Skip to content
Report · auto-updating

State of the agent economy

Live measurement of the agent web: supply funnel, live-rate by ecosystem, protocol adoption, inflow concentration, and 30-day growth. Data refreshes every five minutes from the same observability spine that powers every public Agenstry page.

As of 2026-11-09 11:34:29 UTC methodology JSON CSV cite this archive
Weekly briefing · 2026-W43 archived view
Oct 19, 2026

Week 43 is opening with a wider live surface, but not yet with evidence of a more mature or evenly distributed agent economy. Agenstry’s indexed corpus rose to 9,531 listings and live endpoints to 1,329; meanwhile, recent revenue remains highly concentrated, and the current week’s protocol cohort is only a partial-week snapshot as of Monday, October 19.

Reach is growing faster than verified operation

Indexed listings increased by 610 week over week (+6.8%), while live endpoints rose by 230 (+20.9%). That is a stronger gain in operationally probeable services than in listings overall. Yet the funnel remains steep: 8,233 listings returned a parseable A2A/MCP card, but only 1,329 were live on JSON-RPC or introspectable MCP, and 171 published a JWS signature. The distinction matters for buyers and integrators: a discoverable card is not the same as a working endpoint, and neither establishes signed identity.

The source mix reinforces that point. The registry and A2A Registry listings have live rates of 57.4% and 65.7%, respectively, while agentic_market is at 5.1% and cdp_discovery at 5.6%. These are source-level rates, not directly comparable quality rankings: source populations may differ in how they select and describe listings. Still, the gap suggests that discovery coverage is broader than reliable runtime availability.

Payments: x402 dominates the measured surface

Among listings with payment-protocol evidence, x402 is the clear center of gravity: the corpus records 5,442 x402 listings, against 129 for MPP, 73 for A2A x402, and 38 for AP2. The W43 cohort shows 35 x402 entries and no entries for the other listed payment protocols—but the cohort begins October 19, so it is a partial week and should not be read as a weekly adoption comparison with W42’s 592.

Evidence quality remains an important qualification. Agenstry labels 5,687 payment-protocol records; 2,623 are self-declared live, meaning the endpoint itself answered an unpaid request with a 402 challenge or served an x402 manifest. The dataset notes that runtime challenges are authoritative; static cards, directories, and catalog entries are weaker evidence. This distinction is relevant as implementation work continues: the x402 Foundation repository’s current issue tracker shows active discussions and reported bugs involving payment-header compatibility, settlement retries, response sizes, and browser access. Those entries are issue reports and proposals, not proof that the underlying problems are widespread or unresolved.

Revenue remains concentrated

Over the measured 30-day window, gross receipts were $912,688.77 across 3,345 earning listings, with a median of $0.32. The top seller accounts for 73.4% of receipts, the top 10 account for 93.6%, and the Gini coefficient is 0.995. Week over week, the earning-listing count rose by 136 (+4.2%), while the supplied Gini delta moved from 0.994 to 0.995.

These figures describe Agenstry’s scanned wallet-linked sample, not the whole ecosystem. The measurement covers wallets scanned so far—2,629 of 2,714 listings with a wallet—and multiple listings can share one wallet. Nor is “earning” a subset of “live”: many paid APIs return a 402 challenge instead of answering a free JSON-RPC probe. The concentration signal is therefore useful as a view of observed settlement, but should not be mistaken for a complete market-share estimate.

Protocol governance and implementation

There was no confirmed major specification release in the sources reviewed for this week. The latest notable A2A project announcements found were earlier: the project’s October 1 post introduced its CLI, while its August announcement described joining the Agentic AI Foundation. For MCP, the most relevant official update located was the August roadmap, rather than a release published during W43. The distinction is worth keeping: protocol roadmaps and governance changes set direction, but do not on their own establish that deployed agents interoperate reliably.

