Hosted MCP · U.S. DOL LCA + PERM disclosures

Visa sponsorship data your agents can trust.

Filings turns the Department of Labor’s public LCA and PERM files into one MCP server. Your agent sends a messy company name and gets back the right employer, certified wages and a citation. When a name is ambiguous, it gets candidates instead of a guess.

Keys are issued by hand during the pilot · Works with Claude, Claude Code, Cursor and any MCP client

Your agent filings MCP · connected
Does Google file LCAs for software engineers, and what pay do they certify?
✓identify_employer("Google", state="CA")→ Google LLC · 0.96
✓wage_summary(employer_id, job_title="Software Engineer")→ 5,372 wages
Median certified wage
$195,000
Employer
Google LLC
Cases
5,377 certified
Period
Jul 2025 – Jun 2026
p25 $167kp50 $195kp75 $217k
Google LLC is 1 of 5 legal entities in group Alphabet (Google). These 5,377 cases are for this entity only, not the group total (5,575 with the same filters).
Source: DOL OFLC LCA disclosure · decisions Jul 2025 – Jun 2026 · a real answer, trimmed
3,466,142certified LCA cases (H-1B, E-3, H-1B1) decided through Jun 2026
727,091certified PERM (green card) cases decided through Jun 2026
24DOL disclosure files loaded, FY2020 to FY2026 Q3
Every answercarries as_of, its data window and the source

Why Filings

Your agent’s answers, finally right.

H-1B and green card data that agents can trust, without the spreadsheet work.

01

Ask about any company. Get the right one.

Brand names, typos, old names, even an email address. Filings knows who you mean, and when it isn’t sure, it asks.

“YouTube” → Alphabet (Google) · “jane@stripe.com” → Stripe, Inc. · “Microsft” → “Did you mean Microsoft Corporation?”
02

See the whole company, not just one entity.

Big employers file under many names. Filings shows each one’s own numbers and how they add up to the group.

VMware LLC: 101 certified H-1B LCAs in the last four quarters · Broadcom, the whole group: 280
03

From visa to green card.

Not just H-1B: see who sponsors employees all the way to permanent residence.

“Does Amazon sponsor green cards for engineers?” → yes: 14,216 certified PERM cases for software engineers since 2019, in one call
04

Spot who’s hiring more, and who stopped.

Filings since 2019, ready to compare. Find growing sponsors, new ones, and the ones that went quiet.

“Which companies grew H-1B sponsorship most last year?” → Apple: 3,466 → 6,318 certified LCAs (+2,852), FY2024 to FY2025
05

Answers, not spreadsheets.

Median pay, top employers, the share of new hires: Filings hands your agent the finished number, so it never has to add things up.

“Is $140k fair for a data scientist in Seattle?” → about the 32nd percentile of 268 certified H-1B wages; median $163,322
06

Straight about what it doesn’t know.

No made-up lottery odds or approval rates. Every answer says where it comes from and how recent it is.

“Do H-1B transfers get approved faster?” → “I can’t answer that from this data: it has no USCIS approval rates or processing times. It can show how many certified LCAs are transfers vs new hires.” · Source: DOL OFLC, as of 2026-06-30

90–95% fully correct · at most 3 wrong figures in 100 · about half the cost per correct answer, vs. an agent searching the web itself. See how we measured →

Benchmark

Fewer wrong answers than web search.

90–95%fully correct with Filings, against 65–83% for an agent that searches the web itself
≤ 3 in 100answers with a wrong figure with Filings, against 10–22 of 100 with web search
About halfthe cost per correct answer (API-price estimate)

Same agent, two sets of 105 questions, November 2026, scored without the caveat rule (it favours Filings). The reference figures come from the DOL data Filings serves, which favours Filings. Setup, grading and limits →

Connect

One URL. Your agent is connected.

Filings is a hosted MCP server. There is nothing to install or download: add the URL and your API key to your client, and the tools appear.

Building your own agent? The same tools are on the REST API. Read the docs →

claude mcp add --transport http filings \
  https://filings-api.fly.dev/mcp \
  --header "Authorization: Bearer YOUR_KEY"
Replace YOUR_KEY with your Filings key.

Why agents can rely on it

When a name is ambiguous, Filings doesn’t guess.

“Delta” is an airline, a software firm and two dental insurers. A spreadsheet lookup picks one and moves on. Filings returns assigned: false with the most likely candidates, so your agent asks the user instead of reporting the wrong company.

A wrong employer in a recruiting or sales workflow costs more than a follow-up question. That is the trade-off we make every time.

identify_employer(query="Delta")Unassigned · 5 candidates
"assigned": false,
"reason": "ambiguous",
"candidates": [  // name, confidence
  "Delta Air Lines, Inc."           0.6
  "DELTA SYSTEM & SOFTWARE, INC."   0.3
  "Delta Dental Of California"      0.3
  "Delta Dental Insurance Company"  0.3
  "Delta Computer Consulting"       0.3
]
Real output, trimmed for space.Swipe to see more →

The public file vs Filings

The data is public. Making it usable is the product.

