47 posts tagged with "AI Agents"

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.

If you are responsible for imports, landed-cost estimates, product classification, or customs review, HTS lookup is not an academic exercise. A wrong code changes margin, delivery timing, and compliance risk.

The first question is usually simple: "What HTS code should we use for this product?" Then the real questions start. Is the description close enough? Is there a more specific subheading? What is the general duty rate? Does a Section 301 surcharge apply? Is the result reliable enough to quote from, or does it need broker review?

The HTS Tariff MCP server is built for that first-pass classification workflow. Your agent can search tariff entries, inspect the hierarchy, pull duty fields, notice surcharge references, and turn the result into a short explanation your team can actually use.

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.

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.

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.

If you run vendor onboarding, finance operations, marketplace trust, logistics compliance, or diligence research, sanctions screening is often one step inside a bigger decision. The team is not asking for a database. They are asking whether a counterparty can move forward.

The question sounds simple: "Is this company or person on a sanctions list?" Then reality gets in the way. Which list? Which alias? Is this a close match or just a similar name? Do we need to record the source list, the country, the identifier, and the reason for the match? Is this a vendor review, a customer onboarding step, or a shipping workflow where denied-party screening is only one part of the decision?

That is what the Global Sanctions & Watchlists MCP server is built for. It gives an agent a normalized sanctions search surface so the lookup can happen inside the workflow that needs the answer.

The average MCP tool description is bad. Two recent arXiv papers measured exactly how bad. 97.1% of analyzed tools carry at least one description smell. 73% of servers reuse the same display_name across multiple tools. In head-to-head selection between five functionally equivalent servers, the one with a clearer description gets picked 72% of the time vs a 20% baseline.

A 260% selection lift from prose alone is the headline. Descriptions aren't documentation; they're part of the agent-facing prompt, and a bad one quietly costs you every selection round your server is in. So we built a scorer.

MCPBundles now runs an LLM-as-judge rubric over every published server, covering tool descriptions, server-level skill content, and the structured MCP annotations that the runtime actually reads. The verdict shows up on the public listing page.

Substack is one of the largest homes for independent newsletters: journalists, analysts, founders, and operators build serious audiences there — often six figures for top writers. But the platform does not ship an official MCP server, and direct API access is thin. That leaves a gap between "read a Substack link in the chat" and "have the AI systematically research, compare, and monitor publications."

MCPBundles closes that gap with a hosted Substack provider (substack) exposing 4 MCP tools — browse any publication's posts, read full article content with HTML, explore all 31 Substack categories, and access your personalized reader feed.

arXiv hosts more than 2.4 million papers across physics, mathematics, computer science, quantitative biology, and more. Researchers, ML engineers, and academics increasingly want the same thing from their AI stack: search papers, read abstracts, follow citations, track new work in a field, and go deeper into full text — all from the same chat thread.

arXiv does not ship an official MCP server. Community implementations exist on GitHub, but they vary in quality, transport, and maintenance. MCPBundles hosts a dedicated arXiv provider (arxiv) with 4 MCP tools backed by the official arXiv Atom API — no API key required, no self-hosting, no config files. Enable the bundle, connect your AI client, and start searching.

MCP Apps are interactive tool outputs that render as rich HTML and CSS inside supported AI clients. Instead of stopping at plain text or raw JSON, an MCP tool can return a full, styled experience: dashboards, charts, forms, data tables, and cards that users can read and interact with in context.

The Model Context Protocol already made it possible for assistants to call tools against live systems. MCP Apps extend that idea: they turn those calls into something that feels closer to a small application than a chat transcript. For anyone searching mcp app or mcp apps, this guide explains what that means technically, why teams care, and how to build one.

Traditional MCP tools return text. AI clients display text well. Many real workflows still need visual output — a stock dashboard, a compliance summary, a project status board, a customer profile. MCP Apps bridge the gap between “the model called a tool” and “the user got something they can actually use on screen.”