We read the agentic web
six to twelve months early.
Operators are already running production agentic workflows. Major Labs measures that activity in real time and publishes quarterly State of reports that call which servers, mandates, and standards become category-defining next. Each report is published alongside its methodology and, where possible, the raw data.
The State of MCP
What the Model Context Protocol unlocked, how far it spread, and the trust layer it still lacks. A field scan of 2,322 servers read against the public security and governance record. Every external claim is source-strength tagged; the scan method and data are open.
The report is a snapshot.
These stay live.
The State of MCP PDF freezes the ecosystem on the day we published. These two tools run on the same Sentinel scan and let you interrogate it yourself: every server, every transport, every license, refreshed each scan pass. The same primary data behind the report, open to your own questions.
MCP Server Picker
Every catalogued server in one filterable index. Sort by reach, filter by transport, language, and license. The fragmented registries, finally made searchable.
MCP Registry Tracker
The population at a glance: transport and language mix, license composition, and maintenance health. 1,841 of 2,413 servers still active, refreshed each scan pass.
Open methodology, source-strength tagged, firsthand scan. Not the inflated registry totals, the servers we independently catalogued.
What this is, and is not
What we do
- Primary data collection. Scans of public infrastructure (MCP servers, agent registries), query studies (citation overlap, AI overview behaviour), and anonymised production telemetry from products we ship.
- Quarterly State of reports. Three per year. Public PDF, open methodology, citable numbers. The category becomes legible because someone measured it.
- Open methodology. Code, scan parameters, query lists, and sampling approach are published alongside each report. Independently reproducible.
What we are not
- Not academic AI research. We do not publish papers on transformer architecture or alignment theory. We work two layers up: the systems built on top of frontier models.
- Not analyst consulting. We do not sell custom decks at Gartner or Forrester rates. The reports are free. The hosted products are priced like dev tools, not like advisory.
- Not corporate research. Anthropic, OpenAI, and the hyperscalers publish their own research aligned with their products. We sit at the network layer and report on what they ship.
Methodology principles
Five rules that decide how a Major Labs report gets written and what it does not contain.
Primary over secondary
If we cite a number, we either collected it ourselves or we link to the primary source that did. No analyst estimates of analyst estimates. No headline charts without raw data behind them.
Reproducible by default
Every State of report ships with the methodology, the scan code, and the data sample. Anyone with a weekend and the right access tokens can reproduce the findings.
Skin in the game
Major Labs ships products into the same categories it reports on. If the MCP Quality Registry is wrong about server security, the registry is the first thing embarrassed. The research has consequences for us.
Vendor-neutral by construction
No fundraising in the first 18 months. No vendor sponsorship of reports. No data deals that compromise the catalogue. The Switzerland position is a deliberate constraint on what we will accept as a business model.
Editorial backbone from Major Matters
The frameworks the reports use (the MM Trust Layer Model, the MM Liability Gap, the agentic commerce stack map) were developed first at Major Matters, tested against two years of news cycles, and adopted into Major Labs as the analytical scaffolding for empirical work. Editorial and empirical research run in parallel. Both are independent of Mastercard.
How the research is produced
The data behind the State of reports is collected by a suite of five named agents we build and run. Each agent has a single scope. The Bench together is the forward indicator machine.
Read about each agent on the home page under The Bench.
Upcoming reports
The full Major Labs research calendar through Q1 2027.
- State of MCP Security
The deep security edition, building on our published field scan of the 10,000-plus active public servers. Active probing of the 910 HTTP-capable endpoints for authentication, input handling, and request-forgery exposure. Open data set. Open scan code.
Q3 2026In progress - State of Agent Commerce
Anonymised production data from BudgetGuard and partner platforms. Per-task spend, loop incidence, kill-switch frequency, refund patterns, and merchant integration depth. Sample size will be disclosed before publication.
Q4 2026Planned - State of Agent Identity
Cross-walk between W3C DIDs, FIDO Agentic Auth, and EUDI Wallet implementations. Coverage gaps and adoption signals across 100-plus deployments. First independent comparative study of the agent identity stack.
Q1 2027Planned
Where this fits in AI research
The AI research landscape has at least four distinct layers. Major Labs sits at the systems layer. The position matters because it is the layer with the least independent coverage.
Primary data on what the agents actually do, where the infrastructure breaks, and which standards survive contact with production. The layer between "the model can do X" and "the buyer pays Y for X."
We read this layer six to twelve months before the discourse catches up.
No one publishes the systems layer independently at scale. Foundation labs cannot (it conflicts with their product position). Academics cannot (the data moves too fast for peer review). Analysts cannot (their methodology is locked behind a paywall and their cadence is annual). The forward indicator is the position.
Get the research
State of reports drop quarterly. Subscribers get the report 48 hours before public release plus the methodology bundle and the raw data sample.
One email per essay (twice weekly). No marketing sends. The quarterly reports go to subscribers first.