AI Law Tracker

Measured conclusion: Deep-tested. L2 outcome: tools_ok.

Audited AI-regulation data: laws, bills, news and obligations across US, EU and 62 jurisdictions

Add to your agent

Copy this into your MCP client config:

{
  "mcpServers": {
    "AI Law Tracker": {
      "url": "https://ai-law-tracker.com/mcp",
      "transport": "streamable-http"
    }
  }
}

Measured tools (30)

• search_ai_laws read-only

  Full-text search over the audited AI-regulation dataset (US state + federal, EU, global) by title and summary. Returns matching law records with jurisdiction, status, and the official source URL. Data by AI Law Tracker (CC BY 4.0). Informational only — not legal advice.

  Parameters:

  • q (required) — string — Search text (required), e.g. "facial recognition" or "hiring".
  • sort — string — Sort field (default updated_at).
  • limit — integer — Page size (max 100; free/anon are capped lower).
  • order — string — Sort direction (default desc).
  • scope — string — One of: state, federal, eu, global.
  • offset — integer — Pagination offset.
  • status — string — Case-insensitive substring match on status.
  • in_force — boolean — Filter by the in_force flag.
  • jurisdiction — string — Exact jurisdiction slug (e.g. california, us-federal, eu, canada). See list_jurisdictions.
  • updated_since — string — ISO timestamp; only records updated at/after this.

  Hints: read-only yes · destructive no · idempotent yes · open-world yes

• list_ai_laws read-only

  List AI-regulation records with filters (scope, jurisdiction, status, in_force, updated_since, keyword q), sorting and pagination. Use this to browse laws for a place; use search_ai_laws for free-text search. Data by AI Law Tracker (CC BY 4.0). Informational only — not legal advice.

  Parameters:

  • q — string — Substring search over title + summary.
  • sort — string — Sort field (default updated_at).
  • limit — integer — Page size (max 100; free/anon are capped lower).
  • order — string — Sort direction (default desc).
  • scope — string — One of: state, federal, eu, global.
  • offset — integer — Pagination offset.
  • status — string — Case-insensitive substring match on status.
  • in_force — boolean — Filter by the in_force flag.
  • jurisdiction — string — Exact jurisdiction slug (e.g. california, us-federal, eu, canada). See list_jurisdictions.
  • updated_since — string — ISO timestamp; only records updated at/after this.

  Hints: read-only yes · destructive no · idempotent yes · open-world yes

• get_ai_law read-only

  Fetch a single AI-law record by its stable id (the id field from search_ai_laws / list_ai_laws). Data by AI Law Tracker (CC BY 4.0). Informational only — not legal advice.

  Parameters:

  • id (required) — string — The record uuid (the `id` from a list/search result).

  Hints: read-only yes · destructive no · idempotent yes · open-world yes

• get_law_history read-only

  Full change history for one law record — every observed snapshot (ascending), with what changed and the values at each point. Paid feature (Developer+): anon/free receive a 403 with an upgrade hint, which is returned verbatim. Data by AI Law Tracker (CC BY 4.0). Informational only — not legal advice.

  Parameters:

  • id (required) — string — The record uuid.

  Hints: read-only yes · destructive no · idempotent yes · open-world yes

• get_law_sources read-only

  The primary/secondary source URLs backing one law record — its own official (.gov) link plus the curated jurisdiction sources, each tiered. Basic tiers (anon/free) get PRIMARY sources only; Developer+ get the full set incl. secondary/analysis links (the response carries an upgrade hint verbatim when withheld). Only real, held URLs — no fabrication. Data by AI Law Tracker (CC BY 4.0). Informational only — not legal advice.

  Parameters:

  • id (required) — string — The record uuid (the `id` from a list/search result).

  Hints: read-only yes · destructive no · idempotent yes · open-world yes

• get_law_citations read-only

  The citation projection for one law record: its identifier, title, audited alternate names, and a formatting-convenience suggested citation over public metadata (clearly labelled — never presented as an official cite). Free at every tier. No fabrication. Data by AI Law Tracker (CC BY 4.0). Informational only — not legal advice.

  Parameters:

  • id (required) — string — The record uuid (the `id` from a list/search result).

