Montana Code MCP Server

Montana Code Annotated

Montana state statutes by citation, plus topic search across the whole code. Keyless.

Part of Pipeworx — an MCP gateway connecting AI agents to 1856+ live data sources. This is an independent, unofficial integration — not affiliated with, endorsed by, or published by the upstream provider.

Tools

• mt_code_section -- the full text of one section by citation, e.g. 1-1-307 (postponement of a day appointed for an action when it falls on a holiday or Saturday) or 45-5-102 (deliberate homicide).
• mt_code_search -- full-text search by topic or keyword, e.g. "computing time period days holiday". Returns ranked sections with their citation, heading and an opening excerpt; call mt_code_section with a result for the full text. A query with no hits returns found: false, never an empty list.

Coverage

All 54 titles of the Montana Code Annotated (2025 edition), about 44,000 sections. That includes Title 25, chapter 20, the Montana Rules of Civil Procedure (Rule 6, computing and extending time, is MCA 25-20-206), and the other court rule sets published in Title 25.

Search is a full-text match, not semantic search: it ranks sections containing all the query's words, and falls back to any-word matching when no section contains them all.

How search works

mt_code_search uses the shared statute search store: an FTS5 index in the SEARCH_SHARD Durable Object (shard name mt-statutes) and the section text in the shared datasets R2 bucket (statutes/mt/<title>.json, one bundle per title, plus _index.json). No new Cloudflare binding. The index is loaded by scripts/ingest-montana-statutes.mjs; re-run it after the Legislature publishes a new edition. Every response carries data_as_of.

Data source

Montana Legislature, Montana Code Annotated. Montana statutes are public record. Citation lookups call the Legislature live on each request; topic search reads a pre-fetched copy of the current code.

Stored copy and data_as_of (fleet #3754)

mt_code_section answers from the Montana Code Annotated already held in the shared statute store (R2, statutes/mt/, one object per title, loaded by scripts/ingest-montana-statutes.mjs for topic search). The legislature's archive site refuses requests that leave from some data centres (70 "upstream down" against 171 successes from external callers over 14 days). A section the stored title lists is answered with no upstream request: served_from: "stored-copy", data_as_of (when the title was last read from the source) and the section's history line. A title that cannot be read, or a section it does not list, falls back to the live read. Refreshing the store refreshes both search and lookup.

Quick Start

Add to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):

{
  "mcpServers": {
    "montana-code": {
      "url": "https://gateway.pipeworx.io/montana-code/mcp"
    }
  }
}

What this endpoint actually serves

tools/list at https://gateway.pipeworx.io/montana-code/mcp returns the tools in the table above plus the shared Pipeworx meta-tools — ask_pipeworx, discover_tools, search_within, remember/recall and the rest of the gateway-wide set. So the tool count you see is larger than this table: a single-pack endpoint currently lists roughly 30 shared tools alongside the pack's own. The connection's initialize response states its exact scope, and is the authoritative answer for a given day.

This is deliberate, not multiplexing by accident. The meta-tools are what let a scoped connection answer a question this pack does not cover — via ask_pipeworx, which routes across the whole catalog — without you adding a second MCP server. There is currently no way to mount a pack endpoint without them; if the extra schemas cost you more context than the routing is worth, connect to the full gateway once rather than to several pack endpoints.

Or connect to the full Pipeworx gateway to get every pack's tools listed directly, instead of just this one's:

{
  "mcpServers": {
    "pipeworx": {
      "url": "https://gateway.pipeworx.io/mcp"
    }
  }
}

Both URLs reach the same gateway and the same 1856+ data sources. The only difference is which pack's tools are listed directly; ask_pipeworx reaches all of them from either one.

No MCP client? Call it over HTTP

curl -X POST https://gateway.pipeworx.io/v1/tools/mt_code_section \
  -H 'Content-Type: application/json' \
  -d '{"section":"45-5-102"}'

No account needed for the first calls. Inspect any tool: GET https://gateway.pipeworx.io/v1/tools/mt_code_section. Find one: POST https://gateway.pipeworx.io/v1/tools/search_packs with {"query":"..."}.

Run it from npm

@pipeworx/mcp-montana-code is a local stdio bridge to the Pipeworx gateway: your MCP client starts it with npx, and it forwards every call to the same https://gateway.pipeworx.io/montana-code/mcp endpoint shown above. It needs network access; there is no offline mode.

{
  "mcpServers": {
    "montana-code": {
      "command": "npx",
      "args": ["-y", "@pipeworx/mcp-montana-code"]
    }
  }
}

Without a key it calls anonymously, capped at 50 calls a day. A free account raises that to 200 a day: get a key at https://pipeworx.io/signup and add "env": { "PIPEWORX_API_KEY": "<your key>" } to the server entry. The key is sent as a Bearer token, the same way a hosted connection sends it, so calls are metered and billed exactly as they are there.

It lists only this pack's tools by default. Set PIPEWORX_META_TOOLS=1 to also list ask_pipeworx and the other gateway-wide tools.

Behind an HTTPS proxy: Node's built-in fetch does not read HTTPS_PROXY by default. Newer Node releases honour it when NODE_USE_ENV_PROXY=1 is set; check your Node version's documentation.

Using with ask_pipeworx

Instead of calling tools directly, you can ask questions in plain English — this works on the pack endpoint above as well as on the full gateway:

ask_pipeworx({ question: "your question about Montana Code data" })

The gateway picks the right tool and fills the arguments automatically.

More

• Docs and guides
• pipeworx.io

License

MIT