10 posts tagged with "Data Exploration"

Housing research questions are easy to ask and easy to answer badly.

"Is this county affordable?" "What does HUD say about rent here?" "Which income limit should I use?" "How much cost burden shows up in CHAS?"

A language model alone will blur Fair Market Rent, income limits, MTSP tables, and CHAS affordability data into one vague paragraph. The HUD Housing Data MCP server pulls the official HUD rows first, then explains what they mean — with geography and year range spelled out.

TL;DR​

• Query 30.8 million EPC certificates, 2.7 million UK postcodes, and 1.34 million persisted Land Registry–EPC matches through the UK Property Intelligence app and MCP server.
• Resolve an address or postcode, pull HM Land Registry sold prices, join EPC floor area where the match is strong, and return price-per-square-foot bands with explicit confidence flags—not a black-box valuation.
• Built for lenders, property analysts, retrofit planners, and AI agents who need show your working evidence before formal RICS sign-off.

Most AI valuation demos make the same mistake. A user types an address, the model returns a number, and everyone pretends the answer came from evidence.

That is backwards. UK property questions are only useful when the agent can show its working: nearby sold prices, EPC floor area, property type, transfer dates, postcode geography, match confidence, and the gaps where public data is thin.

We built UK Property Intelligence around that evidence loop — a bounded, inspectable report from sold prices, EPC records, and postcode context, not a false-certainty number.

TL;DR​

• 40,726 officer-year pay records from 4,046 public companies (2017–2025), covering 17,240 named executives parsed from DEF 14A proxy statements, live in the SEC Executive Compensation MCP server.
• Search by ticker, CIK, or executive name and get salary, bonus, stock awards, option grants, and total compensation in structured fields — not buried in a 100-page proxy PDF.
• Built for governance research, comp consulting, investing, and journalism where the question is how much did this executive make, and what drove it?

If you work in governance research, compensation consulting, investing, board advisory, or business journalism, executive compensation data is only useful when you can compare it quickly and explain the components clearly.

The pay data lives in SEC proxy filings. Recent filings include inline XBRL tags, but the human-readable compensation tables still vary across companies. Older filings are even messier. The important numbers are inside long DEF 14A documents, footnotes, named executive officer tables, director compensation tables, pay-vs-performance sections, and company-specific formatting.

The SEC Executive Compensation MCP server is built so an agent can answer pay questions from structured SEC compensation data instead of making a user dig through proxy filings by hand.

TL;DR​

• 4,289 active FDIC-insured institutions — $25T+ in combined reported assets as of 12/31/2025, plus 27,832 total historical rows — are queryable through the FDIC Bank Lookup MCP server.
• Search by bank name, city, state, or certificate number and get structured institution and financial fields back inside the agent or API call, not in a separate BankFind tab.
• Built for fintech risk, treasury ops, vendor diligence, and counterparty verification — the moment someone needs to know whether a bank is active, insured, and how large it is.

If you work in fintech risk, bank partnerships, treasury operations, vendor diligence, or financial research, FDIC data usually appears at the moment someone needs confidence about an institution.

Is this bank FDIC-insured? What is its certificate number? Is it active? How large is it? What do its profitability metrics look like? Can I compare it to another institution without leaving the report I am writing?

The FDIC Bank Lookup MCP server gives AI agents and REST clients structured access to FDIC-insured institution data.

TL;DR​

• Vet 2.19 million active motor carriers — 4.4 million total registered across 117 states and territories — through the FMCSA Carrier Safety MCP server.
• Detail lookups enrich census rows with live crash counts, inspection history, and out-of-service rates from FMCSA QCMobile, so a broker or shipper can vet a DOT number inside the same conversation where the load decision is happening.
• Property carriers no longer publish public BASIC percentile scores (FAST Act 2015); passenger carriers still return BASIC data where available.

Every freight broker, shipper, and logistics team needs to answer the same question:

Can we trust this carrier?

The data exists. FMCSA publishes carrier data, safety records, crash counts, inspection history, out-of-service rates, authority status, and related signals. But the workflow is still clunky. People bounce between SAFER, FMCSA tools, carrier-vetting products, spreadsheets, and internal notes.