  Hints: read-only yes · destructive no · idempotent yes · open-world yes

• list_recent_changes read-only

  Unified changelog: time-ordered inserts/updates across the whole dataset. Poll with `since` = the previous response meta.cursor. Paid feature (Developer+); the lookback window is clamped per tier. Data by AI Law Tracker (CC BY 4.0). Informational only — not legal advice.

  Parameters:

  • limit — integer — Page size (max 100; free/anon are capped lower).
  • order — string — Sort direction (default desc).
  • scope — string — One of: state, federal, eu, global.
  • since — string — ISO timestamp cursor — only changes observed after this (pass prior meta.cursor).
  • entity — string — Restrict to one dataset (default: both).
  • offset — integer — Pagination offset.
  • significant — boolean — Drop internal metadata-only updates.
  • jurisdiction — string — Exact jurisdiction slug (e.g. california, us-federal, eu, canada). See list_jurisdictions.

  Hints: read-only yes · destructive no · idempotent yes · open-world yes

• list_law_feed read-only

  A lean, human-scannable stream of the newest significant AI-law changes (inserts + real field changes, no value diffs). Paid feature (Developer+). Data by AI Law Tracker (CC BY 4.0). Informational only — not legal advice.

  Parameters:

  • limit — integer — Page size (max 100; free/anon are capped lower).
  • scope — string — One of: state, federal, eu, global.
  • since — string — ISO timestamp cursor.
  • jurisdiction — string — Exact jurisdiction slug (e.g. california, us-federal, eu, canada). See list_jurisdictions.

  Hints: read-only yes · destructive no · idempotent yes · open-world yes

• list_ai_law_news read-only

  The audited AI-regulation news feed: headline + short excerpt + publisher + source URL (never full article text). Free/anon get a taste (fewer results, newest only, excerpt withheld); Developer+ gets the full archive with excerpts. Data by AI Law Tracker (CC BY 4.0). Informational only — not legal advice.

  Parameters:

  • q — string — Keyword substring over headline + excerpt.
  • to — string — Only headlines published on/before this date (YYYY-MM-DD).
  • from — string — Only headlines published on/after this date (YYYY-MM-DD).
  • limit — integer — Page size (max 100; free/anon are capped lower).
  • scope — string — One of: state, federal, eu, global.
  • since — string — Alias for `from`.
  • offset — integer — Pagination offset.
  • jurisdiction — string — Exact jurisdiction slug (e.g. california, us-federal, eu, canada). See list_jurisdictions.

  Hints: read-only yes · destructive no · idempotent yes · open-world yes

• list_jurisdictions read-only

  All covered jurisdictions (US states, US federal, EU, and countries) with record counts. Use the returned slugs for the `jurisdiction` argument of other tools. Data by AI Law Tracker (CC BY 4.0). Informational only — not legal advice.

  Parameters:

  • scope — string — One of: state, federal, eu, global.

  Hints: read-only yes · destructive no · idempotent yes · open-world yes

• list_us_states read-only

  US state jurisdictions with AI-law record counts. Data by AI Law Tracker (CC BY 4.0). Informational only — not legal advice.

  Hints: read-only yes · destructive no · idempotent yes · open-world yes

• list_countries read-only

  National (global-scope) jurisdictions with AI-law record counts. Data by AI Law Tracker (CC BY 4.0). Informational only — not legal advice.

  Hints: read-only yes · destructive no · idempotent yes · open-world yes

• list_categories read-only

  Dataset facets: the distribution of record_type and scope across all records. Data by AI Law Tracker (CC BY 4.0). Informational only — not legal advice.

  Hints: read-only yes · destructive no · idempotent yes · open-world yes

• list_sectors read-only

  The sector index — valid `sector` slugs (with name, inherent risk and description) for get_ai_obligations, get_ai_penalties and assess_ai_compliance. Data by AI Law Tracker (CC BY 4.0). Informational only — not legal advice.

