Missouri Code MCP Server

Missouri Revised Statutes by citation

Keyless. Example: 565.020.

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.

Answers HTTP 200 for a citation that does not exist, so the section number itself is confirmed in the returned text before the page is treated as a statute.

See docs/state-law-probe.md — every state pack confirms a MISS is distinguishable from a HIT before shipping.

Data source

Official state legislature site. Statutes are public record.

Stored copy and data_as_of (fleet #3754)

The Revisor of Statutes' site refuses requests that leave from some data centres (58 "upstream down" against 17 successes from external callers over 14 days). A cache cannot help a first touch, so the Revised Statutes of Missouri are stored, one JSON object per chapter, in the shared statute store (R2, statutes/mo/) that the Michigan, Ohio, West Virginia and Wisconsin packs also use. The gateway hands the pack its R2 binding and the pack reads only the object a call names. A section found there is answered with no upstream request; the response says served_from: "stored-copy" and carries data_as_of (when that chapter was last read from the source) and effective (the section's effective date). A section the copy cannot answer (chapter missing, object unreadable, or listed with no stored text) falls back to the live read. Absence is never remembered.

Nothing is loaded at module scope: the data never enters the gateway bundle. The reader is shared/src/stored-statute.ts, the same one the Montana pack uses.

Refresh

MO_DATA_DIR=<dir> node mcps/missouri-code/scripts/bake-sections.mjs     # all chapters -> <dir>
MO_DATA_DIR=<dir> node mcps/missouri-code/scripts/bake-sections.mjs --only 565
MO_DATA_DIR=<dir> node mcps/missouri-code/scripts/upload-chapters.mjs   # publish to R2 (statutes/mo/), changed files only

The publisher offers no chapter-level text and no bulk file, so the refresh makes one request per chapter for its section list and one per section. Sequential, a delay between requests, an honest user agent, bounded retries, a stop on the first 429/403/451, raw pages kept so an interrupted run resumes. Exit 0 only if every listed section was fetched and parsed and the totals clear the floors. The baked files are a working copy, not committed (.bake/ is gitignored).

Quick Start

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

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

What this endpoint actually serves

tools/list at https://gateway.pipeworx.io/missouri-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/mo_revised_statute \
  -H 'Content-Type: application/json' \
  -d '{"section":"565.020"}'

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

Run it from npm

@pipeworx/mcp-missouri-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/missouri-code/mcp endpoint shown above. It needs network access; there is no offline mode.

{
  "mcpServers": {
    "missouri-code": {
      "command": "npx",
      "args": ["-y", "@pipeworx/mcp-missouri-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 Missouri Code data" })

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

More

• Docs and guides
• pipeworx.io

License

MIT