What to watch next week

The immediate question is whether W43’s x402-heavy intake persists once the week is complete, and whether new listings convert into live, independently probeable services. The next full-week comparison should separate genuine adoption from Monday’s partial cohort effect and track runtime evidence alongside registry growth.

Sources

  1. x402 Foundation repository’s current issue tracker
  2. October 1 post introduced its CLI
  3. August roadmap
1 · Supply funnel

Most of the agent economy is indexed, not yet operational.

Counting agents conflates supply with operation. Below is the corpus broken into five stages: what fraction of indexed agents pass each gate. The decay curve is the honest read on how mature the agent web is at any given moment.

Stage Count % of indexed Definition
Indexed 11,443
100.0%
Every listing we hold across every source; 3,638 archived listings are not counted here or in any step below.
Valid card 9,963
87.1%
Returned a parseable A2A/MCP card on probe.
Live 1,737
15.2%
Live JSON-RPC / introspectable MCP.
Signed 267
2.3%
Card published with a JWS signature.
Earning (30d) 4,919
43.0%
Listings whose declared payTo wallet received inbound USDC in the last 30 days (2,216 distinct wallets; several listings can share one). Measured over the wallets scanned so far (3,005 of 3,232 with a wallet) — not an ecosystem-wide total. Not a subset of Live: most are paid APIs, which answer 402 rather than a free JSON-RPC probe.
2 · Live-rate by ecosystem

Which source registries actually ship live agents.

Each row shows one source registry (Anthropic's MCP directory, Smithery, Glama, Postman, GitHub well-knowns, Wayback CDX scans) alongside how many of the agents it lists actually respond live on probe. The gap between seen-count and live-count is the source's effective freshness.

Source Seen Live Live rate
agentic_market 5,947 304 5.1%
cdp_discovery 5,582 389 7.0%
manifests 2,378 583 24.5%
mcp_registry 1,747 281 16.1%
n8n_workflows 1,479 0 0.0%
x402_list 1,456 204 14.0%
smithery 1,080 272 25.2%
registry 1,001 588 58.7%
github_code 906 85 9.4%
a2aregistry 845 553 65.4%
a2a_registry_org 836 486 58.1%
lists 563 68 12.1%
8004scan 247 69 27.9%
dexter_discovery 217 2 0.9%
github_topics 165 9 5.5%
3a · By protocol kind

A2A vs MCP vs paid_api

paid_api
6,492
a2a_agent
3,472
workflow
1,479
3b · By observed payment-protocol label

Index composition, not global market share. x402 has multiple dedicated catalogs and a live HTTP probe; AP2, L402 and Stripe ACP are predominantly visible only when cards declare them.

x402 / AP2 / Stripe MPP / L402

x402
6,766
mpp
135
a2a_x402
98
ap2
45
l402
6
stripe_acp
1
3b · Evidence grade

How we know they take payment

3,572 of 7,051 payment-labelled agents (50.7%) proved it themselves — their own endpoint answered an unpaid request with an HTTP 402 challenge, or the host serves a /.well-known/x402 manifest. The rest is declared in a static agent card or described by a third-party catalog.

Live 402 challenge
2,931
Facilitator feed
2,293
Agent card
752
/.well-known/x402
500
Catalog listing
422
mpp_manifest
105
mpp_challenge
36
Official protocol directory
12
3c · Indexed protocol labels over time · last 12 weeks

Newly indexed agents per week, by payment label

Changes reflect both ecosystem activity and changes in crawler source coverage.