  Hints: read-only yes · destructive no · idempotent yes · open-world yes

• get_sector_detail read-only

  One sector’s cross-section: the free awareness OVERVIEW (name, inherent risk, enforcement bodies, federal penalty structure) PLUS the derived per-law obligations + penalties for that sector. The overview is open to every tier; the derived obligations/penalties are the salable interpreted layer (Pro+ for obligations) — under-tier callers get a one-item preview + upsell (meta.preview), never a blank wall. Every derived record is grounded in a real law + its primary source (no LLM). Use list_sectors for valid slugs. NOT legal advice.

  Parameters:

  • sector (required) — string — A sector slug (see list_sectors), e.g. healthcare, finance, hr-recruiting.

  Hints: read-only yes · destructive no · idempotent yes · open-world yes

• get_ai_deadlines read-only

  The upcoming AI-law effective / compliance-date calendar, derived deterministically from the curated corpus (no LLM). Each entry carries the verbatim source deadline text + primary-source URL; jurisdictions whose deadline text has no explicit date are reported only as meta.undated (never given an invented date). Free at every tier. This tool returns JSON; a compliance team can also SUBSCRIBE to the same feed as a live RFC 5545 calendar at https://ai-law-tracker.com/api/v1/deadlines?format=ical (webcal). NOT legal advice.

  Parameters:

  • all — boolean — Alias to include past dates as well (equivalent to upcoming=false).
  • scope — string — One of: state, federal, eu, global.
  • upcoming — boolean — Only future dates (default true). Set false to include past effective dates too.
  • jurisdiction — string — Exact jurisdiction slug (e.g. california, us-federal, eu, canada). See list_jurisdictions.

  Hints: read-only yes · destructive no · idempotent yes · open-world yes

• list_bills read-only

  The curated landmark-bill index — the named, name-searchable AI laws (valid slugs for get_bill). Read from the primary-sourced landmark registry. Free at every tier. Data by AI Law Tracker (CC BY 4.0). Informational only — not legal advice.

  Hints: read-only yes · destructive no · idempotent yes · open-world yes

• get_bill read-only

  One curated landmark bill by slug: its core fields, tiered source URLs, citations (identifier + audited aka), and cross-links. Where a matching live record exists, the response binds the change-timeline link (use get_law_history). Served from the primary-sourced registry (no LLM); a missing binding simply omits the history link, never fabricates one. Use list_bills for valid slugs. Data by AI Law Tracker (CC BY 4.0). Informational only — not legal advice.

  Parameters:

  • slug (required) — string — A bill slug (see list_bills).

  Hints: read-only yes · destructive no · idempotent yes · open-world yes

• get_ai_obligations read-only

  The interpreted "what must I do" layer: who must do what, by when, or owe what penalty, for a jurisdiction and/or sector. Every obligation is grounded in a real law record + primary source (no LLM). Provide at least a jurisdiction or a sector. Paid feature (Pro+); lower tiers get a one-item preview with an upgrade hint. NOT legal advice.

  Parameters:

  • use — string — Comma-separated AI uses: hiring, customer, content, analytics, product, other.
  • sector — string — A sector slug (see list_sectors), e.g. healthcare, finance, hr-recruiting.
  • jurisdiction — string — Exact jurisdiction slug (e.g. california, us-federal, eu, canada). See list_jurisdictions.
  • decision_impact — string — What the AI decides about people (escalates applicability).

  Hints: read-only yes · destructive no · idempotent yes · open-world yes

• get_ai_penalties read-only

  The penalty & enforcement dataset for the applicable laws: monetary/other penalty, enforcing body, citation and primary source, plus a sector-level penalty-structure summary. Provide at least a jurisdiction or a sector. Paid feature (Developer+); lower tiers get a one-item preview. NOT legal advice.

  Parameters:

  • sector — string — A sector slug (see list_sectors).
  • jurisdiction — string — Exact jurisdiction slug (e.g. california, us-federal, eu, canada). See list_jurisdictions.

  Hints: read-only yes · destructive no · idempotent yes · open-world yes

• assess_ai_compliance read-only

  The compliance-report engine (deterministic, no LLM — cannot hallucinate) as a tool. Give a business profile; get the applicable AI-law obligations plus a reproducible 1–10 risk score with a named factor breakdown. `state` and `sector` are required. Paid feature (Pro+); lower tiers get a preview (risk band + counts + one sample obligation). NOT legal advice.

