domain_knowledge(question)

Search expert interview knowledge base

get_parameter_advice(param_name)

Look up guidance for a specific MOM6 parameter

Related MCP server: Log Analyzer MCP Server

Resources

URI

Content

ocean://case/{case_dir}/params

Parsed MOM_input as KEY=VALUE

ocean://case/{case_dir}/errors

Extracted errors from recent logs

ocean://knowledge/index

Summary of knowledge base contents

Knowledge Base

Domain knowledge comes from expert interviews on regional MOM6 modelling (private repo: AidanJanney/RegionalMOM6_InterviewTranscripts). Topics include: OBC setup, tidal forcing, bathymetry, stability, BGC, grid design, and regional ocean dynamics.

The transcripts are a git submodule in data/transcripts/. After cloning this repo:

git submodule update --init data/transcripts

Setup

pip install -e .
# with the transcripts submodule:
git submodule update --init data/transcripts

Running

regional-ocean-debugger-mcp
# or
python server.py

Add to .mcp.json:

{
  "mcpServers": {
    "ocean-debugger": {
      "command": "python",
      "args": ["/path/to/MCP_regional_ocean_debugger/server.py"]
    }
  }
}

Design

  • Stateless: reads from the filesystem per call

  • No ML dependencies: knowledge search is keyword-based (fast, transparent, works without GPU)

  • Composable: use find_errorsclassify_errorquery_domain_knowledge in sequence for triage

  • Private data: transcripts submodule is private; do not make public without authorisation

CESM / MOM6 paths on Derecho

Cases: ~/croc_cases/
MOM_input: <case_dir>/run/MOM_input or <case_dir>/Buildconf/momconf/MOM_input
diag_table: <case_dir>/run/diag_table

Install Server
F
license - not found
A
quality
B
maintenance

Maintenance

Maintainers
Response time
Release cycle
Releases (12mo)
Commit activity

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Servers

  • F
    license
    -
    quality
    D
    maintenance
    A streamlined MCP server that provides essential AI-powered tools for interactive development chat and systematic root cause analysis. It supports multiple AI providers to help developers brainstorm technical solutions and perform evidence-based debugging.
    Last updated
  • A
    license
    -
    quality
    D
    maintenance
    An MCP server for intelligent log analysis providing semantic search, error pattern clustering, and smart error detection. It enables users to process, vectorize, and query local logs to efficiently identify issues and generate AI-powered summaries.
    Last updated
    MIT
  • A
    license
    A
    quality
    D
    maintenance
    MCP server for log file analysis. Gives LLMs the ability to efficiently analyze large log files without loading them into context.
    Last updated
    7
    95
    MIT
  • A
    license
    -
    quality
    D
    maintenance
    An MCP server enabling AI agents to record, query, and share structured problem-solving experiences with human review and confidence decay.
    Last updated
    7
    MIT

View all related MCP servers

Related MCP Connectors

  • MCP server for the Fail Modes taxonomy — a knowledge base of AI system failure modes

  • Persistent memory and cross-session learning for AI coding assistants (hosted remote MCP).

  • An MCP server for deep research or task groups

View all MCP Connectors

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/CROCODILE-CESM/MCP_regional_ocean_debugger'

If you have feedback or need assistance with the MCP directory API, please join our Discord server