2026-W34 · a2a_x402: 1 2026-W34 · ap2: 1 2026-W34 · mpp: 4 2026-W34 · x402: 174 34 2026-W35 · a2a_x402: 4 2026-W35 · ap2: 4 2026-W35 · mpp: 1 2026-W35 · x402: 156 2026-W36 · a2a_x402: 3 2026-W36 · mpp: 1 2026-W36 · stripe_acp: 1 2026-W36 · x402: 318 36 2026-W37 · a2a_x402: 5 2026-W37 · mpp: 1 2026-W37 · x402: 263 2026-W38 · a2a_x402: 2 2026-W38 · ap2: 1 2026-W38 · mpp: 7 2026-W38 · x402: 160 38 2026-W39 · a2a_x402: 4 2026-W39 · ap2: 1 2026-W39 · mpp: 1 2026-W39 · x402: 240 2026-W40 · a2a_x402: 3 2026-W40 · ap2: 7 2026-W40 · mpp: 8 2026-W40 · x402: 469 40 2026-W41 · a2a_x402: 4 2026-W41 · ap2: 3 2026-W41 · mpp: 3 2026-W41 · x402: 360 2026-W42 · a2a_x402: 10 2026-W42 · ap2: 2 2026-W42 · mpp: 7 2026-W42 · x402: 456 42 2026-W43 · a2a_x402: 2 2026-W43 · ap2: 2 2026-W43 · mpp: 9 2026-W43 · x402: 596 2026-W44 · a2a_x402: 4 2026-W44 · ap2: 1 2026-W44 · l402: 2 2026-W44 · mpp: 4 2026-W44 · x402: 712 44 2026-W45 · a2a_x402: 18 2026-W45 · ap2: 4 2026-W45 · mpp: 3 2026-W45 · x402: 402 2026-W46 · x402: 24 46
a2a_x402 ap2 l402 mpp stripe_acp x402
4 · Inflow concentration · 30d

A few settlement wallets receive most of the money.

Across 2,216 earning wallets backing 4,919 linked services, the distribution is heavily power-law. Wallet-level Gini and HHI avoid multiplying transfers when several catalog entries share one recipient.

Observed inflow · 30d
$932,990.41
Recipient wallets
2,216
Active sellers · 30d
2,026
Median · wallet
$0.250
p95 · wallet
$95.81
Top 1 share
63.3%
Top 5 share
79.9%
Gini
0.994
extreme inequality
HHI
4098
highly concentrated
5 · 30-day growth

New agents arriving daily, by first-seen.

Daily count of agents we discovered for the first time. Sourced from every registry + open-web crawl we run.

2026-10-11 peak 363/day 2026-11-09
New agents · 30d
+3,370
New earning wallets · 30d
804
first observed earning in the last 30 days
6 · Demand gaps

What the market asked for and didn't get.

Every section above measures the supply we indexed. This one measures demand we couldn't serve: clustered search intents — from browsers, AI assistants and agents calling our A2A and MCP endpoints — where the index returned nothing or almost nothing. Aggregate only, and shown only for intents searched by enough distinct sources to be a market signal rather than one person's session.

Intent Demand Unmet Trend
aidata active 42% new
bitcoin+payment very active 40% rising

Full list + method: what the agent economy is missing. Building one of these? Add pay-per-call payments to your API →

Cite this report

Public domain numbers (CC BY 4.0). Pick the format that fits. The page auto-updates so the URL is the canonical pointer; the date stamps the snapshot you cited.

Plain text
Agenstry Research. "State of the Agent Economy." Accessed 2026-11-09. https://agenstry.com/reports/state-of-agent-economy
BibTeX
@misc{agenstry_state_of_agent_economy,
  title  = {State of the Agent Economy},
  author = {Agenstry Research},
  url    = {https://agenstry.com/reports/state-of-agent-economy},
  note   = {Accessed 2026-11-09},
  year   = {2026}
}
Embed (iframe)
<iframe src="https://agenstry.com/reports/state-of-agent-economy" width="100%" height="900" frameborder="0"></iframe>
Scope What this report measures, and what it doesn't

Inflow figures count public stablecoin transfers into wallets declared by indexed agents. They are reproducible from public chains, but a transfer may be self-funded and is not proof of a sale. See the measurement method.

Private and off-chain payments, and Agenstry's own paid-skill receipts, are excluded. Coverage varies by chain, asset and date.

Methodology

This report uses dated observations from the public index. Check source coverage, scoring rules and the public feed before comparing it with another dataset.