io.github.mark-brannan/colregs-mcp

Official registry Other

Not for navigation. Pre-release preview: COLREGS Part C night lights, international text only.

Install

Add this to your client's MCP configuration (Claude Desktop: claude_desktop_config.json; Cursor: .cursor/mcp.json; VS Code and others use the same "mcpServers" shape).

NPM package colregs-mcp
Claude Code
claude mcp add colregs-mcp -- npx -y colregs-mcp@0.0.6
JSON configuration (Claude Desktop, Cursor, VS Code)
{
    "mcpServers": {
        "colregs-mcp": {
            "command": "npx",
            "args": [
                "-y",
                "colregs-mcp@0.0.6"
            ]
        }
    }
}

Documentation

From the project's README on GitHub, refreshed weekly. Links open on GitHub.

Contents
  1. colregs-mcp
  2. Try it
  3. Tools
  4. Example
  5. Response shape
  6. Dependencies
  7. Privacy Policy
  8. Releasing
  9. Licence

colregs-mcp

[!WARNING] Not for navigation. This is a preview (0.0.x) built on pre-release rule data. Do not use its output to decide what to do on the water. The tool surface will change without notice.

An MCP server that answers questions under the COLREGS. Every answer carries its paragraph cites and the verbatim rule text those cites resolve to, so a language model cannot quietly simplify it. The rules are evaluated by colregs-engine; this package only decides how the answer is written down.

Try it

Claude Code:

claude mcp add colregs -- npx -y colregs-mcp

Claude connector directory: in Claude, open Settings → Connectors, search for COLREGS and click Connect. No configuration is needed.

Any other MCP client: command npx, arguments -y colregs-mcp, no environment.

From a clone:

git clone https://github.com/mark-brannan/colregs-mcp && cd colregs-mcp && npm install && npm run build

then command node, argument /absolute/path/to/colregs-mcp/dist/cli.js.

Tools

toolinputreturns
evaluatecircumstancesone evaluation: appraisal, signals, indicated, compliance
rule_textcitethe verbatim text of a COLREGS paragraph
lightidone light's definition: colour, character, arc, placement
evaluate

circumstances is the whole picture one vessel is in: self (her own facts), others (each other vessel, with what is known or observed of her) and conditions (visibility, environment). One call evaluates the picture; the response carries four readings of it.

  • signals: every complete, lawful set of lights self may show. Each light carries its modality (shall, may, shall-if-practicable) and the paragraph that prescribes it.
  • appraisal: what the Rules require of self on her own, and then against each other vessel: the kind of encounter, whether risk of collision is asserted, and each vessel's role (stand-on, give-way, shall-not-impede).
  • indicated: for each other vessel, what her observed lights, shapes and sounds indicate she could be.
  • compliance: over a track of circumstances sampled through time, one verdict per vessel per obligation that attached: kept, breached or pending.

Every id travels with its paragraph cite, and cited_paragraphs holds the verbatim text of every paragraph the response cites. The input vocabulary is generated from the colregs data package at startup. A key or value outside it is an error, never an empty answer.

rule_text

Takes a paragraph path such as 25(b) or 26(c)(i), a bare rule number such as 25 for every paragraph of that rule, or a range such as 24(a)(ii)-(iv). Returns the International text as transcribed from the USCG amalgamated Navigation Rules, with its source and retrieval date.

light

Takes a light id as it appears in a response, such as light:sidelights or light:all_round. Returns the Rule 21 definition: colour, character, arc in degrees and placement.

Example

A 12 m sloop under way, alone.

{
  "circumstances": {
    "self": {
      "fact:propulsion": "propulsion:sail",
      "fact:activity": "activity:none",
      "fact:position": "position:underway",
      "fact:length_m": 11.6
    }
  }
}

Trimmed response:

{
  "colregs": { "version": "0.3.4" },
  "signals": {
    "applied": [
      { "id": "rule:25a", "cite": "25(a)", "modality": "modality:shall" },
      { "id": "rule:25b", "cite": "25(b)", "modality": "modality:may" },
      { "id": "rule:25c", "cite": "25(c)", "modality": "modality:may" }
    ],
    "lawful_displays": {
      "count": 3,
      "relation": "any_one_of",
      "options": [
        {
          "option": 1,
          "of": 3,
          "lights": [
            {
              "light": "light:sidelights",
              "modality": "modality:shall",
              "prescribed_by": { "id": "rule:25a", "cite": "25(a)" }
            },
            {
              "light": "light:sternlight",
              "modality": "modality:shall",
              "prescribed_by": { "id": "rule:25a", "cite": "25(a)" }
            }
          ]
        },
        { "option": 2, "of": 3, "...": "..." },
        { "option": 3, "of": 3, "...": "..." }
      ]
    },
    "modality_key": { "modality:shall": "mandatory", "modality:may": "permitted alternative" },
    "cited_paragraphs": {
      "25(a)": "A sailing vessel underway shall exhibit: (i) sidelights; (ii) a sternlight.",
      "25(b)": "…",
      "25(c)": "…"
    }
  },
  "appraisal": { "self": { "...": "..." }, "others": [] },
  "indicated": []
}

The sloop has three lawful displays, because the Rules give her the choice and nothing in the input settles it.

docs/demo.md puts the same question to the same model with and without this server and shows both answers as captured.

Response shape

Three properties hold for every response:

  1. Cited, verbatim. Every entry id travels with its paragraph cite, and cited_paragraphs holds the text of every paragraph cited. The only sentences in a response are the Rules' own.
  2. Modality per light. shall, may and shall-if-practicable are kept on each light, not summarised per display. modality_key is a one-line glossary of the modalities the response uses.
  3. Plural by construction. lawful_displays opens with count and relation before any lights appear, and each option numbers itself n of count. There is no top-level lights field to mistake for the answer.

A vessel that lawfully shows nothing gets one empty display, not an error. An error is reserved for input outside the vocabulary.

Every response carries colregs.version. The server refuses to start if its own copy of colregs and the engine's are different releases.

Dependencies

colregs-engine and colregs are installed from GitHub main, not from npm releases; the lockfile pins the commit. Both must resolve the same release.

Privacy Policy

The server collects nothing. It runs as a local stdio process, answers from the colregs data package installed beside it, and makes no network request of its own. There is no telemetry, no logging of what it is asked, and no account. The only network transaction is the install itself, which is npm's.

Releasing

Automatic from the release tag: npm, the MCP registry, and a .mcpb bundle on the GitHub Release. The remaining by-hand steps are in docs/releasing.md.

Licence

AGPL-3.0-only. The fitness-for-navigation disclaimer in colregs carries over.

Frequently asked questions

What is io.github.mark-brannan/colregs-mcp?

Not for navigation. Pre-release preview: COLREGS Part C night lights, international text only.

How do I install io.github.mark-brannan/colregs-mcp?

It runs on your machine. In Claude Code: claude mcp add colregs-mcp -- npx -y colregs-mcp@0.0.6. For other clients, paste the JSON configuration from this page into their MCP settings.

Does io.github.mark-brannan/colregs-mcp need an API key?

Its registry entry lists no required key or secret. Some features may still need an account with the service it connects to.

Is io.github.mark-brannan/colregs-mcp open source?

Yes. Its code is on GitHub under the AGPL-3.0 license.

Who maintains io.github.mark-brannan/colregs-mcp?

It is published by mark-brannan. AI.tn lists it but does not maintain or endorse it.

From the official MCP Registry. Listing is not an endorsement: review a server's code and permissions before giving it access to your data.