  Parameters:

  • state (required) — string — US state slug (e.g. california).
  • sector (required) — string — Sector slug (see list_sectors).
  • size — string — Company size band (e.g. startup, small, medium, enterprise).
  • aiUse — array — How AI is used.
  • ai_policy — string
  • ai_source — string
  • countries — array — EU/global country slugs also operated in/served.
  • bias_audit — string
  • ai_decision_impact — string

  Hints: read-only yes · destructive no · idempotent yes · open-world yes

• generate_compliance_report

  Generate the personalized, source-grounded AI-law COMPLIANCE REPORT for a business profile — the same deterministic engine behind the $79 report product (no LLM in the grounded path, so it cannot invent a statute, deadline, or penalty). Returns the risk assessment (1–10 score + applicable obligations) PLUS a signed download_url for the rendered PDF. `state` and `sector` are required. Paid feature (Pro+); lower tiers get a preview (risk band + counts + one sample obligation) with the PDF/download withheld and an upgrade hint returned verbatim. Every obligation is anchored to a real law + primary source. Informational only — NOT legal advice. Data by AI Law Tracker (CC BY 4.0). Informational only — not legal advice.

  Parameters:

  • state (required) — string — US state slug (e.g. california). `jurisdiction` is accepted as an alias.
  • sector (required) — string — Sector slug (see list_sectors), e.g. healthcare, finance, hr-recruiting.
  • size — string — Company size band (e.g. startup, small, medium, enterprise).
  • aiUse — array — How AI is used.
  • email — string — Delivery email printed on the report footer (optional).
  • company — string — Company name printed on the report (optional).
  • ai_policy — string
  • ai_source — string
  • countries — array — EU/global country slugs also operated in/served.
  • bias_audit — string
  • jurisdiction — string — Alias for `state` (US state slug).
  • ai_decision_impact — string

  Hints: read-only no · destructive no · idempotent yes · open-world yes

• search_enforcement_matters read-only

  Search regulatory enforcement actions and litigation involving AI — FTC, DOJ, SEC, CFPB, EEOC and state attorneys general — at MATTER level: one row per dispute, with forum, agency, status, the statutes invoked and the official source URL. Filter by agency, jurisdiction, matter type/status, AI role or filing date; `q` searches caption, summary and agency. IMPORTANT: every matter here is recorded from a SINGLE official source (`verification: single_source`) and is published with the URL it came from — attribute claims to that source and link it, never state them as established fact. An empty result means we hold no matching matter, NOT that an agency has taken no action: 123 of our 254 monitored sources are currently stale (see list_enforcement_sources). Data by AI Law Tracker (CC BY 4.0). Informational only — not legal advice.

  Parameters:

  • q — string — Substring over caption, summary and agency, e.g. "chatbot" or "RealPage".
  • sort — string
  • tier — string — A = an enforcement DECISION (complaint filed, consent order, settlement, civil penalty, judgment). B = an enforcement-adjacent SIGNAL (opened investigation, sweep, CID, advisory). Use tier=A when the question is how many real enforcement actions exist. Matters recorded before 2026-08-22 carry no tier and are returned by neither value.
  • limit — integer — Page size (max 100; free/anon are capped lower).
  • order — string — Sort direction (default desc).
  • agency — string — Agency code, comma-separated for several: FTC, DOJ, SEC, CFPB, EEOC, "Texas AG"…
  • offset — integer — Pagination offset.
  • ai_role — string — How AI figures in the matter. See list_enforcement_categories.
  • date_to — string — Filed on or before (YYYY-MM-DD).
  • date_from — string — Filed on or after (YYYY-MM-DD). The date is the SOURCE's own filing date, never our scrape date — each row's date_source names the field it was lifted from. A minority of matters are still undated because the source stated none, and a date filter excludes those.
  • forum_type — string — See list_enforcement_categories.
  • matter_type — string — enforcement_action | civil_litigation | guidance_document | investigation | inquiry_6b. Comma-separated.
  • jurisdiction — string — Jurisdiction slug, comma-separated.
  • matter_status — string — See list_enforcement_categories for the vocabulary.
  • jurisdiction_level — string — federal, state and/or multistate, comma-separated.