The FMCSA Carrier Safety MCP server turns that into a tool an AI agent or backend system can call directly.

TL;DR​

• Query 675,090 public LCA filings across five DOL quarters from 72,477 distinct employers — 659,868 certified and 4,313 denied — through the H-1B Visa Data MCP server.
• Median certified annual wage for Year-unit filings: $133,426. Filter by employer, job title, worksite, and filing period to answer the questions compensation and immigration teams actually ask.
• HR teams, immigration counsel, and recruiters use it for wage benchmarking and sponsor research; job seekers tap the same public corpus without hand-building spreadsheet filters.

H-1B wage data matters because it sits at the intersection of compensation, immigration, recruiting, and employer research.

Job seekers want to know which companies sponsor visas and what they pay. Immigration attorneys and HR teams need wage context for LCA work. Compensation teams want market benchmarks. Recruiters and analysts want employer-level sponsorship patterns.

The H-1B Visa Data MCP server turns public LCA disclosure filings into a searchable workflow for AI agents and REST clients.

TL;DR​

• 1.33 million Form 990 filings from 689,070 organizations across 61 states — full 990, EZ, and private foundation returns — are searchable through the IRS 990 Nonprofit Financials MCP server.
• Pull revenue, assets, expenses, and officer compensation by organization name or EIN, then summarize the numbers in plain language instead of parsing IRS Statistics of Income extract columns by hand.
• Pairs with Nonprofit Lookup: resolve the EIN first, then pull the financial story from the correct entity.

If you work in grantmaking, nonprofit diligence, donor research, journalism, or civic analysis, IRS 990 filings are where the financial story lives. They show revenue, expenses, assets, liabilities, officer compensation, program service activity, and organizational structure.

They are also painful to work with directly.

The data is split across form variants, annual extract files, hundreds of columns, and identity joins. Organization names are not always where people expect them to be. EINs are the stable key, but users often start with a name.

The IRS 990 Nonprofit Financials MCP server turns those filings into a searchable product for AI agents and REST clients.

TL;DR​

• Search 92,525 Senate LDA disclosures from 5,463 registrants representing 22,259 clients through the Federal Lobbying Filings MCP server.
• Automate LD-2 disclosure lookup by client, registrant, issue code, or bill number — then let an agent summarize patterns across filings instead of opening each record by hand.
• Useful for influence research, compliance monitoring, and newsroom investigations where the question is who is lobbying on what, and through whom?

If you are a journalist, policy analyst, advocacy lead, investor, or researcher, lobbying disclosure is useful because it answers a live question about influence.

Who is lobbying for this company? Which clients does this firm represent? What issues are they lobbying on? Has their focus changed over time? Which trade association keeps appearing around the same bill or agency?

The Federal Lobbying Filings MCP server gives AI agents and REST clients a structured way to search and inspect lobbying records.

TL;DR​

• Search nearly two million IRS Business Master File records through the IRS Tax-Exempt Organization Lookup MCP server — 1,628,047 of them active 501(c)(3) charities — by EIN, name, city, or state.
• Grantmakers, donor ops, and compliance teams use it to answer the question that has to come first: which organization is this? Resolve the EIN and tax-exempt subsection before pulling 990 financials or writing a diligence note.
• Coverage spans 63 states and territories; the dataset was last refreshed 2026-04-21.

If you work in grantmaking, donor operations, nonprofit research, or compliance, nonprofit lookup usually starts with one practical problem: you need to know exactly which organization you are looking at.

Is this organization actually tax-exempt? What is its EIN? Is this the same charity as the one in my CRM, or a different organization with a similar name? Can I connect this record to its IRS 990 filings and see the financial picture?

The IRS Tax-Exempt Organization Lookup MCP server turns that into a tool AI agents can call directly. Search by organization name, lookup by EIN, and return structured nonprofit identity data without sending the user into a separate IRS search flow.

Ever stared at a database and thought "where the hell is that data?" You know it's in there somewhere, but you don't know where. That's what this bundle's for.

The Data Exploration MCP server bundle gives you 10 MCP tools to find stuff fast. Browse tables, search across columns, compare datasets, export results. No SQL knowledge required—just ask what you need and the AI figures it out.