Live network intelligence

Observed across the agent economy.

The base rates behind agent infrastructure: what answers, how long listings have existed, which tools they expose, and where payment activity is visible. Everything below is counted from 2,105 research records and 710 unpaid probes in the observation archive as of 2026-08-11. Where the archive is thin, the chart says so.

What this page counts
Research records2,105
Answering when called1,121
Unpaid probes710
Listings with payment terms411
Latest record2026-08-11
Every figure below is a count, never a forecast.
§ 01

Reachability: most of the catalogue does not answer.

Two independent measurements. Liveness comes from the observation sweep across every research record; the status taxonomy comes from unpaid HTTP probes against listed x402 endpoints.

Unpaid probe outcomes

69% of probes produced a qualifying response — 2xx, 3xx, or a 402 payment challenge. A 404 or 405 means the listed path is not where the catalogue says it is.

HTTP status returned to an unpaid probe 402 payment req. 462; 405 method n/a 105; 404 not found 94; 200 served 28; 400 bad request 8; 401 unauthorized 5; none no answer 3; 530 other 2; 525 other 1; 521 other 1; 403 forbidden 1 402 payment req.: 462462402payment req.405 method n/a: 105105405method n/a404 not found: 9494404not found200 served: 2828200served400 bad request: 88400bad request401 unauthorized: 55401unauthorizednone no answer: 33noneno answer530 other: 22530other525 other: 11525other521 other: 11521other403 forbidden: 11403forbidden

Counted from 710 unpaid probe records, latest 2026-08-12. A snapshot, not a trend.

Response latency of endpoints that answered

Mean 417ms. An agent paying per call feels this directly.

Probe latency distribution under 100ms 76; 100– 300ms 319; 300ms– 1s 278; over 1s 37; no answer 0 under 100ms: 7676under100ms100– 300ms: 319319100–300ms300ms– 1s: 278278300ms–1sover 1s: 3737over1sno answer: 00noanswer

Measured response time recorded with each probe. A snapshot, not a trend.

Liveness by listing type

A registry entry is a claim, not a service. Across the observation sweep, 41% of listed MCP servers answered an initialize call, against 70% of x402 endpoint hosts.

Liveness by listing type x402 hosts — answered 936; x402 hosts — silent 401; MCP servers — answered 185; MCP servers — silent 266 x402 hosts — answered x402 hosts — answered: 936 936 x402 hosts — silent x402 hosts — silent: 401 401 MCP servers — answered MCP servers — answered: 185 185 MCP servers — silent MCP servers — silent: 266 266

Counted from the liveness sweep of 2026-08-11. A snapshot, not a trend.

§ 02

Tenure: this market is new, and it shows.

Seller-owned domain registration age for x402 endpoint hosts, read from RDAP. Shared platform hosts are excluded from tenure credit, which is why the unknown column is large.

Domain registration age

40% of hosts with an attributable domain registered it in the last 90 days.

Seller-owned domain age under 90 days 357; 90d– 1 year 340; 1–3 years 72; over 3 years 127; shared or unknown 660 under 90 days: 357357under90 days90d– 1 year: 34034090d–1 year1–3 years: 72721–3yearsover 3 years: 127127over3 yearsshared or unknown: 660660shared orunknown

Domain registration dates read from RDAP for 1,556 endpoint hosts. A snapshot, not a trend.

Catalogue coverage

The archive tracks 36,484 catalogue entries. A research record — RDAP, wallet, llms.txt, tool inventory — exists for 5.8% of them so far.

Coverage of the tracked universe MCP registry entries tracked 21,221; MCP research records built 549; x402 catalogue entries tracked 15,263; x402 research records built 1,556 MCP registry entries tracked MCP registry entries tracked: 21,221 21,221 MCP research records built MCP research records built: 549 549 x402 catalogue entries tracked x402 catalogue entries tracked: 15,263 15,263 x402 research records built x402 research records built: 1,556 1,556

Counted from catalogue history and the research records held today.

§ 03

Tool surface: what an MCP server actually exposes.

Tool counts are inventoried by completing an initialize handshake and calling tools/list. A server that will not answer has no inventory, which is itself the finding.

Tools per MCP server

Inventoried for 247 of 549 servers with a research record.

Tools per MCP server 0 tools 0; 1–5 tools 99; 6–20 tools 115; 21+ tools 33; no inventory 302 0 tools: 000tools1–5 tools: 99991–5tools6–20 tools: 1151156–20tools21+ tools: 333321+toolsno inventory: 302302noinventory

Tool inventories recorded when each server was last researched.

Machine-readable posture of x402 hosts

Whether the seller has done the work an agent needs: documentation an LLM can read, and parseable payment terms.

