Government Index

Firecrawl Government Index searches US federal, state, and local statutes, regulations, codes, court opinions, and other government publications. It helps an agent find the legal or regulatory text behind a question. Ranked matches can also include historical versions, bill text, agency guidance, and third-party reproductions; a match is not a guarantee of current governing law.

Find the regulation that sets a labeling, reporting, or licensing requirement
Read the statute or code section behind a compliance question
Locate a court opinion that interprets a rule
Pull the government publication an agency issued on a topic

Choose and verify sources

Include the jurisdiction, agency or citation, and relevant date when known. Ask for a missing jurisdiction before identifying the governing rule. If the user supplies a source URL, read it directly with scrape instead of searching again. Before answering a current-law question, verify the source’s issuer, jurisdiction, enacted/effective status, and version. Read the source behind a match when the snippet cannot establish the rule. Check a bill’s status and effective date rather than inferring them from its title or digest. Cite the controlling section and supporting passage, and only give a page, section, or effective-date detail that the evidence supports. The index focuses on US material. Use general search for other jurisdictions or missing coverage; no hits does not establish that no applicable law exists.

Endpoints

Task	Endpoint
Search the Government Index	`GET` or `POST /search/gov`

Search the Government Index

Send a natural-language question and get back ranked results from legal and regulatory sources. Results come back in the standard web group, each with url, title, description, and position, the same shape as a web result from /search. Government Index searches are free and use no credits, with or without zero data retention. No API key is needed to get started; add one for higher rate limits. Government Index calls have a daily limit set by your plan, and Scale and Enterprise plans are unlimited. The limit covers /search/gov, the gov category on /search, and the Government Index tool in Alexandria. See rate limits for the limit on each plan. The SDK examples use the Gov methods available in firecrawl 4.44.1 or later and firecrawl-py 4.49.2 or later; filters need later versions. Set FIRECRAWL_API_KEY for the authenticated SDK examples; use the HTTP examples for keyless requests. If an installed client lacks the method, upgrade the SDK. In Python, call gov_search on the initialized client instance; class-only reflection may not list methods assigned during initialization.

# No API key needed to get started; add -H "Authorization: Bearer $FIRECRAWL_API_KEY" for higher rate limits:
curl -s "https://api.firecrawl.dev/v2/search/gov?query=food%20labeling%20requirements%20for%20allergens&k=10"

firecrawl gov "food labeling requirements for allergens" --limit 10

import os
from firecrawl import Firecrawl

client = Firecrawl(api_key=os.environ["FIRECRAWL_API_KEY"])

result = client.gov_search("food labeling requirements for allergens", k=10)
print(result)

import { Firecrawl } from "firecrawl";

const client = new Firecrawl({
  apiKey: process.env.FIRECRAWL_API_KEY,
});

const result = await client.govSearch(
  "food labeling requirements for allergens",
  {
    k: 10,
  },
);
console.log(result);

POST is available on the same path with the same fields as a JSON body:

cURL

# No API key needed to get started; add -H "Authorization: Bearer $FIRECRAWL_API_KEY" for higher rate limits:
curl -X POST https://api.firecrawl.dev/v2/search/gov \
  -H "Content-Type: application/json" \
  -d '{
    "query": "food labeling requirements for allergens",
    "k": 10
  }'

query is required. k sets how many results come back, from 1 to 100, defaulting to 10. Unknown fields are rejected with 400. See the Government Index search reference for the full request and response schema.

Filters

Narrow a search with optional filters: jurisdiction, court, courtType, cites, and domain. They combine with AND semantics. See the reference for the value of each filter. Filters keep only pages the index has labeled, so a filtered search can leave out relevant pages, and no results does not mean none exist. Court labels are most complete for federal courts and case-law collections. An invalid filter value, such as an unknown court id or a citation the index cannot read, returns 400 with the reason. The filters need firecrawl 4.51.0, firecrawl-py 4.54.0, firecrawl-cli 1.26.20, the Elixir firecrawl package 1.12.6, or firecrawl-mcp 3.34.0 or later. Earlier JS SDK versions send only query and k, so a filter passed to them is ignored.

curl -s -G "https://api.firecrawl.dev/v2/search/gov" \
  --data-urlencode "query=qualified immunity" \
  --data-urlencode "jurisdiction=us-ca" \
  --data-urlencode "courtType=state-supreme"

firecrawl gov "qualified immunity" --jurisdiction us-ca --court-type state-supreme

result = client.gov_search(
    "qualified immunity",
    jurisdiction="us-ca",
    court_type="state-supreme",
)

const result = await client.govSearch("qualified immunity", {
  jurisdiction: "us-ca",
  courtType: "state-supreme",
});

The same search is also available on /search as categories: ["gov"], with results in data.web. That category takes only the query; use /search/gov to filter.

The hosted MCP server exposes this index as firecrawl_gov_search, and the CLI as firecrawl gov. Neither writes anything.

Get Started

Core Endpoints

More

Quickstarts

Developer Guides

Webhooks

Use Cases

Other

Contributing

Choose and verify sources

Endpoints

Search the Government Index

Filters

​Choose and verify sources

​Endpoints

​Search the Government Index

​Filters

Choose and verify sources

Endpoints

Search the Government Index

Filters