AI Law Tracker

Search AI enforcement matters

search_enforcement_matters

Read-onlyIdempotent

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.

Input Schema

TableJSON Schema

Name	Required	Description
`q`	No	Substring over caption, summary and agency, e.g. "chatbot" or "RealPage".
`sort`	No
`tier`	No	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`	No	Page size (max 100; free/anon are capped lower).
`order`	No	Sort direction (default desc).
`agency`	No	Agency code, comma-separated for several: FTC, DOJ, SEC, CFPB, EEOC, "Texas AG"…
`offset`	No	Pagination offset.
`ai_role`	No	How AI figures in the matter. See list_enforcement_categories.
`date_to`	No	Filed on or before (YYYY-MM-DD).
`date_from`	No	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`	No	See list_enforcement_categories.
`matter_type`	No	enforcement_action \| civil_litigation \| guidance_document \| investigation \| inquiry_6b. Comma-separated.
`jurisdiction`	No	Jurisdiction slug, comma-separated.
`matter_status`	No	See list_enforcement_categories for the vocabulary.
`jurisdiction_level`	No	federal, state and/or multistate, comma-separated.

Schema Changelog

Changes observed during successful MCP inspections.

Changed3 schema fields changedAug 22, 2026

changedInput schema / properties / date_from / description

Previous value: -"Filed on or after (YYYY-MM-DD). NOTE: filed_date is null on most matters, so a date filter excludes the undated majority."New value: +"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."

changedInput schema / properties / sort / enum

Previous value: -[
-  "filed_date",
-  "first_seen_at",
-  "last_verified_at",
-  "closed_date"
-]New value: +[
+  "filed_date",
+  "decided_date",
+  "first_seen_at",
+  "last_verified_at",
+  "closed_date"
+]

addedInput schema / properties / tier

Added value: +{
+  "description": "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.",
+  "type": "string"
+}

AddedAug 22, 2026

TDQS

A4.5/5.0

Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already mark the tool read-only and open-world, but the description adds substantial behavioral detail beyond that: every matter is recorded from a single official source, claims must be attributed to that source, and 123 of 254 monitored sources are currently stale. It also warns that results are informational and not legal advice, which meaningfully shapes how an agent should use the output.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is dense but every sentence earns its place: scope, filters, result interpretation, single-source warning, stale-data caveat, attribution, and licensing. It is front-loaded with the core purpose and then layers critical usage caveats in a logical order.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity (15 optional parameters, no output schema), the description covers the essential return fields, filtering behavior, data provenance, and interpretation pitfalls. An agent has enough context to call this tool correctly and avoid overstating the results.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 93%, so the schema carries most of the parameter documentation burden. The description reinforces key semantics like 'q searches caption, summary and agency' and notes row-level granularity, but it does not add substantial new meaning beyond the schema for most of the 15 parameters.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a specific verb ('Search'), a precise resource ('regulatory enforcement actions and litigation involving AI'), and a granularity ('at MATTER level: one row per dispute'). It lists the relevant agencies and the fields returned, making it clearly distinguishable from sibling tools like get_enforcement_matter or search_ai_laws.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description states what can be filtered by, what `q` searches, and adds explicit guidance on interpreting results: an empty result means no matching matter, not that no action was taken, and stale sources are noted with a pointer to list_enforcement_sources. It does not explicitly exclude alternatives such as get_enforcement_coverage, but the context and caveats are sufficiently clear.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All AI Law Tracker tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?