Oravan

Oravan

Your line to Congress · Tu línea con el Congreso

Oravan is free, nonpartisan civic infrastructure: find your federal representatives, understand active bills in plain language (English and Spanish), get a 30-second call script, and make the call — in under 5 minutes, with no account.

The name is the Oravan: the platform in the Roman Forum where citizens stood to address the public and the powerful — the original place a voice met power. Latin roots are the shared ancestry of English and Spanish alike.

MCP server

This repository also implements a remote MCP (Model Context Protocol) server — the same decoded corpus and lookups, exposed for AI assistants and agents:

• Endpoint (Streamable HTTP): https://oravan.org/api/mcp/mcp — keyless, read-only, rate-limited; no account or credentials required
• Local/stdio: npm ci then npx tsx scripts/mcp-stdio.mjs — the same 5 tools over stdio, zero env vars/secrets required
• Implementation: app/api/mcp/[transport]/route.ts (built on mcp-handler + @modelcontextprotocol/sdk), tool definitions shared with the stdio entry via lib/core/mcp-tools.ts, pure data layer in lib/core/
• Five tools: lookup_representatives, get_bill, search_bills, whats_moving, get_representative — every response carries a citation envelope (source, as-of freshness, AI-content label, license) in English or Spanish
• Official MCP Registry: published as org.oravan/mcp (server.json at the repo root, schema-validated in CI by scripts/check-server-json.mjs)
• Docs: oravan.org/mcp (tool reference, client config, privacy posture) · docs/mcp-server-readme.md

Design principles

1. Zero accounts. ZIP code, interests, and call history live in localStorage on the visitor's device. No server-side user data exists — nothing to breach, leak, or subpoena. This is the core privacy posture for at-risk users, not a missing feature.
2. Static-first. Bills, legislators, district offices, and ZIP→district mappings are static JSON in data/, baked into ~1,000 statically generated pages. Fast, nearly free to host, resilient under load. The only dynamic endpoints are /api/script (AI script generation, cached per bill+stance+language, IP rate-limited), /api/reps (pure lookup), /api/district (stateless split-ZIP address refinement: proxies the Census geocoder so the visitor's IP never reaches census.gov; the address is never stored or logged), and /api/feedback (beta feedback relayed to a private GitHub issue — only what the visitor volunteered, no identifiers).
3. Bilingual as a first-class feature. Full EN/ES UI via next-intl; scripts are generated in the user's language.
4. Truth first; the call is the natural next step. Oravan leads as an unbiased, plain-words account of what Congress is actually doing — understanding is the front door, never an assignment. The call apparatus stays the differentiator (voicemail legitimized, offices tally it identically; after-hours calling encouraged; district offices listed alongside DC; outcomes — spoke / voicemail / couldn't reach — logged locally on the device), and every decoded answer keeps a completed call script within two interactions. Demoted, never buried. (Amended 2026-07-26; previously "The call moment is the product." Enforced by the three named invariants in tests/funnel.spec.ts — see DESIGN.md structural constraint 2.)
5. Honest about AI. Every generated summary and script is labeled at first contact, and nothing publishes unless the automated gates pass: both languages present, the official record attached, and a schema check on every decode — a decode that comes back missing a required field is discarded rather than stored half-written, and scripts/verify-sync.mjs re-checks the whole corpus and fails the nightly run before it is allowed to commit anything. (Amended 2026-08-12: one check left that file and now runs AFTER the commit — the cursor-age ceiling in scripts/check-cursor-age.mjs. It is a progress signal, not a corpus one: a stalled cursor means we are behind, and failing it before the commit made a stalled night throw away a night of already-paid decodes. Every corpus check named here is unchanged and still runs before anything is committed. See CLAUDE.md's amendment of the same date.) Nonpartisan wording is a drafting instruction to the model on bill decodes and an enforced vocabulary lint on Big Questions (lib/moments-gate.mjs) — the two are not the same guarantee, and the copy never blurs them. The nightly decode path has no human step and the product never claims one; the one review it does claim is real: a caller reads, and can edit, the call script before dialing. (Amended 2026-08-06; previously "labeled, editable, and reviewed by the human before any call." See CLAUDE.md's 2026-07-25 amendment, which this line should have followed and did not.)
6. Accessible by default. Semantic landmarks, skip link, visible focus, prefers-reduced-motion, 44px+ touch targets, AA contrast.

