Every figure below is the sentence the matching Sato Hub numbers page is serving right now, quoted as it stands, with the week-over-week change of the same series beside it. Nothing here is restated in different words, and nothing is carried over from a previous week: a series with one reading shows "no prior reading" rather than a change of zero. Readings are as of 2026-10-19.
Agents registered on ERC-8004, by chain
Registered agents per chain: 0G 3,930,426, BNB Chain 376,321, Base 256,649 and 23 more chains; chains are never added together, as of 2026-10-19.
| What | This week | Change on last week | |---|---|---| | 0G | 3,930,426 registered | no prior reading — one weekly reading banked so far | | BNB Chain | 376,321 registered | +4,347 | | Base | 256,649 registered | +165,403 | | Ethereum | 54,279 registered | +1,600 | | Abstract | 16,919 registered | no prior reading — one weekly reading banked so far | | X Layer | 15,062 registered | no prior reading — one weekly reading banked so far | | MegaETH | 12,727 registered | no prior reading — one weekly reading banked so far | | Monad | 10,414 registered | no prior reading — one weekly reading banked so far |
Method, coverage and the chains or pairs behind this figure: https://satohub.ai/numbers/erc-8004-agents-by-chain. Measured against ERC-8004 — Trustless Agents (the EIP), ERC-8004 reference implementation.
x402 payment endpoints that actually answer
11 of the 12 x402 payment endpoints we reached replied with valid payment terms; nothing was paid, as of 2026-10-19.
| What | This week | Change on last week |
|---|---|---|
| Paid resources (named in a /.well-known/x402 manifest) answering a parseable HTTP 402 | 11 | no prior reading — the probe is a point-in-time run, not a banked weekly series |
| x402 sellers registered (venue stage selling) | unknown | no prior reading — one weekly reading banked so far |
| x402 settlements observed (venue stage settling) | unknown | no prior reading — one weekly reading banked so far |
Method, coverage and the chains or pairs behind this figure: https://satohub.ai/numbers/x402-endpoints-that-answer. Measured against x402 — protocol specification, RFC 9110 §15.5.3 — HTTP 402 Payment Required.
Listed crypto MCP servers that answered a handshake
53 of 84 listed crypto MCP servers answered and listed their tools without a key; 25 asked for a key and 6 did not connect, as of 2026-10-19.
| What | This week | Change on last week |
|---|---|---|
| Endpoints that answered initialize + tools/list anonymously | 53 | no prior reading — a daily point-in-time check of other people's servers, not a banked weekly series |
Method, coverage and the chains or pairs behind this figure: https://satohub.ai/numbers/mcp-servers-that-answer. Measured against Model Context Protocol — the initialize handshake.
The Uniswap fee tier carrying the most observed volume
The 0.01% fee tier carries the most Uniswap v3 volume for 3 of 7 agent pairs on 3 chains, as of 2026-10-19.
| What | This week | Change on last week | |---|---|---| | cbbtc-weth on Base | 0.05% tier leads | no prior reading — the log walk is capped, so the covered window is 1.539 days, not a week | | usdc-usdt on Base | 0.01% tier leads | no prior reading — the log walk is capped, so the covered window is 1.539 days, not a week | | weth-usdc on Base | 0.3% tier leads | no prior reading — the log walk is capped, so the covered window is 1.516 days, not a week | | usdc-usdt on Ethereum | 0.01% tier leads | no prior reading — the log walk is capped, so the covered window is 7 days, not a week | | wbtc-weth on Ethereum | 0.05% tier leads | no prior reading — the log walk is capped, so the covered window is 7 days, not a week | | weth-usdc on Ethereum | 0.3% tier leads | no prior reading — the log walk is capped, so the covered window is 7 days, not a week |
Method, coverage and the chains or pairs behind this figure: https://satohub.ai/numbers/uniswap-fee-tiers-for-agent-pairs. Measured against Uniswap — fee tiers and how swap fees accrue, Uniswap v3 core — the pool contract these readings come from.
Score movers
Across 460 listings carrying a Sato Score on both days between 2026-10-12 and 2026-10-19, 8 rose and 8 fell, 8 crossed a tier boundary, and 29 were scored for the first time. Every reading is a daily snapshot; a day nobody measured is a gap and is never carried forward, and the Sato Score is how open, active and verifiable a project is — not a safety, quality or returns grade.
| What | This week | Change on last week | |---|---|---| | Nodit MCP Server | 79 (High) | +22 · maintenance 13→35 | | TensorFeed x402 Base MCP | 75 (High) | +18 · maintenance 25→35 | | Daydreams | 81 (High) | +15 · maintenance 20→35 | | EruditePay Blockchain Intelligence | 34 (Low) | -30 · maintenance 35→5 | | hood.fun | 22 (Low) | -15 · maintenance 20→8 | | RugCheck | 20 (Low) | -12 · maintenance 20→8 |
Method, coverage and the chains or pairs behind this figure: https://satohub.ai/movers. Measured against Nodit MCP Server — the project's own source, TensorFeed x402 Base MCP — the project's own source, Daydreams — the project's own source, EruditePay Blockchain Intelligence — the project's own source.
What arrived in the directory
29 listings were added to the Sato Hub directory and 34 published a release in the last 7 days, as of 2026-10-19: Agent Control, AkashML, Chutes, Circle Gateway Nanopayments, Crossmint, deBridge DLN. Each is an observed event with a date and a link to its own source, never an endorsement.
The rows, with the source for each: https://satohub.ai/launches.
What we corrected
Over the last 6 months Sato Hub added 349 listings and retired 3, recorded 0 verification changes, applied 1 corrections from 0 verified claims, and decided 24 submissions. The ledger behind that sentence, month by month, is at https://satohub.ai/transparency.
How to check any of this
Every figure above is derived at page-render time from Sato Hub's own tables and from public chain and registry reads. The free catalogue export is at https://satohub.ai/api/export/index.json and the current-week adoption rows at https://satohub.ai/api/export/adoption.json, both CC-BY-4.0. Over MCP: onchain_agent_get_metrics, onchain_agent_get_trend and onchain_agent_explain_number, which returns the method for any of these.
A figure here is never summed across venues, chains or stages — those rows do not add — a sampled rate is never multiplied by a population, and an unknown is an unknown, never a zero.