The Agent Trust Index
One number for a hard question: how safe is the agentic web to actually transact on? We fuse three firsthand, read-only measurements into a single score, updated every week. Higher is safer.
Composite withheld: supply-chain scanner method changed this quarter; its exposure rate is a re-baseline, not a delta, so the composite is withheld until all three pillars share a stable method. The two pillars measured the same way as last quarter are shown below with their deltas.
The three pillars
Each pillar is 100 − the share at risk, so a low score means a large share of the population is exposed. The composite is the equal-weighted mean of the three.
What sits behind the score
The score measures whether agents are safe to transact; these measure that they already are transacting. Full data on /security and /data.
The series
The composite, captured every weekly sweep. The question it answers over time: is the agentic web getting safer as it professionalizes, or just bigger?
Methodology & honest caveats
Method v1 (2026-06). Every input is a firsthand, read-only static measurement of the public MCP server population. We never connect to, run, install, or probe a server. Aggregate statistics only; per-repo findings go to maintainers through coordinated disclosure, never into a public list.
Lower bounds. The detectors are tuned for precision over recall, so each pillar is conservative: the true exposure is at least this high. Equal weighting is a deliberate v1 choice, published so it can be argued with and versioned when it changes.
Major Labs, The Agent Trust Index (2026). Composite withheld this sweep, method v1 (2026-06). majorlabs.co/trust, accessed 2026-10-19. Machine-readable: trust-index.json.