Data sources

File	Source	Refresh
data/bills.json + data/bills-es.json	Decoded bill corpus (Congress.gov bills + AI plain-language summaries, English and Spanish)	Nightly sync (scripts/sync-bills.mjs via sync-bills.yml): statuses refresh freely; new bills are decode-before-publish, entering the corpus only once their EN and ES summaries exist
data/legislators.json	unitedstates/congress-legislators (public domain) + district offices	scripts/process-data.py
data/zip-districts.json	OpenSourceActivismTech/us_zipcodes_congress	same
data/vacancies.json	Derived, not fetched: scripts/vacancy_diff.py diffs seat sets against the currently-committed data every run, so a departed member with no successor surfaces as an explicit vacancy (reps page, /api/reps, MCP lookup_representatives) instead of silently disappearing or being backfilled from a stale term record	scripts/process-data.py (same run as legislators.json)
data/redistricting-watch.json	Human-authored (status/note) for the 10 states with contested-or-recent 2025–26 mid-decade map changes; rdh_lastmod is a tripwire baseline against the Redistricting Data Hub's own state-page sitemap — see docs/solutions/two-clock-district-boundaries.md	scripts/check-redistricting-watch.mjs, weekly via refresh-legislators.yml; on change it comments on ONE standing, pinned redistricting-watch issue whose body is a rewritten 10-state status board (it used to open one issue per changed state — ten accumulated in six weeks, eight of them from a single RDH site-wide republish), never auto-updates status/note
data/nominations.json	Civilian Senate nominations (PNs) of the 119th Congress — Congress.gov's own citation, description sentence, and latest action, plus a status derived from that action text by lib/nomination-status.mjs's rule table. No AI touches this file — Oravan does not decode or rewrite a nomination, because Congress.gov's description is already one plain English sentence, so /nominations/[slug] renders the Senate's own record verbatim and says so on the page. The one piece of AI is the call script, labeled where it is generated. A nomination can be a Big Question's vehicle; the card, the page, and the call are live. It stays English on /es like the coverage titles below (see Known v1 caveats). Military promotion lists are excluded (no description, no nameable nominee). No MCP tool exposes nominations yet.	scripts/sync-nominations.mjs (nightly, one free request; gated by scripts/check-nominations.mjs)
data/coverage.json	Real news articles about top-band bills via TheNewsAPI, AI-relevance-filtered (Haiku)	scripts/sync-coverage.mjs (nightly, gated on NEWS_API_KEY)
data/media-bias.json	Outlet political-lean ratings by AllSides, used under CC BY-NC with attribution	Vendored snapshot

Portraits are served from the public-domain unitedstates/images project.

Solved pipeline incidents (root cause + the CI gates that prevent recurrence) are documented in docs/solutions/.

The "Read" section (outlet-bias coverage)

Each top bill's page shows real third-party articles about it, labeled by the outlet's political lean (Left / Center / Right) — reusing AllSides' publication-level ratings, never a Oravan-invented one. Oravan takes no stance and authors no partisan text: AI is used only behind the scenes — generating each bill's news-search terms (press-style names and a subject query) and a cheap relevance gate (is this article about this bill?) — and authors nothing displayed. The ingestion runs nightly in CI and bakes results to JSON, so the site still makes zero runtime third-party calls. Without NEWS_API_KEY the sync is a no-op and the section renders nothing; a small hand-built real sample (data/coverage.json) keeps it demoable. Lean is shown by text label + position only — never party colors (a hard rule; see DESIGN.md).

Develop

npm install
echo "ANTHROPIC_API_KEY=sk-ant-..." > .env.local   # script generation + decode/relevance
echo "NEWS_API_KEY=..." >> .env.local               # optional; enables the "Read" coverage sync
npm run dev

npm run build statically generates every bill page in both locales.

Known v1 caveats

• ZIP→district mapping is ZCTA-based; a split ZIP shows all candidate districts by default (senators are unaffected). Entering a street address — optional, sent once by POST, never stored or logged — narrows it to the actual district via a server-proxied Census-geocoder lookup; the all-candidates view remains the graceful fallback whenever the geocoder can't help. The geocoder request pins the "119th Congressional Districts" layer, which needs a bump when the Census rolls the vintage to the 120th.
• Script cache and rate limits are in-memory per serverless instance — fine at demo scale, should move to a shared store before heavy traffic.
• New bills can lag behind Congress.gov: the nightly sync decodes at most MAX_NEW_DECODES new bills per run (cost ceiling), so after a missed window the corpus catches up over several nights (decode-before-publish; the backlog drains oldest-first).
• "Read" coverage exists only for top-band bills (the long tail shows nothing); the ES locale shows the same English articles with localized chrome; outlets absent from data/media-bias.json appear without a lean chip.

License

• Code: GNU AGPL-3.0. You may use, modify, and run this code — including as a network service — provided modified versions you operate or distribute remain open under the same license. Embedding Oravan's hosted widgets on your site via the loader/script tag does not subject your site to the AGPL; that's use of our service, not distribution of this code.
• Not licensed: the Oravan name, logo, and brand assets (assets/brand/, app icons). All rights reserved — forks must use their own identity.
• Content: underlying legislative data is U.S. government work (public domain). AI-generated decodes and summaries are licensed CC BY 4.0, exactly as declared in the MCP citation envelope and on the citations page.