Host posture Publishes llms.txt 910; No llms.txt 646; Declares a payee wallet 411; Behind a CDN 1,550 Publishes llms.txt Publishes llms.txt: 910 910 No llms.txt No llms.txt: 646 646 Declares a payee wallet Declares a payee wallet: 411 411 Behind a CDN Behind a CDN: 1,550 1,550

Read from the research record held for each listing.

§ 04

Money: almost nothing is moving yet.

Inbound USDC observed on Base at declared payee wallets, inside a disclosed block range. Observed inflow is not revenue, and a wallet declaration does not establish legal ownership.

Wallets scanned58declared on listings
With any inflow916% of scanned
Inbound transfers153observed total
Total observed inflow11.86USDC, all wallets combined

Observed inflow by wallet

Every wallet with at least one observed inbound transfer, largest first. The entire observed market is 11.86 USDC.

Observed USDC inflow by wallet 0x4aAbE1…C1DF26 · 8 tx · 2 payer(s) 6.008; 0x52Ab53…4b6C06 · 70 tx · 5 payer(s) 4.9; 0x970007…40D3Ab · 26 tx · 1 payer(s) 0.669; 0x72f62d…F3396c · 3 tx · 1 payer(s) 0.101; 0x2b6D49…FC32C5 · 26 tx · 5 payer(s) 0.066; 0xf444ab…9514a0 · 5 tx · 3 payer(s) 0.06; 0xdCEca2…A67566 · 4 tx · 2 payer(s) 0.04; 0x44b169…a6cdd3 · 1 tx · 1 payer(s) 0.01; 0x127462…5cD0B6 · 10 tx · 7 payer(s) 0.01 0x4aAbE1…C1DF26 · 8 tx · 2 payer(s) 0x4aAbE1…C1DF26 · 8 tx · 2 payer(s): 6.008 USDC 6.008 0x52Ab53…4b6C06 · 70 tx · 5 payer(s) 0x52Ab53…4b6C06 · 70 tx · 5 payer(s): 4.9 USDC 4.9 0x970007…40D3Ab · 26 tx · 1 payer(s) 0x970007…40D3Ab · 26 tx · 1 payer(s): 0.669 USDC 0.669 0x72f62d…F3396c · 3 tx · 1 payer(s) 0x72f62d…F3396c · 3 tx · 1 payer(s): 0.101 USDC 0.101 0x2b6D49…FC32C5 · 26 tx · 5 payer(s) 0x2b6D49…FC32C5 · 26 tx · 5 payer(s): 0.066 USDC 0.066 0xf444ab…9514a0 · 5 tx · 3 payer(s) 0xf444ab…9514a0 · 5 tx · 3 payer(s): 0.06 USDC 0.06 0xdCEca2…A67566 · 4 tx · 2 payer(s) 0xdCEca2…A67566 · 4 tx · 2 payer(s): 0.04 USDC 0.04 0x44b169…a6cdd3 · 1 tx · 1 payer(s) 0x44b169…a6cdd3 · 1 tx · 1 payer(s): 0.01 USDC 0.01 0x127462…5cD0B6 · 10 tx · 7 payer(s) 0x127462…5cD0B6 · 10 tx · 7 payer(s): 0.01 USDC 0.01

Observed inbound USDC transfers on Base, scanned through 2026-08-11T16:34:15.565Z. Inflow is not revenue.

Wallet balance snapshots

A balance is not revenue and not inflow — it is a point-in-time reading at the declared address. Most declared wallets hold under one dollar.

Declared wallet USDC balance zero 18; under 1 USDC 129; 1–100 USDC 228; 100–1k USDC 11; over 1k USDC 7; not read 1,163 zero: 1818zerounder 1 USDC: 129129under1 USDC1–100 USDC: 2282281–100USDC100–1k USDC: 1111100–1kUSDCover 1k USDC: 77over1k USDCnot read: 1,1631,163notread

Balance of each declared payment wallet at the last scan.

Observed modal price per call

The most common inbound transfer size at each active wallet — the closest observable proxy for a list price. Agent commerce is priced in fractions of a cent to a few cents.

Modal observed price per call $0.001 1; $0.0025 1; $0.003 1; $0.01 3; $0.05 2; $1 1 $0.001: 11$0.001$0.0025: 11$0.0025$0.003: 11$0.003$0.01: 33$0.01$0.05: 22$0.05$1: 11$1

Most common observed transfer size across 9 wallets. Observed transfers, not published prices.

§ 05

Concentration: one wallet, many listings.

