Alabama Code

@pipeworx/alabama-code

Code of Alabama 1975 (Alabama state statutes) — full section text by citation, real full-text topic search, and amendment history.

Part of Pipeworx — an MCP gateway connecting AI agents to 1861+ live data sources. This is an independent, unofficial integration — not affiliated with, endorsed by, or published by the upstream provider.

Tools

• al_statute(citation) — full current text of one Code of Alabama section (e.g. "13A-6-2", murder), with the section title, the Legislature's own amendment-history citation list (amendment_history), repealed/transferred disposition, previous/next-section neighbors, and — when an Act has already been enacted but is not yet in force — a forward-looking pending_version carrying its future effective date and text.
• al_search(query, limit?) — REAL full-text search over actual section body text (e.g. "landlord", "concealed pistol permit"), run live against the Alabama Legislature's own search index. Unlike several sibling state-code packs, this is not limited to captions/catchlines.

Auth

Keyless.

Data sources

• https://alison.legislature.state.al.us/graphql — the Alabama Legislature's own public GraphQL API, confirmed keyless and reachable from Cloudflare Worker egress (edge-probed, not just laptop-tested). Both tools call it live, per request; nothing is baked.
• query codeOfAlabamaSection($displayId: String!) — one section's current (and, when present, pending-future) text, title, and amendment-history string, plus codeOfAlabamaNeighbors for previous/next citation.
• query searchCodeOfAlabama($query: String!, $limit: Int, $offset: Int) — full-text search (fullTextQuery argument) over section body content, not just titles; returns a count of total matches independent of limit.

Trap avoided: there are TWO graphql-shaped hosts, only one of which serves statute data. cms.alison.legislature.state.al.us also answers POST /graphql (it serves the site's marketing/CMS content — page copy, the logo asset, etc.) and returns a *plausible* 400 (Cannot query field "codesOfAlabama" on type "Query") for every statute query, because it's a different schema on a different service, not an error about this pack's query shape. The real statute API lives on the main site's own domain, alison.legislature.state.al.us/graphql (found in a plain inline URL reference inside the page's own HTML — not something a build-config guess would find — and confirmed by pulling the query text for codeOfAlabamaSection/searchCodeOfAlabama straight out of the Next.js chunk bundle that defines them).

Trap avoided: the GraphQL endpoint answers HTTP 200 on a query-level error. A malformed or schema-mismatched query comes back as a 200 with a body-level errors array — not a 4xx. al_statute/al_search read the body and check for errors explicitly and throw a LOUD error naming the GraphQL message; neither tool ever reshapes that into found: false.

Capabilities — three available, one is forward-looking instead of backward

• Citation lookup — al_statute.
• Topic/full-text search — al_search, over real section body text (verified live: "landlord" matches 88 sections, including ones whose title never says "landlord").
• Amendments/enactment history — AVAILABLE. Every in-force section's history field from the API is the Legislature's own Acts citation list (e.g. "(Acts 1977, No. 607, p. 812, §2005; Act 2016-29, §2.)"), returned as amendment_history with §/& entities decoded.
• Historical version (the text as it read before an amendment) — NOT AVAILABLE going backward. ALISON publishes the CURRENT in-force text only: no per-year archive, no "view as of" date picker, and codeOfAlabamaSection never returns more than one *past* row for a citation (checked live on several amended sections). It DOES sometimes return a *future* row — when the Legislature has already enacted an amendment that is not yet in force, the same query returns a second version whose effectiveDate is the date it takes over. al_statute surfaces that as pending_version (verified live on 26-2-2, effective 2027-01-01 under Act 2026-488) and says explicitly that this is forward-looking, not a historical archive.

Source and shape — read this before touching the parser

alison.legislature.state.al.us ("ALISON") is a Next.js single-page app — the August state-law survey (docs/state-law-probe.md) correctly flagged the HTML shell as "client-rendered or bot-walled" (it carries no statute text at all), and stopped one layer too early, the same way the survey was wrong on South Dakota and Utah. The SPA is fed by a keyless, public GraphQL API (not REST, unlike South Dakota/North Dakota) — found by downloading the site's own /_next/static/chunks/*.js bundles and grepping for query codeOfAlabamaSection, which is where the exact query text used in this pack's SECTION_QUERY/SEARCH_QUERY constants comes from verbatim.

The citation shape is title-chapter-section (13A-6-2); titles can carry a trailing letter (13A, 26-2A). al_statute's regex accepts 2 or 3 dash-separated segments plus an optional decimal suffix, matching the sibling packs' validation shape.

No baked index exists for this pack, unlike mcps/south-dakota-code or mcps/north-dakota-code: ALISON's own searchCodeOfAlabama query is a real full-text search over section body content, so there is nothing to bake — building an offline index would only add staleness (the Code gains pending future-effective rows on its own legislative schedule) with no accuracy benefit over the live call.

Known gaps

• No per-year historical archive — see "Historical version" above.
• al_search is full-text over body content but still keyword-shaped (not a phrase/boolean query language) — it is the Legislature's own search backend, not Pipeworx's.

Quick Start

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

{

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

What this endpoint actually serves

tools/list at https://gateway.pipeworx.io/alabama-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 1861+ 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/al_statute \

-H 'Content-Type: application/json' \ -d '{"citation":"13A-6-2"}'

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

Run it from npm

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

{

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

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

More

• Docs and guides
• pipeworx.io

License

MIT