Skip to main content
Glama
deenesjakoruzh
CAPTW

imo-rules-mcp

by CAPTW
OverviewSchemaSourceRelated ServersScoreDiscussionsAdmin
TypeScript
Local

⚓ imo-rules-mcp

Bring your corpus. Keep the rules local.

A read-only MCP server for offline semantic search, keyword search, document retrieval, citation traversal, and structured browsing across a locally supplied IMO regulatory corpus.

MCP Runtime Mode Corpus

Tools · Set up a corpus · Rights boundary · Full technical reference

The server is open. The corpus is yours to license, store, and protect.

imo-rules-mcp exposes a local corpus of maritime instruments to MCP-compatible clients without crawling the web or redistributing regulation text.

MCP tools

Tool

Purpose

imo_semantic_search

Meaning-based retrieval with ranked regulations, breadcrumbs, snippets, and document keys.

imo_keyword_search

Literal title or body search.

imo_get_document

Retrieve one normalized regulation with navigation context and citations.

imo_list_instruments / imo_browse

Navigate instruments, chapters, and regulations.

imo_get_citations

Follow outbound cross-references.

imo_stats

Inspect corpus coverage and index state.

Related MCP server: Markdown RAG MCP

Architecture

flowchart LR
    A["Licensed local corpus"] --> B["SQLite documents"]
    A --> C["TOC tree"]
    A --> D["Local embedding index"]
    B --> E["MCP server"]
    C --> E
    D --> E
    E --> F["Offline MCP client"]

Quickstart

Install:

npm install

Import a compatible exported corpus:

node scripts/import-corpus.mjs /path/to/KRcrawl

Start the stdio server:

npm start

A repository-scoped .mcp.json is included for hosts that support project-local MCP configuration.

Corpus and rights boundary

This repository contains server code only. It does not ship SOLAS, MARPOL, STCW, IMO Codes, or any other regulation corpus.

  • Supply only material you are licensed to use.

  • Keep corpus/ outside version control.

  • Do not publish or redistribute proprietary regulation text.

  • If a convenience bundle includes corpus data, keep that repository private and apply the applicable rights controls.

  • Server-code licensing does not grant rights to the corpus.

Runtime contract

  • Read-only tools only.

  • No crawler and no required network path.

  • Semantic search loads its local model/index on demand.

  • Other tools operate directly on the local corpus structures.

  • Corpus completeness, currency, interpretation, and legal authority remain external responsibilities.

Full technical reference

The original detailed README — including the expected corpus layout, environment variables, client configuration, and tool-by-tool behavior — is preserved unchanged at:

README.technical.2026-08-25.md

License

Server code is MIT. Corpus data is excluded from that grant.

This server cannot be installed

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Maintenance

ActivityMaintained
ResponsivenessNo issues

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

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

Related MCP Connectors

Related MCP Servers

  • ragi

    SusuTawar
    A
    license
    A
    quality
    D
    maintenance
    Local-first RAG indexing and semantic search MCP server. Enables document retrieval and context-aware queries using local embedding models.
    3
    6
    MIT

  • Markdown RAG MCP

    mohllal
    A
    license
    Not graded
    quality
    D
    maintenance
    Provides semantic search over markdown documentation using RAG, allowing natural language queries and integration with MCP clients.
    1
    MIT

  • RAG MCP Server

    alejandro-ao
    F
    license
    Not graded
    quality
    D
    maintenance
    Provides tools for ingesting documents into a local vector database and retrieving relevant information via semantic search, enabling retrieval-augmented generation for MCP clients.
    6
    -

  • DocAgent-MCP

    wuliuke
    F
    license
    Not graded
    quality
    C
    maintenance
    Enables local document question-answering and retrieval via MCP, supporting multi-turn conversation, intent recognition, and tools for document search, Q&A, and summarization.
    5
    -