  Hints: read-only yes · destructive no · idempotent yes · open-world yes

• get_enforcement_matter read-only

  Fetch one enforcement matter by its matter_uid (from search_enforcement_matters) with its full chain: the event timeline, the parties, the relief imposed and its dollar amount, the statutes cited, and the source documents each claim traces to. matter_uid is an OPAQUE KEY, not a description — read `caption` for the matter name; some uids are demonstrably mislabelled. Read `verification` (currently single_source on every matter), `events[].is_date_estimated` (the source gave a year, not a day) and `laws[].link_status` before repeating anything. Named private individuals are withheld from `parties` by policy. If `chains_sampled` is true you are seeing 2 rows of each chain and `chain_totals` gives the real sizes — say so rather than implying the matter is that small. Data by AI Law Tracker (CC BY 4.0). Informational only — not legal advice.

  Parameters:

  • matter_uid (required) — string — The `matter_uid` from a search result.

  Hints: read-only yes · destructive no · idempotent yes · open-world yes

• list_enforcement_sources read-only

  The 254 official sources behind the enforcement registry — agency newsrooms, AG press feeds, court dockets — with the last successful read and whether each is currently stale or blocked. Use it BEFORE concluding that an agency has done nothing: a stale or disabled source is a gap in our monitoring, not evidence of inaction, and only about half of the registry is currently answering. Free at every tier, no key needed. Data by AI Law Tracker (CC BY 4.0). Informational only — not legal advice.

  Parameters:

  • is_stale — boolean — true = sources we have not managed to read inside their own silence budget.
  • is_enabled — boolean
  • jurisdiction_level — string

  Hints: read-only yes · destructive no · idempotent yes · open-world yes

• list_enforcement_categories read-only

  The thirteen controlled vocabularies the enforcement filters accept — matter_type, matter_status, forum_type, party_role, party_kind, relief_type, event_type, ai_role, law_relation, verification, jurisdiction_level, pii_class and redaction_policy. Call this to get valid values for search_enforcement_matters instead of guessing them. Free at every tier, no key needed. Data by AI Law Tracker (CC BY 4.0). Informational only — not legal advice.

  Parameters:

  • kind — string — Return just one vocabulary, e.g. matter_type.

  Hints: read-only yes · destructive no · idempotent yes · open-world yes

• get_enforcement_coverage read-only

  How big the enforcement registry actually is: matters held, matters publishable, how many are withheld as duplicates or pending translation, breakdowns by agency, matter type and jurisdiction, and the de-duplicated monetary relief total. Use it to state coverage honestly — the number of matters a search can return is smaller than the number held, and the registry is a few dozen matters, not a comprehensive index of US AI enforcement. Free at every tier, no key needed. Data by AI Law Tracker (CC BY 4.0). Informational only — not legal advice.

  Hints: read-only yes · destructive no · idempotent yes · open-world yes

• get_api_status read-only

  Liveness + backend status of the AI Law Tracker data API.

  Hints: read-only yes · destructive no · idempotent yes · open-world yes

• start_checkout

  Create a hosted checkout link to upgrade to a paid API plan (starter $49, pro $99, business $299 / month). Returns a checkout_url the user opens in a browser; payment happens on our own checkout, and on success the user's API key is upgraded automatically. Does not modify any data.

  Parameters:

  • tier (required) — string — Plan to buy. AI Law Tracker: starter | pro | business. US Law Platform: us_entry (sold as "Starter") | us_solo | us_starter (sold as "Pro").
  • email — string — Optional — pre-fills the checkout / links the subscription to this email.

  Hints: read-only no · destructive no · idempotent no · open-world yes

• create_free_key

  Mint a FREE-tier API key and email it to the given address (the key is also returned once here). Paste that key into the connector's x-api-key header to unlock full fields, filters and higher limits. One active free key per email.

  Parameters:

  • email (required) — string — Where to deliver the key.

  Hints: read-only no · destructive no · idempotent no · open-world yes

Publisher website

Measured by MCPYP probing. Untested fields are omitted, never estimated. Listing is always free; MCPYP never proxies calls or stores user tokens.