DimensionRaw DOL disclosure fileWhat your agent gets from Filings
Employer namesThe same company under different spellings and entities, quarter after quarterOne stable employer_id, with a confidence and the reason it matched
Ambiguous namesNothing tells you that “Delta” is several different filersNo assignment, ranked candidates, so the agent can ask
Corporate groupsLegal entities are separate rows; there is no group totalEntities roll up into groups for rankings, with a warning whenever an answer covers one entity only
WagesOne row per case, in hourly, weekly or yearly unitsCertified p25, p50 and p75, withheld when there are fewer than 5 cases
Freshness and sourceLarge Excel files to download from dol.gov every quarteras_of, the data window and the OFLC citation on every answer

Methodology

How we resolve an employer

Three rules, applied to every lookup. The reason for each decision comes back in the answer, so your agent can show its work.

Rule 01

Match on name, alias and state

We normalise the name and compare it with legal names and a maintained alias list, using the state when the agent passes it. No language model runs when your agent asks. The alias and group lists are reviewed with the help of AI models, and a name is added only with documented evidence. Every match returns a confidence and a reason.

reason: "alias+state" · 0.96
Rule 02

Assign only when it’s certain

Only a unique match with a confidence of 0.80 or higher gets an employer_id. Anything else comes back unassigned, with candidates and the reason for each.

assigned: false · reason: "ambiguous"
Rule 03

Keep entities and groups apart

Lookalike companies stay apart: a shared brand is not a reason to merge. Entities roll up into their group for rankings, and every entity-level answer says it is not the group total.

group: Alphabet (Google) · 5 entities
≥ 0.80confidence needed before a name is assigned to an employer
0wrong employers allowed on our hand-checked test set, or a new release is not loaded
n ≥ 5certified wages needed before we show percentiles
0language models in an answer: the same question on the same data gets the same answer

Kept apart, on purpose

  • Amazon.com Services≠AWS≠Amazon.com Inc.
  • Waymo LLC≠Google LLC
  • Deloitte Consulting≠Deloitte Tax≠Deloitte & Touche

How agents use it

Three calls. Then stop.

Agents resolve the employer first, then fetch only what they need. Resolving first means a wrong guess never reaches a search.

  1. 01
    Is this the same employer?

    identify_employer with the name and state. If it abstains, the agent picks from the candidates instead of guessing.

  2. 02
    What did they certify?

    search_cases by employer_id: titles, wages and worksites, certified cases only.

  3. 03
    What is this case?

    get_case by case number: one case, its as_of date and the resolved employer.

Need pay ranges? Add wage_summary. It only returns percentiles when there are at least 5 certified wages.

a typical agent run
identify_employer(query="google", state="CA")
# → emp_us_google_llc · 0.96 · alias+state

search_cases(employer_id="emp_us_google_llc",
             job_title="Software Engineer")
# → certified cases: title, wage, worksite

wage_summary(employer_id="emp_us_google_llc",
             worksite_state="CA")
# → p25 / p50 / p75, only if n ≥ 5

get_case(case_number="I-200-25267-331421")
# → one case, as_of, resolved employer

Tools

Twelve tools your agent picks from

Full reference in the docs →
identify_employer

A messy company name, plus state if known, becomes an employer_id. Ambiguous names return candidates.

employer_profile

LCA and PERM totals for one employer, with sample cases.

search_cases

Certified cases by employer, title, city, state, visa class or wage level.

get_case

One LCA or PERM case in full, by case number.

wage_summary

Certified wage percentiles. Withheld below 5 cases.

rank_employers

Rankings over all matching cases: top sponsors, highest median wage, by city or title.

title_search

The most-filed job titles for an employer, a place or a visa class.

list_releases

Every DOL release that is loaded, with as_of dates and row counts.

cite

The official OFLC source, publication date and caveat for the current window.

sponsorship_check

Does a company sponsor, for a role and in a place? A finished answer with certified counts, the latest decision and how the name was matched.

compare_offer

Where a base salary falls among certified wages for a role and place, with the prevailing wage per level.

sponsor_trends

Change over fiscal years: per-year counts, growing and declining sponsors, new and stopped ones.

Ask it like you would ask a colleague

Recruiting agents

Which companies in Austin filed LCAs for data engineers last year, and at what pay?

Has this employer filed PERM cases for this role before?

Sales and GTM agents

Resolve the 400 company names in this CRM export and flag the active sponsors.

Top 10 sponsors of registered nurses in Texas.

Research and HR teams

Median certified wage for level II software engineers in Seattle.

How did this group’s filings change between FY2024 and FY2025?

Coverage

Seven fiscal years, refreshed every quarter

The disclosure files of the Office of Foreign Labor Certification from October 2019 on. When DOL publishes a new quarter, we load it, re-run the matching and test it before it goes live. Your agent can check what is loaded with list_releases.

FY2020LCA + PERM
FY2021LCA + PERM
FY2022LCA + PERM
FY2023LCA + PERM
FY2024LCA + PERM
FY2025LCA + PERM
FY2026FY2026 Q3 · current
Nextnext DOL release
currentFY2026 Q3 windowdecisions through 2026-06-30 sourceOFLC disclosure data, dol.gov

Pricing

Priced per tool call, not per seat.

Prices are not final and nothing is on sale yet. Keys are issued by hand during the pilot, and no payment is taken.

Scope

What Filings is, and what it isn’t

Independent

Filings is not affiliated with the U.S. Department of Labor. We republish its public disclosure files.

Determined cases only

A certified LCA is not a USCIS H-1B approval. Pending cases are not in the files.

Data, not advice

Filings tells you what was filed and certified. It does not give legal or immigration advice.

Cited, every time

Each answer names its data window, as_of date and the OFLC release it came from.

Give your agent the employer, not the spreadsheet.

Keys are issued by hand during the pilot. Connecting takes one command.