A declared payee wallet appearing across dozens of catalogue entries changes what a payment record proves. Model 1.0 discounts financial-evidence credit when the wallet is shared or the payer set is narrow.

Most-reused payee wallets

411 listings declare a payee across only 231 distinct wallets.

Listings per declared payee wallet 0x52Ab53…4b6C06 58; 0x6E8B64…064E2E 54; 0xFFc458…E537b1 19; 0x8C128f…5Df1b2 10; 0xf444ab…9514a0 5; 0x6302D9…35Ad57 4; 0x1Ee427…F3b5A8 4; 0x10800a…427dE0 4 0x52Ab53…4b6C06 0x52Ab53…4b6C06: 58 58 0x6E8B64…064E2E 0x6E8B64…064E2E: 54 54 0xFFc458…E537b1 0xFFc458…E537b1: 19 19 0x8C128f…5Df1b2 0x8C128f…5Df1b2: 10 10 0xf444ab…9514a0 0xf444ab…9514a0: 5 5 0x6302D9…35Ad57 0x6302D9…35Ad57: 4 4 0x1Ee427…F3b5A8 0x1Ee427…F3b5A8: 4 4 0x10800a…427dE0 0x10800a…427dE0: 4 4

Payment addresses as declared by each listing, not proof of ownership.

Payer diversity at active wallets

How many distinct addresses actually paid. A single-payer wallet cannot distinguish a real customer from the operator testing their own endpoint.

Distinct payers per wallet 0x4aAbE1…C1DF26 · top payer 50% 2; 0x52Ab53…4b6C06 · top payer 53% 5; 0x970007…40D3Ab · top payer 100% 1; 0x72f62d…F3396c · top payer 100% 1; 0x2b6D49…FC32C5 · top payer 62% 5; 0xf444ab…9514a0 · top payer 40% 3; 0xdCEca2…A67566 · top payer 75% 2; 0x44b169…a6cdd3 · top payer 100% 1; 0x127462…5cD0B6 · top payer 30% 7 0x4aAbE1…C1DF26 · top payer 50% 0x4aAbE1…C1DF26 · top payer 50%: 2 2 0x52Ab53…4b6C06 · top payer 53% 0x52Ab53…4b6C06 · top payer 53%: 5 5 0x970007…40D3Ab · top payer 100% 0x970007…40D3Ab · top payer 100%: 1 1 0x72f62d…F3396c · top payer 100% 0x72f62d…F3396c · top payer 100%: 1 1 0x2b6D49…FC32C5 · top payer 62% 0x2b6D49…FC32C5 · top payer 62%: 5 5 0xf444ab…9514a0 · top payer 40% 0xf444ab…9514a0 · top payer 40%: 3 3 0xdCEca2…A67566 · top payer 75% 0xdCEca2…A67566 · top payer 75%: 2 2 0x44b169…a6cdd3 · top payer 100% 0x44b169…a6cdd3 · top payer 100%: 1 1 0x127462…5cD0B6 · top payer 30% 0x127462…5cD0B6 · top payer 30%: 7 7

Distinct paying addresses observed per wallet in the scanned block range.

§ 06

Daily activity.

One point per archive day. The observatory archive opened 2026-08-11 and holds 2 day(s), so these series are as long as the record allows and no longer.

Catalogue entries added

New listings appearing in the tracked catalogues each archive day.

Catalogue entries added per day 2 observation day(s) from 2026-08-11 to 2026-08-12. Minimum 378, maximum 36,106. 2026-08-11: 36,1062026-08-12: 378 2026-08-11 2026-08-12

Counted from catalogue sweep history.

Probes run

Unpaid endpoint probes executed each archive day.

Probes per day 2 observation day(s) from 2026-08-11 to 2026-08-12. Minimum 150, maximum 560. 2026-08-11: 1502026-08-12: 560 2026-08-11 2026-08-12

Counted from the unpaid probe log.

Observed USDC inflow

Inbound transfers to all scanned payee wallets each archive day.

Observed USDC inflow per day 1 observation day(s) from 2026-08-11 to 2026-08-11. Minimum 11.864, maximum 11.864. 2026-08-11: 11.864SINGLE ARCHIVE DAY — NO TREND EXISTS YET 2026-08-11 2026-08-11

Daily totals of observed inbound USDC transfers.

Why these are single points. The observatory began archiving 2026-08-11. A trend line drawn through one observation would be a decoration, not a measurement, so we draw the observation and label the gap. Each series extends automatically as archive days accumulate.

How to cite this page

MCP Scores / MCP Authority, observatory archive as of 2026-08-11, model 1.0. Underlying counts are reproducible through the public JSON API. If a figure here contradicts something you can measure, tell us — that is a correction, and we publish those.